feat(hanzo_engine): native-engine node pack over one shared client

Run Hanzo Studio AI workloads on the native-Rust Hanzo Engine instead of in-process Python. Transport, config, and Studio<->engine type conversions live in one client (client.py); each node is one endpoint, so a new engine endpoint is a new small node with no framework change. Nodes (category Hanzo/Engine): HanzoChat (SSE streaming, model dropdown from /v1/models), HanzoImageGen (engine width/height/n schema), HanzoTTS (/v1/audio/speech -> AUDIO), HanzoASR (/v1/audio/transcriptions -> text), HanzoEngineRequest (generic /v1 escape hatch), HanzoVisionCaption, HanzoTextToVideo, HanzoImageTo3D, HanzoSaveText. Config: one way, HANZO_ENGINE_URL (default http://127.0.0.1:1234), /v1/* only. Ships example user/default/workflows/hanzo-native-pipeline.json (LLM prompt -> image prompt -> image gen -> save), e2e-verified against a CPU Qwen3-0.6B engine.
byo-gpu: ship uploaded inputs with the render job
2026-07-09 21:16:03 -07:00 · 2026-07-08 15:50:46 -07:00 · 2026-07-08 15:23:47 -07:00 · 2026-07-07 20:39:47 -07:00 · 2026-07-07 17:35:05 -07:00 · 2026-07-07 16:48:08 -07:00
725 changed files with 23544 additions and 55585 deletions
@@ -0,0 +1,8 @@
+@echo off
+..\python_embeded\python.exe .\update.py ..\HanzoStudio\
+if exist update_new.py (
+  move /y update_new.py update.py
+  echo Running updater again since it got updated.
+  ..\python_embeded\python.exe .\update.py ..\HanzoStudio\ --skip_self_update
+)
+if "%~1"=="" pause
@@ -47,7 +47,7 @@ def pull(repo, remote_name='origin', branch='master'):
 pygit2.option(pygit2.GIT_OPT_SET_OWNER_VALIDATION, 0)
 repo_path = str(sys.argv[1])
 repo = pygit2.Repository(repo_path)
-ident = pygit2.Signature('comfyui', 'comfy@ui')
+ident = pygit2.Signature('hanzo-studio', 'studio@hanzo.ai')
 try:
    print("stashing current changes")  # noqa: T201
    repo.stash(ident)
@@ -153,8 +153,8 @@ if not os.path.exists(req_path) or not files_equal(repo_req_path, req_path):
        pass


-stable_update_script = os.path.join(repo_path, ".ci/update_windows/update_comfyui_stable.bat")
-stable_update_script_to = os.path.join(cur_path, "update_comfyui_stable.bat")
+stable_update_script = os.path.join(repo_path, ".ci/update_windows/update_studio_stable.bat")
+stable_update_script_to = os.path.join(cur_path, "update_studio_stable.bat")

 try:
    if not file_size(stable_update_script_to) > 10:
@@ -1,8 +0,0 @@
-@echo off
-..\python_embeded\python.exe .\update.py ..\ComfyUI\
-if exist update_new.py (
-  move /y update_new.py update.py
-  echo Running updater again since it got updated.
-  ..\python_embeded\python.exe .\update.py ..\ComfyUI\ --skip_self_update
-)
-if "%~1"=="" pause
@@ -1,8 +0,0 @@
-@echo off
-..\python_embeded\python.exe .\update.py ..\ComfyUI\ --stable
-if exist update_new.py (
-  move /y update_new.py update.py
-  echo Running updater again since it got updated.
-  ..\python_embeded\python.exe .\update.py ..\ComfyUI\ --skip_self_update --stable
-)
-if "%~1"=="" pause
@@ -0,0 +1,8 @@
+@echo off
+..\python_embeded\python.exe .\update.py ..\HanzoStudio\ --stable
+if exist update_new.py (
+  move /y update_new.py update.py
+  echo Running updater again since it got updated.
+  ..\python_embeded\python.exe .\update.py ..\HanzoStudio\ --skip_self_update --stable
+)
+if "%~1"=="" pause
@@ -7,22 +7,19 @@ If you have a AMD gpu:

 run_amd_gpu.bat

-If you have memory issues you can try disabling the smart memory management by running comfyui with:
+If you have memory issues you can try disabling the smart memory management by running Hanzo Studio with:

 run_amd_gpu_disable_smart_memory.bat

-IF YOU GET A RED ERROR IN THE UI MAKE SURE YOU HAVE A MODEL/CHECKPOINT IN: ComfyUI\models\checkpoints
+IF YOU GET A RED ERROR IN THE UI MAKE SURE YOU HAVE A MODEL/CHECKPOINT IN: HanzoStudio\models\checkpoints

 You can download the stable diffusion XL one from: https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/sd_xl_base_1.0_0.9vae.safetensors


 RECOMMENDED WAY TO UPDATE:
-To update the ComfyUI code: update\update_comfyui.bat
+To update the Hanzo Studio code: update\update_studio.bat


-TO SHARE MODELS BETWEEN COMFYUI AND ANOTHER UI:
-In the ComfyUI directory you will find a file: extra_model_paths.yaml.example
+TO SHARE MODELS BETWEEN HANZO STUDIO AND ANOTHER UI:
+In the HanzoStudio directory you will find a file: extra_model_paths.yaml.example
 Rename this file to: extra_model_paths.yaml and edit it with your favorite text editor.
-
-
-
@@ -1,2 +1,2 @@
-.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build
+.\python_embeded\python.exe -s HanzoStudio\main.py --windows-standalone-build
 pause
@@ -1,2 +1,2 @@
-.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build --disable-smart-memory
+.\python_embeded\python.exe -s HanzoStudio\main.py --windows-standalone-build --disable-smart-memory
 pause
@@ -1,2 +1,2 @@
-.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build --fast
+.\python_embeded\python.exe -s HanzoStudio\main.py --windows-standalone-build --fast
 pause
@@ -15,20 +15,20 @@ run_cpu.bat



-IF YOU GET A RED ERROR IN THE UI MAKE SURE YOU HAVE A MODEL/CHECKPOINT IN: ComfyUI\models\checkpoints
+IF YOU GET A RED ERROR IN THE UI MAKE SURE YOU HAVE A MODEL/CHECKPOINT IN: HanzoStudio\models\checkpoints

-You can download the stable diffusion 1.5 one from: https://huggingface.co/Comfy-Org/stable-diffusion-v1-5-archive/blob/main/v1-5-pruned-emaonly-fp16.safetensors
+You can download the stable diffusion 1.5 one from: https://huggingface.co/hanzoai/stable-diffusion-v1-5-archive/blob/main/v1-5-pruned-emaonly-fp16.safetensors


 RECOMMENDED WAY TO UPDATE:
-To update the ComfyUI code: update\update_comfyui.bat
+To update the Hanzo Studio code: update\update_studio.bat



-To update ComfyUI with the python dependencies, note that you should ONLY run this if you have issues with python dependencies.
-update\update_comfyui_and_python_dependencies.bat
+To update Hanzo Studio with the python dependencies, note that you should ONLY run this if you have issues with python dependencies.
+update\update_studio_and_python_dependencies.bat


-TO SHARE MODELS BETWEEN COMFYUI AND ANOTHER UI:
-In the ComfyUI directory you will find a file: extra_model_paths.yaml.example
+TO SHARE MODELS BETWEEN HANZO STUDIO AND ANOTHER UI:
+In the HanzoStudio directory you will find a file: extra_model_paths.yaml.example
 Rename this file to: extra_model_paths.yaml and edit it with your favorite text editor.
@@ -1,3 +1,3 @@
-..\python_embeded\python.exe -s ..\ComfyUI\main.py --windows-standalone-build --disable-api-nodes
-echo If you see this and ComfyUI did not start try updating your Nvidia Drivers to the latest. If you get a c10.dll error you need to install vc redist that you can find: https://aka.ms/vc14/vc_redist.x64.exe
+..\python_embeded\python.exe -s ..\HanzoStudio\main.py --windows-standalone-build --disable-api-nodes
+echo If you see this and Hanzo Studio did not start try updating your Nvidia Drivers to the latest. If you get a c10.dll error you need to install vc redist that you can find: https://aka.ms/vc14/vc_redist.x64.exe
 pause
@@ -1,2 +1,2 @@
-.\python_embeded\python.exe -s ComfyUI\main.py --cpu --windows-standalone-build
+.\python_embeded\python.exe -s HanzoStudio\main.py --cpu --windows-standalone-build
 pause
@@ -1,3 +1,3 @@
-.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build
-echo If you see this and ComfyUI did not start try updating your Nvidia Drivers to the latest. If you get a c10.dll error you need to install vc redist that you can find: https://aka.ms/vc14/vc_redist.x64.exe
+.\python_embeded\python.exe -s HanzoStudio\main.py --windows-standalone-build
+echo If you see this and Hanzo Studio did not start try updating your Nvidia Drivers to the latest. If you get a c10.dll error you need to install vc redist that you can find: https://aka.ms/vc14/vc_redist.x64.exe
 pause
@@ -1,3 +1,3 @@
-.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build --fast fp16_accumulation
-echo If you see this and ComfyUI did not start try updating your Nvidia Drivers to the latest. If you get a c10.dll error you need to install vc redist that you can find: https://aka.ms/vc14/vc_redist.x64.exe
+.\python_embeded\python.exe -s HanzoStudio\main.py --windows-standalone-build --fast fp16_accumulation
+echo If you see this and Hanzo Studio did not start try updating your Nvidia Drivers to the latest. If you get a c10.dll error you need to install vc redist that you can find: https://aka.ms/vc14/vc_redist.x64.exe
 pause
@@ -0,0 +1,127 @@
+# yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json
+language: "en-US"
+early_access: false
+tone_instructions: "Only comment on issues introduced by this PR's changes. Do not flag pre-existing problems in moved, re-indented, or reformatted code."
+
+reviews:
+  profile: "chill"
+  request_changes_workflow: false
+  high_level_summary: false
+  poem: false
+  review_status: false
+  review_details: false
+  commit_status: true
+  collapse_walkthrough: true
+  changed_files_summary: false
+  sequence_diagrams: false
+  estimate_code_review_effort: false
+  assess_linked_issues: false
+  related_issues: false
+  related_prs: false
+  suggested_labels: false
+  auto_apply_labels: false
+  suggested_reviewers: false
+  auto_assign_reviewers: false
+  in_progress_fortune: false
+  enable_prompt_for_ai_agents: true
+
+  path_filters:
+    - "!studio_api_nodes/apis/**"
+    - "!**/generated/*.pyi"
+    - "!.ci/**"
+    - "!script_examples/**"
+    - "!**/__pycache__/**"
+    - "!**/*.ipynb"
+    - "!**/*.png"
+    - "!**/*.bat"
+
+  path_instructions:
+    - path: "**"
+      instructions: |
+        IMPORTANT: Only comment on issues directly introduced by this PR's code changes.
+        Do NOT flag pre-existing issues in code that was merely moved, re-indented,
+        de-indented, or reformatted without logic changes. If code appears in the diff
+        only due to whitespace or structural reformatting (e.g., removing a `with:` block),
+        treat it as unchanged. Contributors should not feel obligated to address
+        pre-existing issues outside the scope of their contribution.
+    - path: "studio/**"
+      instructions: |
+        Core ML/diffusion engine. Focus on:
+        - Backward compatibility (breaking changes affect all custom nodes)
+        - Memory management and GPU resource handling
+        - Performance implications in hot paths
+        - Thread safety for concurrent execution
+    - path: "studio_api_nodes/**"
+      instructions: |
+        Third-party API integration nodes. Focus on:
+        - No hardcoded API keys or secrets
+        - Proper error handling for API failures (timeouts, rate limits, auth errors)
+        - Correct Pydantic model usage
+        - Security of user data passed to external APIs
+    - path: "studio_extras/**"
+      instructions: |
+        Community-contributed extra nodes. Focus on:
+        - Consistency with node patterns (INPUT_TYPES, RETURN_TYPES, FUNCTION, CATEGORY)
+        - No breaking changes to existing node interfaces
+    - path: "studio_execution/**"
+      instructions: |
+        Execution engine (graph execution, caching, jobs). Focus on:
+        - Caching correctness
+        - Concurrent execution safety
+        - Graph validation edge cases
+    - path: "nodes.py"
+      instructions: |
+        Core node definitions (2500+ lines). Focus on:
+        - Backward compatibility of NODE_CLASS_MAPPINGS
+        - Consistency of INPUT_TYPES return format
+    - path: "alembic_db/**"
+      instructions: |
+        Database migrations. Focus on:
+        - Migration safety and rollback support
+        - Data preservation during schema changes
+
+  auto_review:
+    enabled: true
+    auto_incremental_review: true
+    drafts: false
+    ignore_title_keywords:
+      - "WIP"
+      - "DO NOT REVIEW"
+      - "DO NOT MERGE"
+
+  finishing_touches:
+    docstrings:
+      enabled: false
+    unit_tests:
+      enabled: false
+
+  tools:
+    ruff:
+      enabled: false
+    pylint:
+      enabled: false
+    flake8:
+      enabled: false
+    gitleaks:
+      enabled: true
+    shellcheck:
+      enabled: false
+    markdownlint:
+      enabled: false
+    yamllint:
+      enabled: false
+    languagetool:
+      enabled: false
+    github-checks:
+      enabled: true
+      timeout_ms: 90000
+    ast-grep:
+      essential_rules: true
+
+chat:
+  auto_reply: true
+
+knowledge_base:
+  opt_out: false
+  learnings:
+    scope: "auto"
@@ -0,0 +1,32 @@
+models/
+output/
+input/
+custom_nodes/*
+# ...but the pack manifest must reach the build context so the image can vendor
+# the packs reproducibly (scripts/install_custom_nodes.sh clones them at build).
+# Local clones stay excluded so the image builds them fresh from the manifest.
+!custom_nodes/hanzo-packs.txt
+user/
+temp/
+orgs/
+.git/
+.github/
+__pycache__/
+*.pyc
+*.pyo
+*.log
+*.egg-info/
+.venv/
+venv/
+.mypy_cache/
+.pytest_cache/
+.ruff_cache/
+tests/
+tests-unit/
+scripts/*
+# ...except the pack installer, which the image build invokes.
+!scripts/install_custom_nodes.sh
+notebooks/
+*.swp
+.env
+.env.*
@@ -1,5 +1,5 @@
 name: Bug Report
-description: "Something is broken inside of ComfyUI. (Do not use this if you're just having issues and need help, or if the issue relates to a custom node)"
+description: "Something is broken inside of Hanzo Studio. (Do not use this if you're just having issues and need help, or if the issue relates to a custom node)"
 labels: ["Potential Bug"]
 body:
  - type: markdown
@@ -7,23 +7,23 @@ body:
      value: |
        Before submitting a **Bug Report**, please ensure the following:

-        - **1:** You are running the latest version of ComfyUI.
-        - **2:** You have your ComfyUI logs and relevant workflow on hand and will post them in this bug report.
+        - **1:** You are running the latest version of Hanzo Studio.
+        - **2:** You have your Hanzo Studio logs and relevant workflow on hand and will post them in this bug report.
        - **3:** You confirmed that the bug is not caused by a custom node. You can disable all custom nodes by passing
        `--disable-all-custom-nodes` command line argument. If you have custom node try updating them to the latest version.
-        - **4:** This is an actual bug in ComfyUI, not just a support question. A bug is when you can specify exact
+        - **4:** This is an actual bug in Hanzo Studio, not just a support question. A bug is when you can specify exact
        steps to replicate what went wrong and others will be able to repeat your steps and see the same issue happen.

        ## Very Important

-        Please make sure that you post ALL your ComfyUI logs in the bug report. A bug report without logs will likely be ignored.
+        Please make sure that you post ALL your Hanzo Studio logs in the bug report. A bug report without logs will likely be ignored.
  - type: checkboxes
    id: custom-nodes-test
    attributes:
      label: Custom Node Testing
      description: Please confirm you have tried to reproduce the issue with all custom nodes disabled.
      options:
-        - label: I have tried disabling custom nodes and the issue persists (see [how to disable custom nodes](https://docs.comfy.org/troubleshooting/custom-node-issues#step-1%3A-test-with-all-custom-nodes-disabled) if you need help)
+        - label: I have tried disabling custom nodes and the issue persists (see [how to disable custom nodes](https://docs.hanzo.ai/troubleshooting/custom-node-issues#step-1%3A-test-with-all-custom-nodes-disabled) if you need help)
          required: false
  - type: textarea
    attributes:
@@ -40,7 +40,7 @@ body:
  - type: textarea
    attributes:
      label: Steps to Reproduce
-      description: "Describe how to reproduce the issue. Please be sure to attach a workflow JSON or PNG, ideally one that doesn't require custom nodes to test. If the bug open happens when certain custom nodes are used, most likely that custom node is what has the bug rather than ComfyUI, in which case it should be reported to the node's author."
+      description: "Describe how to reproduce the issue. Please be sure to attach a workflow JSON or PNG, ideally one that doesn't require custom nodes to test. If the bug open happens when certain custom nodes are used, most likely that custom node is what has the bug rather than Hanzo Studio, in which case it should be reported to the node's author."
    validations:
      required: true
  - type: textarea
@@ -1,11 +1,8 @@
 blank_issues_enabled: true
 contact_links:
-  - name: ComfyUI Frontend Issues
-    url: https://github.com/Comfy-Org/ComfyUI_frontend/issues
-    about: Issues related to the ComfyUI frontend (display issues, user interaction bugs), please go to the frontend repo to file the issue
-  - name: ComfyUI Matrix Space
-    url: https://app.element.io/#/room/%23comfyui_space%3Amatrix.org
-    about: The ComfyUI Matrix Space is available for support and general discussion related to ComfyUI (Matrix is like Discord but open source).
-  - name: Comfy Org Discord
-    url: https://discord.gg/comfyorg
-    about: The Comfy Org Discord is available for support and general discussion related to ComfyUI.
+  - name: Hanzo Studio Frontend Issues
+    url: https://github.com/hanzoai/studio/issues
+    about: Issues related to the Hanzo Studio frontend (display issues, user interaction bugs).
+  - name: Hanzo AI Discord
+    url: https://discord.gg/hanzoai
+    about: The Hanzo AI Discord is available for support and general discussion related to Hanzo Studio.
@@ -1,5 +1,5 @@
 name: Feature Request
-description: "You have an idea for something new you would like to see added to ComfyUI's core."
+description: "You have an idea for something new you would like to see added to Hanzo Studio's core."
 labels: [ "Feature" ]
 body:
    - type: markdown
@@ -7,11 +7,11 @@ body:
        value: |
                Before submitting a **Feature Request**, please ensure the following:

-                **1:** You are running the latest version of ComfyUI.
+                **1:** You are running the latest version of Hanzo Studio.
                **2:** You have looked to make sure there is not already a feature that does what you need, and there is not already a Feature Request listed for the same idea.
-                **3:** This is something that makes sense to add to ComfyUI Core, and wouldn't make more sense as a custom node.
+                **3:** This is something that makes sense to add to Hanzo Studio Core, and wouldn't make more sense as a custom node.

-                If unsure, ask on the [ComfyUI Matrix Space](https://app.element.io/#/room/%23comfyui_space%3Amatrix.org) or the [Comfy Org Discord](https://discord.gg/comfyorg) first.
+                If unsure, ask on the [Hanzo AI Discord](https://discord.gg/hanzoai) first.
    - type: textarea
      attributes:
            label: Feature Idea
@@ -7,17 +7,17 @@ body:
        value: |
            Before submitting a **User Report** issue, please ensure the following:

-            **1:** You are running the latest version of ComfyUI.
+            **1:** You are running the latest version of Hanzo Studio.
            **2:** You have made an effort to find public answers to your question before asking here. In other words, you googled it first, and scrolled through recent help topics.

-                If unsure, ask on the [ComfyUI Matrix Space](https://app.element.io/#/room/%23comfyui_space%3Amatrix.org) or the [Comfy Org Discord](https://discord.gg/comfyorg) first.
+                If unsure, ask on the [Hanzo AI Discord](https://discord.gg/hanzoai) first.
    - type: checkboxes
      id: custom-nodes-test
      attributes:
        label: Custom Node Testing
        description: Please confirm you have tried to reproduce the issue with all custom nodes disabled.
        options:
-          - label: I have tried disabling custom nodes and the issue persists (see [how to disable custom nodes](https://docs.comfy.org/troubleshooting/custom-node-issues#step-1%3A-test-with-all-custom-nodes-disabled) if you need help)
+          - label: I have tried disabling custom nodes and the issue persists (see [how to disable custom nodes](https://docs.hanzo.ai/troubleshooting/custom-node-issues#step-1%3A-test-with-all-custom-nodes-disabled) if you need help)
            required: false
    - type: textarea
      attributes:
@@ -0,0 +1,9 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="1280" height="640" viewBox="0 0 1280 640" role="img" aria-label="studio">
+<rect width="1280" height="640" fill="#0A0A0A"/>
+<svg x="96" y="215" width="210" height="210" viewBox="0 0 67 67"><path d="M22.21 67V44.6369H0V67H22.21Z" fill="#fff"/><path d="M66.7038 22.3184H22.2534L0.0878906 44.6367H44.4634L66.7038 22.3184Z" fill="#fff"/><path d="M22.21 0H0V22.3184H22.21V0Z" fill="#fff"/><path d="M66.7198 0H44.5098V22.3184H66.7198V0Z" fill="#fff"/><path d="M66.7198 67V44.6369H44.5098V67H66.7198Z" fill="#fff"/></svg>
+<text x="378" y="276" font-family="Inter,system-ui,-apple-system,sans-serif" font-size="78" font-weight="800" letter-spacing="-2" fill="#ffffff">studio</text>
+<text x="378" y="322" font-family="Inter,system-ui,sans-serif" font-size="30" fill="#ffffff" opacity=".66">Hanzo Studio — Visual AI Engine</text>
+<rect x="378" y="338" width="806" height="3" rx="1.5" fill="#ffffff" opacity=".9"/>
+<text x="378" y="390" font-family="Inter,system-ui,sans-serif" font-size="24" font-weight="600" fill="#ffffff" opacity=".5">github.com/hanzoai</text>
+<text x="1184" y="390" text-anchor="end" font-family="Inter,system-ui,sans-serif" font-size="24" font-weight="600" fill="#ffffff" opacity=".5">hanzo.ai</text>
+</svg>
@@ -4,7 +4,7 @@ on:
  pull_request_target:
    types: [opened, reopened, synchronize, ready_for_review]
    paths:
-      - 'comfy_api_nodes/**'   # only run if these files changed
+      - 'studio_api_nodes/**'   # only run if these files changed

 permissions:
  contents: read
@@ -0,0 +1,22 @@
+# Canonical CI/CD — imports the shared hanzoai/ci reusable workflow, which
+# reads hanzo.yml (images + test + deploy + kms). No per-repo build logic,
+# no GitHub-hosted runners (defaults to the Hanzo cloud arc pool).
+name: CI/CD
+
+on:
+  push:
+    branches: [main]
+    tags: ['v*']
+  pull_request:
+  workflow_dispatch:
+
+jobs:
+  cicd:
+    uses: hanzoai/ci/.github/workflows/build.yml@v1
+    # Target the Hanzo arc scale set by its installation name. ARC scale sets
+    # are matched by name, not by the [self-hosted,linux,amd64] label triple
+    # that ci@v1 defaults to — without this override the job never gets a
+    # runner and sits queued.
+    with:
+      runner: '["hanzo-build-linux-amd64"]'
+    secrets: inherit
@@ -1,5 +1,5 @@
-# This is the GitHub Workflow that drives full-GPU-enabled tests of pull requests to ComfyUI, when the 'Run-CI-Test' label is added
-# Results are reported as checkmarks on the commits, as well as onto https://ci.comfy.org/
+# This is the GitHub Workflow that drives full-GPU-enabled tests of pull requests to Hanzo Studio, when the 'Run-CI-Test' label is added
+# Results are reported as checkmarks on the commits, as well as onto https://ci.hanzo.ai/
 name: Pull Request CI Workflow Runs
 on:
    pull_request_target:
@@ -34,7 +34,7 @@ jobs:
          python_version: ${{ matrix.python_version }}
          torch_version: ${{ matrix.torch_version }}
          google_credentials: ${{ secrets.GCS_SERVICE_ACCOUNT_JSON }}
-          comfyui_flags: ${{ matrix.flags }}
+          studio_flags: ${{ matrix.flags }}
          use_prior_commit: 'true'
  comment:
    if: ${{ github.event.label.name == 'Run-CI-Test' }}
@@ -49,5 +49,5 @@ jobs:
              issue_number: context.issue.number,
              owner: context.repo.owner,
              repo: context.repo.repo,
-              body: '(Automated Bot Message) CI Tests are running, you can view the results at https://ci.comfy.org/?branch=${{ github.event.pull_request.number }}%2Fmerge'
+              body: '(Automated Bot Message) CI Tests are running, you can view the results at https://ci.hanzo.ai/?branch=${{ github.event.pull_request.number }}%2Fmerge'
            })
@@ -126,7 +126,7 @@ jobs:
            --arg release_tag "$RELEASE_TAG" \
            --arg release_url "$RELEASE_URL" \
            '{
-              event_type: "comfyui_release_published",
+              event_type: "studio_release_published",
              client_payload: {
                release_tag: $release_tag,
                release_url: $release_url
@@ -138,7 +138,7 @@ jobs:
            -H "Accept: application/vnd.github+json" \
            -H "Content-Type: application/json" \
            -H "Authorization: Bearer ${DISPATCH_TOKEN}" \
-            https://api.github.com/repos/Comfy-Org/desktop/dispatches \
+            https://api.github.com/repos/hanzoai/studio-desktop/dispatches \
            -d "$PAYLOAD"

-          echo "✅ Dispatched ComfyUI release ${RELEASE_TAG} to Comfy-Org/desktop"
+          echo "✅ Dispatched Hanzo Studio release ${RELEASE_TAG} to hanzoai/studio-desktop"
@@ -16,8 +16,11 @@ jobs:
      with:
        python-version: 3.x

+    - name: Install uv
+      run: curl -LsSf https://astral.sh/uv/install.sh | sh
+
    - name: Install Ruff
-      run: pip install ruff
+      run: uv pip install --system ruff

    - name: Run Ruff
      run: ruff check .
@@ -35,14 +38,16 @@ jobs:
      with:
        python-version: '3.12'

+    - name: Install uv
+      run: curl -LsSf https://astral.sh/uv/install.sh | sh
+
    - name: Install requirements
      run: |
-        python -m pip install --upgrade pip
-        pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
-        pip install -r requirements.txt
+        uv pip install --system torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
+        uv pip install --system -r requirements.txt

    - name: Install Pylint
-      run: pip install pylint
+      run: uv pip install --system pylint

    - name: Run Pylint
-      run: pylint comfy_api_nodes
+      run: pylint studio_api_nodes
@@ -76,7 +76,7 @@ on:
        default: true

 jobs:
-  package_comfy_windows:
+  package_studio_windows:
    permissions:
      contents: "write"
      packages: "write"
@@ -93,12 +93,12 @@ jobs:
        with:
          path: |
            ${{ inputs.cache_tag }}_python_deps.tar
-            update_comfyui_and_python_dependencies.bat
+            update_studio_and_python_dependencies.bat
          key: ${{ runner.os }}-build-${{ inputs.cache_tag }}-${{ inputs.python_minor }}
      - shell: bash
        run: |
          mv ${{ inputs.cache_tag }}_python_deps.tar ../
-          mv update_comfyui_and_python_dependencies.bat ../
+          mv update_studio_and_python_dependencies.bat ../
          cd ..
          tar xf ${{ inputs.cache_tag }}_python_deps.tar
          pwd
@@ -107,7 +107,7 @@ jobs:
      - shell: bash
        run: |
          cd ..
-          cp -r ComfyUI ComfyUI_copy
+          cp -r HanzoStudio HanzoStudio_copy
          curl https://www.python.org/ftp/python/3.${{ inputs.python_minor }}.${{ inputs.python_patch }}/python-3.${{ inputs.python_minor }}.${{ inputs.python_patch }}-embed-amd64.zip -o python_embeded.zip
          unzip python_embeded.zip -d python_embeded
          cd python_embeded
@@ -117,11 +117,11 @@ jobs:
          ./python.exe get-pip.py
          ./python.exe -s -m pip install ../${{ inputs.cache_tag }}_python_deps/*

-          grep comfy ../ComfyUI/requirements.txt > ./requirements_comfyui.txt
-          ./python.exe -s -m pip install -r requirements_comfyui.txt
-          rm requirements_comfyui.txt
+          grep -E "comfyui-frontend-package|comfyui-workflow-templates|comfyui-embedded-docs|comfy-kitchen|comfy-aimdo" ../HanzoStudio/requirements.txt > ./requirements_studio.txt
+          ./python.exe -s -m pip install -r requirements_studio.txt
+          rm requirements_studio.txt

-          sed -i '1i../ComfyUI' ./python3${{ inputs.python_minor }}._pth
+          sed -i '1i../HanzoStudio' ./python3${{ inputs.python_minor }}._pth

          if test -f ./Lib/site-packages/torch/lib/dnnl.lib; then
            rm ./Lib/site-packages/torch/lib/dnnl.lib #I don't think this is actually used and I need the space
@@ -131,40 +131,40 @@ jobs:

          cd ..

-          git clone --depth 1 https://github.com/comfyanonymous/taesd
-          cp taesd/*.safetensors ./ComfyUI_copy/models/vae_approx/
+          git clone --depth 1 https://github.com/hanzoai/taesd
+          cp taesd/*.safetensors ./HanzoStudio_copy/models/vae_approx/

-          mkdir ComfyUI_windows_portable
-          mv python_embeded ComfyUI_windows_portable
-          mv ComfyUI_copy ComfyUI_windows_portable/ComfyUI
+          mkdir HanzoStudio_windows_portable
+          mv python_embeded HanzoStudio_windows_portable
+          mv HanzoStudio_copy HanzoStudio_windows_portable/HanzoStudio

-          cd ComfyUI_windows_portable
+          cd HanzoStudio_windows_portable

          mkdir update
-          cp -r ComfyUI/.ci/update_windows/* ./update/
-          cp -r ComfyUI/.ci/windows_${{ inputs.rel_name }}_base_files/* ./
-          cp ../update_comfyui_and_python_dependencies.bat ./update/
+          cp -r HanzoStudio/.ci/update_windows/* ./update/
+          cp -r HanzoStudio/.ci/windows_${{ inputs.rel_name }}_base_files/* ./
+          cp ../update_studio_and_python_dependencies.bat ./update/

          cd ..

-          "C:\Program Files\7-Zip\7z.exe" a -t7z -m0=lzma2 -mx=9 -mfb=128 -md=768m -ms=on -mf=BCJ2 ComfyUI_windows_portable.7z ComfyUI_windows_portable
-          mv ComfyUI_windows_portable.7z ComfyUI/ComfyUI_windows_portable_${{ inputs.rel_name }}${{ inputs.rel_extra_name }}.7z
+          "C:\Program Files\7-Zip\7z.exe" a -t7z -m0=lzma2 -mx=9 -mfb=128 -md=768m -ms=on -mf=BCJ2 HanzoStudio_windows_portable.7z HanzoStudio_windows_portable
+          mv HanzoStudio_windows_portable.7z HanzoStudio/HanzoStudio_windows_portable_${{ inputs.rel_name }}${{ inputs.rel_extra_name }}.7z

      - shell: bash
        if: ${{ inputs.test_release }}
        run: |
          cd ..
-          cd ComfyUI_windows_portable
-          python_embeded/python.exe -s ComfyUI/main.py --quick-test-for-ci --cpu
+          cd HanzoStudio_windows_portable
+          python_embeded/python.exe -s HanzoStudio/main.py --quick-test-for-ci --cpu

-          python_embeded/python.exe -s ./update/update.py ComfyUI/
+          python_embeded/python.exe -s ./update/update.py HanzoStudio/

          ls

      - name: Upload binaries to release
        uses: softprops/action-gh-release@v2
        with:
-          files: ComfyUI_windows_portable_${{ inputs.rel_name }}${{ inputs.rel_extra_name }}.7z
+          files: HanzoStudio_windows_portable_${{ inputs.rel_name }}${{ inputs.rel_extra_name }}.7z
          tag_name: ${{ inputs.git_tag }}
          draft: true
          overwrite_files: true
@@ -25,7 +25,8 @@ jobs:
        uses: actions/setup-python@v4
        with:
          python-version: ${{ matrix.python-version }}
+      - name: Install uv
+        run: curl -LsSf https://astral.sh/uv/install.sh | sh
      - name: Install dependencies
        run: |
-          python -m pip install --upgrade pip
-          pip install -r requirements.txt
+          uv pip install --system -r requirements.txt
@@ -1,6 +1,6 @@
-# This is the GitHub Workflow that drives automatic full-GPU-enabled tests of all new commits to the master branch of ComfyUI
-# Results are reported as checkmarks on the commits, as well as onto https://ci.comfy.org/
-name: Full Comfy CI Workflow Runs
+# This is the GitHub Workflow that drives automatic full-GPU-enabled tests of all new commits to the main branch of Hanzo Studio
+# Results are reported as checkmarks on the commits, as well as onto https://ci.hanzo.ai/
+name: Full Hanzo Studio CI Workflow Runs
 on:
  push:
    branches:
@@ -46,7 +46,7 @@ jobs:
          python_version: ${{ matrix.python_version }}
          torch_version: ${{ matrix.torch_version }}
          google_credentials: ${{ secrets.GCS_SERVICE_ACCOUNT_JSON }}
-          comfyui_flags: ${{ matrix.flags }}
+          studio_flags: ${{ matrix.flags }}

  # test-win-nightly:
  #   strategy:
@@ -69,7 +69,7 @@ jobs:
  #         python_version: ${{ matrix.python_version }}
  #         torch_version: ${{ matrix.torch_version }}
  #         google_credentials: ${{ secrets.GCS_SERVICE_ACCOUNT_JSON }}
-  #         comfyui_flags: ${{ matrix.flags }}
+  #         studio_flags: ${{ matrix.flags }}

  test-unix-nightly:
    strategy:
@@ -96,4 +96,4 @@ jobs:
          python_version: ${{ matrix.python_version }}
          torch_version: ${{ matrix.torch_version }}
          google_credentials: ${{ secrets.GCS_SERVICE_ACCOUNT_JSON }}
-          comfyui_flags: ${{ matrix.flags }}
+          studio_flags: ${{ matrix.flags }}
@@ -19,12 +19,13 @@ jobs:
      uses: actions/setup-python@v4
      with:
        python-version: '3.12'
+    - name: Install uv
+      run: curl -LsSf https://astral.sh/uv/install.sh | sh
    - name: Install requirements
      run: |
-        python -m pip install --upgrade pip
-        pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
-        pip install -r requirements.txt
-        pip install -r tests-unit/requirements.txt
+        uv pip install --system torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
+        uv pip install --system -r requirements.txt
+        uv pip install --system -r tests-unit/requirements.txt
    - name: Run Execution Tests
      run: |
        python -m pytest tests/execution -v --skip-timing-checks
@@ -10,26 +10,27 @@ jobs:
  test:
    runs-on: ubuntu-latest
    steps:
-    - name: Checkout ComfyUI
+    - name: Checkout Hanzo Studio
      uses: actions/checkout@v4
      with:
-        repository: "Comfy-Org/ComfyUI"
-        path: "ComfyUI"
+        repository: "hanzoai/studio"
+        path: "studio"
    - uses: actions/setup-python@v4
      with:
        python-version: '3.10'
+    - name: Install uv
+      run: curl -LsSf https://astral.sh/uv/install.sh | sh
    - name: Install requirements
      run: |
-        python -m pip install --upgrade pip
-        pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
-        pip install -r requirements.txt
-        pip install wait-for-it
-      working-directory: ComfyUI
-    - name: Start ComfyUI server
+        uv pip install --system torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
+        uv pip install --system -r requirements.txt
+        uv pip install --system wait-for-it
+      working-directory: studio
+    - name: Start Hanzo Studio server
      run: |
        python main.py --cpu 2>&1 | tee console_output.log &
        wait-for-it --service 127.0.0.1:8188 -t 30
-      working-directory: ComfyUI
+      working-directory: studio
    - name: Check for unhandled exceptions in server log
      run: |
        grep -v "Found comfy_kitchen backend triton: {'available': False, 'disabled': True, 'unavailable_reason': \"ImportError: No module named 'triton'\", 'capabilities': \[\]}" console_output.log | grep -v "Found comfy_kitchen backend triton: {'available': False, 'disabled': False, 'unavailable_reason': \"ImportError: No module named 'triton'\", 'capabilities': \[\]}" > console_output_filtered.log
@@ -38,10 +39,10 @@ jobs:
          echo "Unhandled exception/error found in server log."
          exit 1
        fi
-      working-directory: ComfyUI
+      working-directory: studio
    - uses: actions/upload-artifact@v4
      if: always()
      with:
        name: console-output
-        path: ComfyUI/console_output.log
+        path: studio/console_output.log
        retention-days: 30
@@ -1,4 +1,4 @@
-name: Generate Pydantic Stubs from api.comfy.org
+name: Generate Pydantic Stubs from api.hanzo.ai

 on:
  schedule:
@@ -8,49 +8,49 @@ on:
 jobs:
  generate-models:
    runs-on: ubuntu-latest
-    
+
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4
-      
+
      - name: Set up Python
        uses: actions/setup-python@v4
        with:
          python-version: '3.10'
-      
+
      - name: Install dependencies
        run: |
          python -m pip install --upgrade pip
          pip install 'datamodel-code-generator[http]'
          npm install @redocly/cli
-      
+
      - name: Download OpenAPI spec
        run: |
-          curl -o openapi.yaml https://api.comfy.org/openapi
-      
+          curl -o openapi.yaml https://api.hanzo.ai/openapi
+
      - name: Filter OpenAPI spec with Redocly
        run: |
-          npx @redocly/cli bundle openapi.yaml --output filtered-openapi.yaml --config comfy_api_nodes/redocly.yaml --remove-unused-components
-      
+          npx @redocly/cli bundle openapi.yaml --output filtered-openapi.yaml --config studio_api_nodes/redocly.yaml --remove-unused-components
+
      - name: Generate API models
        run: |
-          datamodel-codegen --use-subclass-enum --input filtered-openapi.yaml --output comfy_api_nodes/apis --output-model-type pydantic_v2.BaseModel
-      
+          datamodel-codegen --use-subclass-enum --input filtered-openapi.yaml --output studio_api_nodes/apis --output-model-type pydantic_v2.BaseModel
+
      - name: Check for changes
        id: git-check
        run: |
-          git diff --exit-code comfy_api_nodes/apis || echo "changes=true" >> $GITHUB_OUTPUT
-      
+          git diff --exit-code studio_api_nodes/apis || echo "changes=true" >> $GITHUB_OUTPUT
+
      - name: Create Pull Request
        if: steps.git-check.outputs.changes == 'true'
        uses: peter-evans/create-pull-request@v5
        with:
          commit-message: 'chore: update API models from OpenAPI spec'
-          title: 'Update API models from api.comfy.org'
+          title: 'Update API models from api.hanzo.ai'
          body: |
-            This PR updates the API models based on the latest api.comfy.org OpenAPI specification.
-            
-            Generated automatically by the a Github workflow.
+            This PR updates the API models based on the latest api.hanzo.ai OpenAPI specification.
+
+            Generated automatically by a Github workflow.
          branch: update-api-stubs
          delete-branch: true
-          base: master
+          base: main
@@ -6,7 +6,7 @@ on:
  workflow_dispatch:
    inputs:
      version:
-        description: 'ComfyUI version (e.g., v0.7.0)'
+        description: 'Hanzo Studio version (e.g., v0.7.0)'
        required: true
        type: string

@@ -26,34 +26,34 @@ jobs:
          fi
          echo "version=$VERSION" >> $GITHUB_OUTPUT

-      - name: Checkout comfyui-ci-container
+      - name: Checkout studio-ci-container
        uses: actions/checkout@v4
        with:
-          repository: comfy-org/comfyui-ci-container
+          repository: hanzoai/studio-ci-container
          token: ${{ secrets.CI_CONTAINER_PAT }}

      - name: Check current version
        id: current
        run: |
-          CURRENT=$(grep -oP 'ARG COMFYUI_VERSION=\K.*' Dockerfile || echo "unknown")
+          CURRENT=$(grep -oP 'ARG STUDIO_VERSION=\K.*' Dockerfile || echo "unknown")
          echo "current_version=$CURRENT" >> $GITHUB_OUTPUT

      - name: Update Dockerfile
        run: |
          VERSION="${{ steps.version.outputs.version }}"
-          sed -i "s/^ARG COMFYUI_VERSION=.*/ARG COMFYUI_VERSION=${VERSION}/" Dockerfile
+          sed -i "s/^ARG STUDIO_VERSION=.*/ARG STUDIO_VERSION=${VERSION}/" Dockerfile

      - name: Create Pull Request
        id: create-pr
        uses: peter-evans/create-pull-request@v7
        with:
          token: ${{ secrets.CI_CONTAINER_PAT }}
-          branch: automation/comfyui-${{ steps.version.outputs.version }}
-          title: "chore: bump ComfyUI to ${{ steps.version.outputs.version }}"
+          branch: automation/studio-${{ steps.version.outputs.version }}
+          title: "chore: bump Hanzo Studio to ${{ steps.version.outputs.version }}"
          body: |
-            Updates ComfyUI version from `${{ steps.current.outputs.current_version }}` to `${{ steps.version.outputs.version }}`
+            Updates Hanzo Studio version from `${{ steps.current.outputs.current_version }}` to `${{ steps.version.outputs.version }}`

            **Triggered by:** ${{ github.event_name == 'release' && format('[Release {0}]({1})', github.event.release.tag_name, github.event.release.html_url) || 'Manual workflow dispatch' }}

          labels: automation
-          commit-message: "chore: bump ComfyUI to ${{ steps.version.outputs.version }}"
+          commit-message: "chore: bump Hanzo Studio to ${{ steps.version.outputs.version }}"
@@ -30,9 +30,9 @@ jobs:
        run: |
          python -m pip install --upgrade pip

-      - name: Update comfyui_version.py
+      - name: Update studio_version.py
        run: |
-          # Read version from pyproject.toml and update comfyui_version.py
+          # Read version from pyproject.toml and update studio_version.py
          python -c '
          import tomllib

@@ -41,8 +41,8 @@ jobs:
              config = tomllib.load(f)
              version = config["project"]["version"]

-          # Write version to comfyui_version.py
-          with open("comfyui_version.py", "w") as f:
+          # Write version to studio_version.py
+          with open("studio_version.py", "w") as f:
              f.write("# This file is automatically generated by the build process when version is\n")
              f.write("# updated in pyproject.toml.\n")
              f.write(f"__version__ = \"{version}\"\n")
@@ -54,6 +54,6 @@ jobs:
          git config --local user.email "github-actions@github.com"
          git fetch origin ${{ github.head_ref }}
          git checkout -B ${{ github.head_ref }} origin/${{ github.head_ref }}
-          git add comfyui_version.py
-          git diff --quiet && git diff --staged --quiet || git commit -m "chore: Update comfyui_version.py to match pyproject.toml"
+          git add studio_version.py
+          git diff --quiet && git diff --staged --quiet || git commit -m "chore: Update studio_version.py to match pyproject.toml"
          git push origin HEAD:${{ github.head_ref }}
@@ -46,18 +46,18 @@ jobs:
        - shell: bash
          run: |
            echo "@echo off
-            call update_comfyui.bat nopause
+            call update_studio.bat nopause
            echo -
            echo This will try to update pytorch and all python dependencies.
            echo -
-            echo If you just want to update normally, close this and run update_comfyui.bat instead.
+            echo If you just want to update normally, close this and run update_studio.bat instead.
            echo -
            pause
-            ..\python_embeded\python.exe -s -m pip install --upgrade torch torchvision torchaudio ${{ inputs.xformers }} --extra-index-url https://download.pytorch.org/whl/cu${{ inputs.cu }} -r ../ComfyUI/requirements.txt pygit2
-            pause" > update_comfyui_and_python_dependencies.bat
+            ..\python_embeded\python.exe -s -m pip install --upgrade torch torchvision torchaudio ${{ inputs.xformers }} --extra-index-url https://download.pytorch.org/whl/cu${{ inputs.cu }} -r ../HanzoStudio/requirements.txt pygit2
+            pause" > update_studio_and_python_dependencies.bat

-            grep -v comfyui requirements.txt > requirements_nocomfyui.txt
-            python -m pip wheel --no-cache-dir torch torchvision torchaudio ${{ inputs.xformers }} ${{ inputs.extra_dependencies }} --extra-index-url https://download.pytorch.org/whl/cu${{ inputs.cu }} -r requirements_nocomfyui.txt pygit2 -w ./temp_wheel_dir
+            grep -v studio requirements.txt > requirements_nostudio.txt
+            python -m pip wheel --no-cache-dir torch torchvision torchaudio ${{ inputs.xformers }} ${{ inputs.extra_dependencies }} --extra-index-url https://download.pytorch.org/whl/cu${{ inputs.cu }} -r requirements_nostudio.txt pygit2 -w ./temp_wheel_dir
            python -m pip install --no-cache-dir ./temp_wheel_dir/*
            echo installed basic
            ls -lah temp_wheel_dir
@@ -68,5 +68,5 @@ jobs:
          with:
            path: |
              cu${{ inputs.cu }}_python_deps.tar
-              update_comfyui_and_python_dependencies.bat
+              update_studio_and_python_dependencies.bat
            key: ${{ runner.os }}-build-cu${{ inputs.cu }}-${{ inputs.python_minor }}
@@ -38,18 +38,18 @@ jobs:
        - shell: bash
          run: |
            echo "@echo off
-            call update_comfyui.bat nopause
+            call update_studio.bat nopause
            echo -
            echo This will try to update pytorch and all python dependencies.
            echo -
-            echo If you just want to update normally, close this and run update_comfyui.bat instead.
+            echo If you just want to update normally, close this and run update_studio.bat instead.
            echo -
            pause
-            ..\python_embeded\python.exe -s -m pip install --upgrade ${{ inputs.torch_dependencies }} -r ../ComfyUI/requirements.txt pygit2
-            pause" > update_comfyui_and_python_dependencies.bat
+            ..\python_embeded\python.exe -s -m pip install --upgrade ${{ inputs.torch_dependencies }} -r ../HanzoStudio/requirements.txt pygit2
+            pause" > update_studio_and_python_dependencies.bat

-            grep -v comfyui requirements.txt > requirements_nocomfyui.txt
-            python -m pip wheel --no-cache-dir ${{ inputs.torch_dependencies }} -r requirements_nocomfyui.txt pygit2 -w ./temp_wheel_dir
+            grep -v studio requirements.txt > requirements_nostudio.txt
+            python -m pip wheel --no-cache-dir ${{ inputs.torch_dependencies }} -r requirements_nostudio.txt pygit2 -w ./temp_wheel_dir
            python -m pip install --no-cache-dir ./temp_wheel_dir/*
            echo installed basic
            ls -lah temp_wheel_dir
@@ -60,5 +60,5 @@ jobs:
          with:
            path: |
              ${{ inputs.cache_tag }}_python_deps.tar
-              update_comfyui_and_python_dependencies.bat
+              update_studio_and_python_dependencies.bat
            key: ${{ runner.os }}-build-${{ inputs.cache_tag }}-${{ inputs.python_minor }}
@@ -42,45 +42,45 @@ jobs:
        - shell: bash
          run: |
            cd ..
-            cp -r ComfyUI ComfyUI_copy
+            cp -r HanzoStudio HanzoStudio_copy
            curl https://www.python.org/ftp/python/3.${{ inputs.python_minor }}.${{ inputs.python_patch }}/python-3.${{ inputs.python_minor }}.${{ inputs.python_patch }}-embed-amd64.zip -o python_embeded.zip
            unzip python_embeded.zip -d python_embeded
            cd python_embeded
            echo 'import site' >> ./python3${{ inputs.python_minor }}._pth
            curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py
            ./python.exe get-pip.py
-            python -m pip wheel torch torchvision torchaudio --pre --extra-index-url https://download.pytorch.org/whl/nightly/cu${{ inputs.cu }} -r ../ComfyUI/requirements.txt pygit2 -w ../temp_wheel_dir
+            python -m pip wheel torch torchvision torchaudio --pre --extra-index-url https://download.pytorch.org/whl/nightly/cu${{ inputs.cu }} -r ../HanzoStudio/requirements.txt pygit2 -w ../temp_wheel_dir
            ls ../temp_wheel_dir
            ./python.exe -s -m pip install --pre ../temp_wheel_dir/*
-            sed -i '1i../ComfyUI' ./python3${{ inputs.python_minor }}._pth
+            sed -i '1i../HanzoStudio' ./python3${{ inputs.python_minor }}._pth

            rm ./Lib/site-packages/torch/lib/dnnl.lib #I don't think this is actually used and I need the space
            cd ..

-            git clone --depth 1 https://github.com/comfyanonymous/taesd
-            cp taesd/*.safetensors ./ComfyUI_copy/models/vae_approx/
+            git clone --depth 1 https://github.com/hanzoai/taesd
+            cp taesd/*.safetensors ./HanzoStudio_copy/models/vae_approx/

-            mkdir ComfyUI_windows_portable_nightly_pytorch
-            mv python_embeded ComfyUI_windows_portable_nightly_pytorch
-            mv ComfyUI_copy ComfyUI_windows_portable_nightly_pytorch/ComfyUI
+            mkdir HanzoStudio_windows_portable_nightly_pytorch
+            mv python_embeded HanzoStudio_windows_portable_nightly_pytorch
+            mv HanzoStudio_copy HanzoStudio_windows_portable_nightly_pytorch/HanzoStudio

-            cd ComfyUI_windows_portable_nightly_pytorch
+            cd HanzoStudio_windows_portable_nightly_pytorch

            mkdir update
-            cp -r ComfyUI/.ci/update_windows/* ./update/
-            cp -r ComfyUI/.ci/windows_nvidia_base_files/* ./
-            cp -r ComfyUI/.ci/windows_nightly_base_files/* ./
+            cp -r HanzoStudio/.ci/update_windows/* ./update/
+            cp -r HanzoStudio/.ci/windows_nvidia_base_files/* ./
+            cp -r HanzoStudio/.ci/windows_nightly_base_files/* ./

-            echo "call update_comfyui.bat nopause
-            ..\python_embeded\python.exe -s -m pip install --upgrade --pre torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/nightly/cu${{ inputs.cu }} -r ../ComfyUI/requirements.txt pygit2
-            pause" > ./update/update_comfyui_and_python_dependencies.bat
+            echo "call update_studio.bat nopause
+            ..\python_embeded\python.exe -s -m pip install --upgrade --pre torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/nightly/cu${{ inputs.cu }} -r ../HanzoStudio/requirements.txt pygit2
+            pause" > ./update/update_studio_and_python_dependencies.bat
            cd ..

-            "C:\Program Files\7-Zip\7z.exe" a -t7z -m0=lzma2 -mx=9 -mfb=128 -md=512m -ms=on -mf=BCJ2 ComfyUI_windows_portable_nightly_pytorch.7z ComfyUI_windows_portable_nightly_pytorch
-            mv ComfyUI_windows_portable_nightly_pytorch.7z ComfyUI/ComfyUI_windows_portable_nvidia_or_cpu_nightly_pytorch.7z
+            "C:\Program Files\7-Zip\7z.exe" a -t7z -m0=lzma2 -mx=9 -mfb=128 -md=512m -ms=on -mf=BCJ2 HanzoStudio_windows_portable_nightly_pytorch.7z HanzoStudio_windows_portable_nightly_pytorch
+            mv HanzoStudio_windows_portable_nightly_pytorch.7z HanzoStudio/HanzoStudio_windows_portable_nvidia_or_cpu_nightly_pytorch.7z

-            cd ComfyUI_windows_portable_nightly_pytorch
-            python_embeded/python.exe -s ComfyUI/main.py --quick-test-for-ci --cpu
+            cd HanzoStudio_windows_portable_nightly_pytorch
+            python_embeded/python.exe -s HanzoStudio/main.py --quick-test-for-ci --cpu

            ls

@@ -88,6 +88,6 @@ jobs:
          uses: svenstaro/upload-release-action@v2
          with:
                repo_token: ${{ secrets.GITHUB_TOKEN }}
-                file: ComfyUI_windows_portable_nvidia_or_cpu_nightly_pytorch.7z
+                file: HanzoStudio_windows_portable_nvidia_or_cpu_nightly_pytorch.7z
                tag: "latest"
                overwrite: true
@@ -25,7 +25,7 @@ on:
 #      - master

 jobs:
-  package_comfyui:
+  package_studio:
    permissions:
        contents: "write"
        packages: "write"
@@ -37,12 +37,12 @@ jobs:
          with:
            path: |
              cu${{ inputs.cu }}_python_deps.tar
-              update_comfyui_and_python_dependencies.bat
+              update_studio_and_python_dependencies.bat
            key: ${{ runner.os }}-build-cu${{ inputs.cu }}-${{ inputs.python_minor }}
        - shell: bash
          run: |
            mv cu${{ inputs.cu }}_python_deps.tar ../
-            mv update_comfyui_and_python_dependencies.bat ../
+            mv update_studio_and_python_dependencies.bat ../
            cd ..
            tar xf cu${{ inputs.cu }}_python_deps.tar
            pwd
@@ -55,7 +55,7 @@ jobs:
        - shell: bash
          run: |
            cd ..
-            cp -r ComfyUI ComfyUI_copy
+            cp -r HanzoStudio HanzoStudio_copy
            curl https://www.python.org/ftp/python/3.${{ inputs.python_minor }}.${{ inputs.python_patch }}/python-3.${{ inputs.python_minor }}.${{ inputs.python_patch }}-embed-amd64.zip -o python_embeded.zip
            unzip python_embeded.zip -d python_embeded
            cd python_embeded
@@ -63,36 +63,36 @@ jobs:
            curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py
            ./python.exe get-pip.py
            ./python.exe -s -m pip install ../cu${{ inputs.cu }}_python_deps/*
-            sed -i '1i../ComfyUI' ./python3${{ inputs.python_minor }}._pth
+            sed -i '1i../HanzoStudio' ./python3${{ inputs.python_minor }}._pth

            rm ./Lib/site-packages/torch/lib/dnnl.lib #I don't think this is actually used and I need the space
            rm ./Lib/site-packages/torch/lib/libprotoc.lib
            rm ./Lib/site-packages/torch/lib/libprotobuf.lib
            cd ..

-            git clone --depth 1 https://github.com/comfyanonymous/taesd
-            cp taesd/*.safetensors ./ComfyUI_copy/models/vae_approx/
+            git clone --depth 1 https://github.com/hanzoai/taesd
+            cp taesd/*.safetensors ./HanzoStudio_copy/models/vae_approx/

-            mkdir ComfyUI_windows_portable
-            mv python_embeded ComfyUI_windows_portable
-            mv ComfyUI_copy ComfyUI_windows_portable/ComfyUI
+            mkdir HanzoStudio_windows_portable
+            mv python_embeded HanzoStudio_windows_portable
+            mv HanzoStudio_copy HanzoStudio_windows_portable/HanzoStudio

-            cd ComfyUI_windows_portable
+            cd HanzoStudio_windows_portable

            mkdir update
-            cp -r ComfyUI/.ci/update_windows/* ./update/
-            cp -r ComfyUI/.ci/windows_nvidia_base_files/* ./
-            cp ../update_comfyui_and_python_dependencies.bat ./update/
+            cp -r HanzoStudio/.ci/update_windows/* ./update/
+            cp -r HanzoStudio/.ci/windows_nvidia_base_files/* ./
+            cp ../update_studio_and_python_dependencies.bat ./update/

            cd ..

-            "C:\Program Files\7-Zip\7z.exe" a -t7z -m0=lzma2 -mx=9 -mfb=128 -md=768m -ms=on -mf=BCJ2 ComfyUI_windows_portable.7z ComfyUI_windows_portable
-            mv ComfyUI_windows_portable.7z ComfyUI/new_ComfyUI_windows_portable_nvidia_cu${{ inputs.cu }}_or_cpu.7z
+            "C:\Program Files\7-Zip\7z.exe" a -t7z -m0=lzma2 -mx=9 -mfb=128 -md=768m -ms=on -mf=BCJ2 HanzoStudio_windows_portable.7z HanzoStudio_windows_portable
+            mv HanzoStudio_windows_portable.7z HanzoStudio/new_HanzoStudio_windows_portable_nvidia_cu${{ inputs.cu }}_or_cpu.7z

-            cd ComfyUI_windows_portable
-            python_embeded/python.exe -s ComfyUI/main.py --quick-test-for-ci --cpu
+            cd HanzoStudio_windows_portable
+            python_embeded/python.exe -s HanzoStudio/main.py --quick-test-for-ci --cpu

-            python_embeded/python.exe -s ./update/update.py ComfyUI/
+            python_embeded/python.exe -s ./update/update.py HanzoStudio/

            ls

@@ -100,7 +100,7 @@ jobs:
          uses: svenstaro/upload-release-action@v2
          with:
                repo_token: ${{ secrets.GITHUB_TOKEN }}
-                file: new_ComfyUI_windows_portable_nvidia_cu${{ inputs.cu }}_or_cpu.7z
+                file: new_HanzoStudio_windows_portable_nvidia_cu${{ inputs.cu }}_or_cpu.7z
                tag: "latest"
                overwrite: true

@@ -0,0 +1,7 @@
+name: Workflow Sanity
+on:
+  pull_request:
+    paths: ['.github/workflows/**']
+jobs:
+  sanity:
+    uses: hanzoai/.github/.github/workflows/workflow-sanity.yml@main
@@ -5,13 +5,17 @@ __pycache__/
 !/input/example.png
 /models/
 /temp/
-/custom_nodes/
-!custom_nodes/example_node.py.example
+# Ignore vendored pack contents but keep the directory listable so the tracked
+# files below can be re-included (a file under a fully-excluded dir cannot be).
+/custom_nodes/*
+!/custom_nodes/example_node.py.example
+# Pinned pack manifest is tracked; the pack sources it clones are not (vendored at build).
+!/custom_nodes/hanzo-packs.txt
 extra_model_paths.yaml
 /.vs
 .vscode/
 .idea/
-venv/
+venv*/
 .venv/
 /web/extensions/*
 !/web/extensions/logging.js.example
@@ -24,3 +28,4 @@ web_custom_versions/
 openapi.yaml
 filtered-openapi.yaml
 uv.lock
+/custom_nodes_quarantine/
@@ -0,0 +1 @@
+LLM.md
@@ -0,0 +1 @@
+LLM.md
@@ -1,2 +1,2 @@
 # Admins
-* @comfyanonymous @kosinkadink @guill
+* @hanzoai/studio
@@ -1,12 +1,12 @@
-# Contributing to ComfyUI
+# Contributing to Hanzo Studio

-Welcome, and thank you for your interest in contributing to ComfyUI!
+Welcome, and thank you for your interest in contributing to Hanzo Studio!

 There are several ways in which you can contribute, beyond writing code. The goal of this document is to provide a high-level overview of how you can get involved.

 ## Asking Questions

-Have a question? Instead of opening an issue, please ask on [Discord](https://comfy.org/discord) or [Matrix](https://app.element.io/#/room/%23comfyui_space%3Amatrix.org) channels. Our team and the community will help you.
+Have a question? Instead of opening an issue, please ask on [Discord](https://discord.gg/hanzoai) first. Our team and the community will help you.

 ## Providing Feedback

@@ -16,24 +16,24 @@ See the `#bug-report`, `#feature-request` and `#feedback` channels on Discord.

 ## Reporting Issues

-Have you identified a reproducible problem in ComfyUI? Do you have a feature request? We want to hear about it! Here's how you can report your issue as effectively as possible.
+Have you identified a reproducible problem in Hanzo Studio? Do you have a feature request? We want to hear about it! Here's how you can report your issue as effectively as possible.


 ### Look For an Existing Issue

-Before you create a new issue, please do a search in [open issues](https://github.com/comfyanonymous/ComfyUI/issues) to see if the issue or feature request has already been filed.
+Before you create a new issue, please do a search in [open issues](https://github.com/hanzoai/studio/issues) to see if the issue or feature request has already been filed.

 If you find your issue already exists, make relevant comments and add your [reaction](https://github.com/blog/2119-add-reactions-to-pull-requests-issues-and-comments). Use a reaction in place of a "+1" comment:

-* 👍 - upvote
-* 👎 - downvote
+* upvote
+* downvote

 If you cannot find an existing issue that describes your bug or feature, create a new issue. We have an issue template in place to organize new issues.


 ### Creating Pull Requests

-* Please refer to the article on [creating pull requests](https://github.com/comfyanonymous/ComfyUI/wiki/How-to-Contribute-Code) and contributing to this project.
+* Please refer to the article on [creating pull requests](https://github.com/hanzoai/studio/wiki/How-to-Contribute-Code) and contributing to this project.


 ## Thank You
@@ -0,0 +1,51 @@
+FROM python:3.11-slim AS base
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+        git \
+        build-essential \
+        libgl1 \
+        libglib2.0-0 \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+
+# Install PyTorch CPU first (large layer, cached separately)
+RUN pip install --no-cache-dir \
+    torch torchvision torchaudio \
+    --index-url https://download.pytorch.org/whl/cpu
+
+# Install remaining dependencies
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Apply Hanzo Studio branding to frontend package
+COPY branding/ /tmp/branding/
+RUN chmod +x /tmp/branding/apply-branding.sh && /tmp/branding/apply-branding.sh && rm -rf /tmp/branding
+
+# Copy application code
+COPY . .
+
+# Vendor the Hanzo Studio custom-node packs (segmentation, controlnet, ipadapter,
+# upscaling, video, utils) at their pinned commits and install their deps with the
+# torch/numpy/transformers stack locked. See custom_nodes/hanzo-packs.txt.
+RUN chmod +x scripts/install_custom_nodes.sh && scripts/install_custom_nodes.sh
+
+# Create directories for runtime volumes
+RUN mkdir -p models output input custom_nodes user
+
+EXPOSE 8188
+
+# Default: listen on all interfaces, CPU mode
+# Environment variables:
+#   STUDIO_ENABLE_IAM_AUTH=1      - Enable IAM auth via hanzo.id
+#   STUDIO_IAM_URL=https://hanzo.id
+#   STUDIO_NO_LOCALHOST_BYPASS=1  - Require auth even for localhost
+#   STUDIO_MULTI_TENANT=1         - Per-org storage isolation
+#   STUDIO_ORG_ID=default-org     - Default org ID
+#   STUDIO_ENABLE_BILLING=1       - Commerce billing integration
+#   STUDIO_BILLING_CHECK_BALANCE=1 - Check balance before prompts
+#   STUDIO_COMMERCE_URL=http://commerce.hanzo.svc:8001
+#   STUDIO_COMMERCE_TOKEN=...     - Commerce API token
+#   STUDIO_ENABLE_METRICS=1       - /metrics endpoint for VictoriaMetrics
+#   STUDIO_RATE_LIMIT_RPM=60      - Prompts per minute per org
+CMD ["python", "main.py", "--listen", "0.0.0.0", "--port", "8188", "--cpu"]
@@ -0,0 +1,191 @@
+# Hanzo Studio
+
+## Overview
+**The most powerful and modular visual AI engine and application.**
+
+## Tech Stack
+- **Language**: Python
+
+## Build & Run
+```bash
+uv sync
+uv run pytest
+```
+
+## Structure
+```
+studio/
+  CODEOWNERS
+  CONTRIBUTING.md
+  Dockerfile
+  LICENSE
+  QUANTIZATION.md
+  README.md
+  alembic.ini
+  alembic_db/
+  api_server/
+  app/
+  blueprints/
+  branding/
+  comfyui.log
+  comfyui.prev.log
+  comfyui.prev2.log
+```
+
+## Key Files
+- `README.md` -- Project documentation
+- `pyproject.toml` -- Python project config
+- `Dockerfile` -- Container build (applies `branding/` then runs `main.py`)
+- `hanzo.yml` + `.github/workflows/cicd.yml` -- canonical CI/CD (hanzoai/ci); builds `ghcr.io/hanzoai/studio`, rolls the `studio` operator Service CR at `studio.hanzo.ai`.
+
+## Custom-node packs ("hanzo packages")
+The popular ComfyUI packs are vendored as first-class hanzo packages, pinned and
+reproducible. One and only one way to add/bump them:
+
+- **Manifest**: `custom_nodes/hanzo-packs.txt` — `<dir> <git_url> <commit_sha>
+  <spdx>` lines (immutable SHAs). This is the tracked source of truth; the cloned
+  pack sources are gitignored (vendored at build).
+- **Deps**: `custom_nodes-requirements.txt` — hand-resolved, only what's not
+  already in `requirements.txt`. Installed with the studio torch(cu130)/NumPy 2.x/
+  Transformers 5.x stack **locked** so packs can never downgrade it.
+- **Installer**: `scripts/install_custom_nodes.sh` clones each pack at its pin and
+  installs deps; the lock is derived from the live env (correct for both the CPU
+  image and the GB10 cu130 venv). `ultralytics` is installed `--no-deps` (else it
+  pulls non-headless opencv). Local (GB10): `STUDIO_PY=.venv/bin/python
+  STUDIO_PIP="uv pip install --python .venv/bin/python" scripts/install_custom_nodes.sh`.
+- **Image**: `Dockerfile` runs the installer after `COPY . .`; `.dockerignore`
+  re-includes only the manifest + installer (`custom_nodes/*` / `scripts/*` form).
+  So `git push origin main` → CI builds `ghcr.io/hanzoai/studio` with the packs →
+  studio.hanzo.ai gets them on the next image build.
+
+**Compat shim — why packs work here at all.** This fork renamed ComfyUI's core
+packages (`comfy`→`studio`, `comfy_extras`→`studio_extras`, `comfy/comfy_types`→
+`studio/node_types`, and the `Comfy*`→`Studio*` API classes; see
+`scripts/rename_modules.py`). `studio_compat/` is one meta-path finder that lazily
+aliases every `comfy*` import to its `studio*` counterpart and mirrors
+`ComfyExtension`/`io.ComfyNode`→`Studio*` — so upstream packs run **unmodified**,
+no forks/renames. It is the phase-4 redirect `rename_modules.py` deferred, done
+with the 3.12 `find_spec` API. Activated by `import studio_compat` at the top of
+`main.py`. `nodes.py` also honors the upstream `comfy_entrypoint` V3 name.
+
+Restart the local worker only when idle: `scripts/studio-service-swap.sh` polls
+`/queue` and restarts on the first empty window. Bad packs are isolated by the
+loader (studio still boots); genuinely-incompatible ones go to
+`custom_nodes_quarantine/` (e.g. was-node-suite: hard `numba` dep vs NumPy 2.5).
+
+## Multi-tenant + IAM (cloud: studio.hanzo.ai)
+Standalone app; `console.hanzo.ai` link-outs land here already authenticated via
+shared Hanzo IAM (standard OIDC code flow). No embedding.
+
+- **Auth** (`middleware/iam_auth_middleware.py`): local **JWKS** JWT validation
+  against `${STUDIO_IAM_URL}/v1/iam/.well-known/jwks` — signature + `exp` +
+  `iss` + `aud` (client_id `hanzo-studio`). Org from the `owner` claim
+  (`organization` fallback) → `request["iam_user"]["org_id"]`. Anonymous mode:
+  off by default locally (loopback bypass); enable in cloud with
+  `STUDIO_ENABLE_IAM_AUTH=true` (the one auth switch — this is the
+  "STUDIO_AUTH=off default" behavior). Browser flow: unauth HTML → IAM
+  `authorize` (code+PKCE) → `/callback` exchanges the code, sets an httpOnly
+  session cookie (no frontend changes). `verify_jwt(...)` is a pure, unit-tested
+  function.
+- **Tenancy** (`folder_paths.py`, `app/user_manager.py`): with
+  `STUDIO_MULTI_TENANT=true`, userdata is `user/orgs/{org}/user/{user}/…` and
+  outputs are `output/orgs/{org}/…`. `get_public_user_directory(user, org)` is
+  org-rooted (fixed the bug where org userdata always resolved to `None`).
+  Execution outputs are scoped via `folder_paths.set_execution_org()`, bound by
+  the prompt worker from the queue item's `org_id`.
+- **GPU federation** (`middleware/{worker_client,prompt_router,compute_config,
+  visor_client}.py`): `/v1/workers/register` (heartbeat), `/v1/workers` (list),
+  `/v1/worker/execute` (in-cluster push fast path). Worker↔coordinator trust via
+  `X-Worker-Token` (`STUDIO_WORKER_TOKEN`, KMS-sourced).
+- **Durable render queue** (`middleware/tasks_queue.py`, `docs/federation.md`):
+  `SqlitePromptQueue` — crash-durable render queue in a single SQLite file
+  (stdlib `sqlite3`, WAL, **zero external processes**). `STUDIO_QUEUE_DB=<path>`
+  → `server.py` swaps `PromptQueue` for it (precedence **STUDIO_QUEUE_DB >
+  STUDIO_PERSIST_QUEUE > memory**; default local behavior unchanged). The
+  `PromptQueue` seam maps to a durable job state machine: `put→INSERT (pending,
+  idempotent on prompt_id)`, `get→claim next pending under BEGIN IMMEDIATE
+  (exactly-once, leased)`, `task_done→done | retry/failed`. Crash-recovery: a
+  lease + reap returns an abandoned claim to `pending` (on every get(), a
+  heartbeat thread, and on boot) so another process re-runs it — idempotent
+  (SaveImage suffixes increment). Multiple Studio processes on the same DB file
+  compete safely. Tested: `middleware_test/tasks_queue_test.py` (incl.
+  crash-recovery across instances). Future (federation.md §6): a remote queue
+  backend served by Hanzo Tasks + a Go/unified-binary (HIP-0106) migration.
+- **Engine selector** (`middleware/engine_selector.py`): `/v1/engines` lists
+  execution targets for the org (`local` + registered compute_config workers) and
+  `PUT /v1/engines/default` sets a per-org default (stored on
+  `ComputeProfile.default_engine`). `prompt_router.route_prompt` routes to the
+  chosen worker; `local` = unchanged. Leased cloud machines (Visor
+  `GET /v1/machines`) are a future engine class (interface stubbed, not built).
+  Frontend picker is a TODO. Tested: `middleware_test/engine_selector_test.py`.
+- **Chat Copilot** (`middleware/copilot.py` + `branding/hanzo-copilot.{js,css}`):
+  a sidebar chat that reads and MUTATES the workflow graph in natural language.
+  Backend `POST /v1/copilot/chat` proxies one OpenAI tool-calling round to a
+  chat endpoint (`STUDIO_COPILOT_URL`; default = local engine
+  `127.0.0.1:1234` if its port is open, else `api.hanzo.ai`; `STUDIO_COPILOT_MODEL`
+  default `zen`; token from `STUDIO_COPILOT_TOKEN`→`STUDIO_COMMERCE_TOKEN`→request
+  bearer). It returns `{reply, ops}`; `add_node` ops are validated against
+  `nodes.NODE_CLASS_MAPPINGS` server-side so the model can't invent node types.
+  The **frontend** applies ops against `app.graph` (LiteGraph) — op schema:
+  `add_node`(id?/pos?) · `set_widget` · `connect`(slots by name or index) ·
+  `set_prompt` · `move_node` · `delete_node` · `layout` (columnar tidy) ·
+  `queue`. Every op is guarded (unknown type/slot = skip + note, never throw).
+  Injected into the prebuilt frontend by `branding/patch_copilot.py` (copies the
+  bundle into static/, CSS `<link>` in `<head>`, deferred `<script>` before
+  `</body>`; idempotent, wired as step 9 of `apply-branding.sh`) — survives
+  frontend upgrades. `window.HanzoCopilot.applyOps` is exposed for tests. Tab
+  registered via `app.extensionManager.registerSidebarTab` (id `hanzo-copilot`).
+  Tested: `middleware_test/copilot_test.py` (op-validation + mocked tool loop) and
+  `branding/copilot_smoke.py` (headless: applier mutates a mock graph + panel
+  renders). Live end-to-end needs one server restart to register the route.
+- **Identity user menu + session API** (`middleware/session.py` +
+  `branding/hanzo-identity.{js,css}`): the top-right user menu, driven entirely
+  by the IAM-validated token. Backend (thin, `/v1` house style, registered in
+  `add_routes` so it works auth-on and auth-off): `GET /v1/session` →
+  `{user,email,org,orgs[],project,projects[],console_url,iam_url,authenticated}`
+  read from `request["iam_user"]`; `POST /v1/session/org` sets the active org
+  (validated against membership → `studio_active_org` cookie); `POST
+  /v1/session/project` sets the workflow-workspace project scope; `GET|POST
+  /logout` clears the session + selection cookies and bounces to the IAM
+  end-session → `/login`. **Org switching is real, one hook**: the auth
+  middleware applies `session.resolve_org(...)` to a COPY of the validated user
+  (never the cached dict) so `iam_user["org_id"]` — the id every tenancy/output
+  path already reads — reflects the switch; membership comes from
+  `_orgs_from_claims` (`owner` + `organizations`/`orgs`/`groups`, list or CSV or
+  `{name}` dicts, home first, deduped). Frontend is a SPA-agnostic fixed pill +
+  dropdown (avatar/initials, user, org switcher, project switcher, Console
+  link → `console.hanzo.ai`, Logout); 401 → "Sign in with Hanzo" → `/login`.
+  Injected by `branding/patch_identity.py` (step 10 of `apply-branding.sh`,
+  same seam as the copilot). `window.HanzoIdentity` is exposed for tests.
+  Tested: `middleware_test/session_test.py` (resolve/orgs/routes/logout, real
+  aiohttp app) + `scratchpad/studio-iam/test_identity.py` (headless: pill,
+  dropdown, org switch re-scope, signed-out). The `/v1/session` routes need one
+  server restart to register (static + de-Comfy load without restart).
+- **De-Comfy display strings** (`branding/patch_destring.py`, step 11 —
+  runs LAST): the systematic English brand-word sweep the curated phrase list in
+  `patch_frontend.py` structurally can't reach. Rule 1: whole-word `ComfyUI` →
+  `Hanzo Studio` only where it reads as a display word (preceded by
+  open-quote/space/`>`/`(`, followed by close-quote/space/sentence-punct) — that
+  boundary skips every code use in the bundle (`ComfyUIStarted`, `.ComfyUI`,
+  `=ComfyUI`, the `/^(ComfyUI-.../` regex, dotted i18n keys `.category.ComfyUI`)
+  and hyphenated product names (`ComfyUI-Manager`). Rule 2: curated bare-`Comfy`
+  **values** as exact `key:` value`` pairs so the Settings dialog **keys**
+  (`Comfy`, `Comfy-Desktop`, `Comfy.ColorPalette`) are preserved while the
+  displayed section header becomes **Studio** / **Studio Desktop** (this is the
+  "Settings must not say Comfy" fix) + `Comfy Cloud` → `Hanzo Cloud`. Scope:
+  English only — files above `LOCALE_RATIO` (0.15%) non-ASCII are skipped (all 33
+  locale bundles are ≥0.31%; English bundles ~0.02%) and each match needs a
+  pure-ASCII window, so the non-English `main-*/nodeDefs-*/commands-*` chunks are
+  left as-is (noted, out of scope). Idempotent. Verified: served English display
+  `ComfyUI` 63→0; a few example filesystem paths (`Documents/ComfyUI`) and the
+  external comfy.org service labels (`Comfy API Key`, `Comfy Node Registry`,
+  behind disabled API-nodes) are intentionally left. patch_frontend.py keeps its
+  orthogonal concern (URLs/domains + `Comfy-Org` → `Hanzo AI`).
+
+## Tests
+`tests-unit/{folder_paths_test,middleware_test,app_test,prompt_server_test}` —
+run `uv run pytest tests-unit/folder_paths_test tests-unit/middleware_test
+tests-unit/app_test tests-unit/prompt_server_test -q`. The auth/tenancy work is
+covered by `middleware_test/iam_auth_test.py`,
+`middleware_test/session_test.py` and
+`folder_paths_test/org_scoping_test.py`.
@@ -0,0 +1,42 @@
+Hanzo Studio
+============
+
+Hanzo Studio is a fork of ComfyUI (https://github.com/comfyanonymous/ComfyUI),
+Copyright (c) ComfyUI contributors, licensed under the GNU General Public
+License v3.0 (GPL-3.0).
+
+Modifications Copyright (c) 2026 Hanzo Industries Inc, also released under the
+GNU General Public License v3.0 (GPL-3.0). See the LICENSE file for the full
+license text.
+
+As required by the GPL-3.0, this fork remains under the same license as the
+upstream project. The original ComfyUI copyright notices are retained.
+
+Modifications made in this fork
+-------------------------------
+
+- Branding: user-visible name changed from "ComfyUI" to "Hanzo Studio",
+  including the served page <title>, favicon, in-app logos, and display
+  strings. The prebuilt frontend package (comfyui-frontend-package) is patched
+  at install time by branding/apply-branding.sh; source assets live in
+  branding/. Backend Python packages are namespaced under studio_* and the
+  server reports itself as "Hanzo Studio".
+
+- Hanzo Engine integration nodes (custom_nodes/hanzo_engine/): first-party
+  nodes that run AI workloads on a local Hanzo Engine OpenAI-compatible server
+  over a shared client — HanzoChat (chat/completions, streaming), HanzoImageGen
+  (images/generations), HanzoTTS (audio/speech), HanzoASR
+  (audio/transcriptions), HanzoEngineRequest (generic /v1 escape hatch),
+  HanzoVisionCaption (vision chat/completions), HanzoTextToVideo (videos),
+  HanzoImageTo3D (3d), and HanzoSaveText. Hanzo Engine is the native-Rust,
+  all-modality inference and training backend.
+
+- Fashion/swimwear starter workflows (user/default/workflows/fashion/):
+  product-shot, garment-edit, and caption-dataset workflow templates for a
+  designer's day-to-day use.
+
+- Deployment/integration middleware for Hanzo infrastructure (IAM auth via
+  hanzo.id, commerce/billing, metrics), wired through environment variables and
+  the Dockerfile.
+
+Third-party components retain their own upstream copyrights and licenses.
@@ -1,4 +1,4 @@
-# The Comfy guide to Quantization
+# The Hanzo Studio guide to Quantization


 ## How does quantization work?
@@ -27,7 +27,7 @@ tensor_dq ~ tensor
 Given that additional information (scaling factor) is needed to "interpret" the quantized values, we describe those as derived datatypes.


-## Quantization in Comfy
+## Quantization in Hanzo Studio

 ```
 QuantizedTensor (torch.Tensor subclass)
@@ -39,7 +39,7 @@ MixedPrecisionOps + Metadata Detection

 ### Representation

-To represent these derived datatypes, ComfyUI uses a subclass of torch.Tensor to implements these using the `QuantizedTensor` class found in `comfy/quant_ops.py`
+To represent these derived datatypes, Hanzo Studio uses a subclass of torch.Tensor to implements these using the `QuantizedTensor` class found in `studio/quant_ops.py`

 A `Layout` class defines how a specific quantization format behaves:
 - Required parameters
@@ -47,7 +47,7 @@ A `Layout` class defines how a specific quantization format behaves:
 - De-Quantize method

 ```python
-from comfy.quant_ops import QuantizedLayout
+from studio.quant_ops import QuantizedLayout

 class MyLayout(QuantizedLayout):
    @classmethod
@@ -67,7 +67,7 @@ The first is a **generic registry** that handles operations common to all quanti

 The second registry is layout-specific and allows to implement fast-paths like nn.Linear.
 ```python
-from comfy.quant_ops import register_layout_op
+from studio.quant_ops import register_layout_op

@register_layout_op(torch.ops.aten.linear.default, MyLayout)
 def my_linear(func, args, kwargs):
@@ -80,7 +80,7 @@ For any unsupported operation, QuantizedTensor will fallback to call `dequantize

 ### Mixed Precision

-The `MixedPrecisionOps` class (lines 542-648 in `comfy/ops.py`) enables per-layer quantization decisions, allowing different layers in a model to use different precisions. This is activated when a model config contains a `layer_quant_config` dictionary that specifies which layers should be quantized and how.
+The `MixedPrecisionOps` class (lines 542-648 in `studio/ops.py`) enables per-layer quantization decisions, allowing different layers in a model to use different precisions. This is activated when a model config contains a `layer_quant_config` dictionary that specifies which layers should be quantized and how.

 **Architecture:**

@@ -125,7 +125,7 @@ We define 4 possible scaling parameters that should cover most recipes in the ne
 |--------|---------------|--------------|----------------|-----------------|-------------|
 | float8_e4m3fn | float32 | float32 (scalar) | - | - | float32 (scalar) |

-You can find the defined formats in `comfy/quant_ops.py` (QUANT_ALGOS).
+You can find the defined formats in `studio/quant_ops.py` (QUANT_ALGOS).

 ### Quantization Metadata

@@ -1,92 +1,74 @@
+<p align="center"><img src=".github/hero.svg" alt="studio" width="880"></p>
+
 <div align="center">

-# ComfyUI
+# Hanzo Studio
 **The most powerful and modular visual AI engine and application.**


 [![Website][website-shield]][website-url]
 [![Dynamic JSON Badge][discord-shield]][discord-url]
 [![Twitter][twitter-shield]][twitter-url]
-[![Matrix][matrix-shield]][matrix-url]
 <br>
 [![][github-release-shield]][github-release-link]
 [![][github-release-date-shield]][github-release-link]
 [![][github-downloads-shield]][github-downloads-link]
 [![][github-downloads-latest-shield]][github-downloads-link]

-[matrix-shield]: https://img.shields.io/badge/Matrix-000000?style=flat&logo=matrix&logoColor=white
-[matrix-url]: https://app.element.io/#/room/%23comfyui_space%3Amatrix.org
-[website-shield]: https://img.shields.io/badge/ComfyOrg-4285F4?style=flat
-[website-url]: https://www.comfy.org/
+[website-shield]: https://img.shields.io/badge/HanzoAI-4285F4?style=flat
+[website-url]: https://www.hanzo.ai/
 <!-- Workaround to display total user from https://github.com/badges/shields/issues/4500#issuecomment-2060079995 -->
-[discord-shield]: https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fdiscord.com%2Fapi%2Finvites%2Fcomfyorg%3Fwith_counts%3Dtrue&query=%24.approximate_member_count&logo=discord&logoColor=white&label=Discord&color=green&suffix=%20total
-[discord-url]: https://www.comfy.org/discord
-[twitter-shield]: https://img.shields.io/twitter/follow/ComfyUI
-[twitter-url]: https://x.com/ComfyUI
+[discord-shield]: https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fdiscord.com%2Fapi%2Finvites%2Fhanzoai%3Fwith_counts%3Dtrue&query=%24.approximate_member_count&logo=discord&logoColor=white&label=Discord&color=green&suffix=%20total
+[discord-url]: https://discord.gg/hanzoai
+[twitter-shield]: https://img.shields.io/twitter/follow/hanaboroai
+[twitter-url]: https://x.com/hanzoai

-[github-release-shield]: https://img.shields.io/github/v/release/comfyanonymous/ComfyUI?style=flat&sort=semver
-[github-release-link]: https://github.com/comfyanonymous/ComfyUI/releases
-[github-release-date-shield]: https://img.shields.io/github/release-date/comfyanonymous/ComfyUI?style=flat
-[github-downloads-shield]: https://img.shields.io/github/downloads/comfyanonymous/ComfyUI/total?style=flat
-[github-downloads-latest-shield]: https://img.shields.io/github/downloads/comfyanonymous/ComfyUI/latest/total?style=flat&label=downloads%40latest
-[github-downloads-link]: https://github.com/comfyanonymous/ComfyUI/releases
+[github-release-shield]: https://img.shields.io/github/v/release/hanzoai/studio?style=flat&sort=semver
+[github-release-link]: https://github.com/hanzoai/studio/releases
+[github-release-date-shield]: https://img.shields.io/github/release-date/hanzoai/studio?style=flat
+[github-downloads-shield]: https://img.shields.io/github/downloads/hanzoai/studio/total?style=flat
+[github-downloads-latest-shield]: https://img.shields.io/github/downloads/hanzoai/studio/latest/total?style=flat&label=downloads%40latest
+[github-downloads-link]: https://github.com/hanzoai/studio/releases

-![ComfyUI Screenshot](https://github.com/user-attachments/assets/7ccaf2c1-9b72-41ae-9a89-5688c94b7abe)
+![Hanzo Studio Screenshot](https://github.com/user-attachments/assets/7ccaf2c1-9b72-41ae-9a89-5688c94b7abe)
 </div>

-ComfyUI lets you design and execute advanced stable diffusion pipelines using a graph/nodes/flowchart based interface. Available on Windows, Linux, and macOS.
+Hanzo Studio lets you design and execute advanced stable diffusion pipelines using a graph/nodes/flowchart based interface. Available on Windows, Linux, and macOS.
+
+## Upstream & License
+
+Hanzo Studio is a fork of [**ComfyUI**](https://github.com/comfyanonymous/ComfyUI) by comfyanonymous and the ComfyUI contributors — full credit to the upstream project for the engine this builds on. ComfyUI is licensed under the **GNU General Public License v3.0 (GPL-3.0)**, and this fork stays under the same license. All modifications in this fork are likewise GPL-3.0.
+
+See [`LICENSE`](LICENSE) for the full license text and [`NOTICE`](NOTICE) for the fork's attribution and a summary of what it changes (branding, Hanzo Engine integration nodes, and fashion workflow templates).

 ## Get Started

-#### [Desktop Application](https://www.comfy.org/download)
- The easiest way to get started.
- Available on Windows & macOS.
-
-#### [Windows Portable Package](#installing)
- Get the latest commits and completely portable.
- Available on Windows.
-
 #### [Manual Install](#manual-install-windows-linux)
 Supports all operating systems and GPU types (NVIDIA, AMD, Intel, Apple Silicon, Ascend).

-## [Examples](https://comfyanonymous.github.io/ComfyUI_examples/)
-See what ComfyUI can do with the [example workflows](https://comfyanonymous.github.io/ComfyUI_examples/).
+#### Docker (Recommended for servers)
+```bash
+docker pull ghcr.io/hanzoai/studio:latest
+docker run -p 8188:8188 ghcr.io/hanzoai/studio:latest --listen --cpu
+```

 ## Features
 - Nodes/graph/flowchart interface to experiment and create complex Stable Diffusion workflows without needing to code anything.
 - Image Models
-   - SD1.x, SD2.x ([unCLIP](https://comfyanonymous.github.io/ComfyUI_examples/unclip/))
-   - [SDXL](https://comfyanonymous.github.io/ComfyUI_examples/sdxl/), [SDXL Turbo](https://comfyanonymous.github.io/ComfyUI_examples/sdturbo/)
-   - [Stable Cascade](https://comfyanonymous.github.io/ComfyUI_examples/stable_cascade/)
-   - [SD3 and SD3.5](https://comfyanonymous.github.io/ComfyUI_examples/sd3/)
-   - Pixart Alpha and Sigma
-   - [AuraFlow](https://comfyanonymous.github.io/ComfyUI_examples/aura_flow/)
-   - [HunyuanDiT](https://comfyanonymous.github.io/ComfyUI_examples/hunyuan_dit/)
-   - [Flux](https://comfyanonymous.github.io/ComfyUI_examples/flux/)
-   - [Lumina Image 2.0](https://comfyanonymous.github.io/ComfyUI_examples/lumina2/)
-   - [HiDream](https://comfyanonymous.github.io/ComfyUI_examples/hidream/)
-   - [Qwen Image](https://comfyanonymous.github.io/ComfyUI_examples/qwen_image/)
-   - [Hunyuan Image 2.1](https://comfyanonymous.github.io/ComfyUI_examples/hunyuan_image/)
-   - [Flux 2](https://comfyanonymous.github.io/ComfyUI_examples/flux2/)
-   - [Z Image](https://comfyanonymous.github.io/ComfyUI_examples/z_image/)
+   - SD1.x, SD2.x, SDXL, SDXL Turbo
+   - Stable Cascade, SD3 and SD3.5
+   - Pixart Alpha and Sigma, AuraFlow, HunyuanDiT
+   - Flux, Flux 2, Lumina Image 2.0, HiDream
+   - Qwen Image, Hunyuan Image 2.1, Z Image
 - Image Editing Models
-   - [Omnigen 2](https://comfyanonymous.github.io/ComfyUI_examples/omnigen/)
-   - [Flux Kontext](https://comfyanonymous.github.io/ComfyUI_examples/flux/#flux-kontext-image-editing-model)
-   - [HiDream E1.1](https://comfyanonymous.github.io/ComfyUI_examples/hidream/#hidream-e11)
-   - [Qwen Image Edit](https://comfyanonymous.github.io/ComfyUI_examples/qwen_image/#edit-model)
+   - Omnigen 2, Flux Kontext, HiDream E1.1, Qwen Image Edit
 - Video Models
-   - [Stable Video Diffusion](https://comfyanonymous.github.io/ComfyUI_examples/video/)
-   - [Mochi](https://comfyanonymous.github.io/ComfyUI_examples/mochi/)
-   - [LTX-Video](https://comfyanonymous.github.io/ComfyUI_examples/ltxv/)
-   - [Hunyuan Video](https://comfyanonymous.github.io/ComfyUI_examples/hunyuan_video/)
-   - [Wan 2.1](https://comfyanonymous.github.io/ComfyUI_examples/wan/)
-   - [Wan 2.2](https://comfyanonymous.github.io/ComfyUI_examples/wan22/)
-   - [Hunyuan Video 1.5](https://docs.comfy.org/tutorials/video/hunyuan/hunyuan-video-1-5)
+   - Stable Video Diffusion, Mochi, LTX-Video
+   - Hunyuan Video, Wan 2.1, Wan 2.2, Hunyuan Video 1.5
 - Audio Models
-   - [Stable Audio](https://comfyanonymous.github.io/ComfyUI_examples/audio/)
-   - [ACE Step](https://comfyanonymous.github.io/ComfyUI_examples/audio/)
+   - Stable Audio, ACE Step
 - 3D Models
-   - [Hunyuan3D 2.0](https://docs.comfy.org/tutorials/3d/hunyuan3D-2)
+   - Hunyuan3D 2.0
 - Asynchronous Queue system
 - Many optimizations: Only re-executes the parts of the workflow that changes between executions.
 - Smart memory management: can automatically run large models on GPUs with as low as 1GB vram with smart offloading.
@@ -94,45 +76,23 @@ See what ComfyUI can do with the [example workflows](https://comfyanonymous.gith
 - Can load ckpt and safetensors: All in one checkpoints or standalone diffusion models, VAEs and CLIP models.
 - Safe loading of ckpt, pt, pth, etc.. files.
 - Embeddings/Textual inversion
- [Loras (regular, locon and loha)](https://comfyanonymous.github.io/ComfyUI_examples/lora/)
- [Hypernetworks](https://comfyanonymous.github.io/ComfyUI_examples/hypernetworks/)
+- Loras (regular, locon and loha)
+- Hypernetworks
 - Loading full workflows (with seeds) from generated PNG, WebP and FLAC files.
 - Saving/Loading workflows as Json files.
- Nodes interface can be used to create complex workflows like one for [Hires fix](https://comfyanonymous.github.io/ComfyUI_examples/2_pass_txt2img/) or much more advanced ones.
- [Area Composition](https://comfyanonymous.github.io/ComfyUI_examples/area_composition/)
- [Inpainting](https://comfyanonymous.github.io/ComfyUI_examples/inpaint/) with both regular and inpainting models.
- [ControlNet and T2I-Adapter](https://comfyanonymous.github.io/ComfyUI_examples/controlnet/)
- [Upscale Models (ESRGAN, ESRGAN variants, SwinIR, Swin2SR, etc...)](https://comfyanonymous.github.io/ComfyUI_examples/upscale_models/)
- [GLIGEN](https://comfyanonymous.github.io/ComfyUI_examples/gligen/)
- [Model Merging](https://comfyanonymous.github.io/ComfyUI_examples/model_merging/)
- [LCM models and Loras](https://comfyanonymous.github.io/ComfyUI_examples/lcm/)
- Latent previews with [TAESD](#how-to-show-high-quality-previews)
+- Nodes interface can be used to create complex workflows like one for Hires fix or much more advanced ones.
+- Area Composition
+- Inpainting with both regular and inpainting models.
+- ControlNet and T2I-Adapter
+- Upscale Models (ESRGAN, ESRGAN variants, SwinIR, Swin2SR, etc...)
+- GLIGEN
+- Model Merging
+- LCM models and Loras
+- Latent previews with TAESD
 - Works fully offline: core will never download anything unless you want to.
- Optional API nodes to use paid models from external providers through the online [Comfy API](https://docs.comfy.org/tutorials/api-nodes/overview) disable with: `--disable-api-nodes`
+- Optional API nodes to use paid models from external providers through the online API. Disable with: `--disable-api-nodes`
 - [Config file](extra_model_paths.yaml.example) to set the search paths for models.

-Workflow examples can be found on the [Examples page](https://comfyanonymous.github.io/ComfyUI_examples/)
-
-## Release Process
-
-ComfyUI follows a weekly release cycle targeting Monday but this regularly changes because of model releases or large changes to the codebase. There are three interconnected repositories:
-
-1. **[ComfyUI Core](https://github.com/comfyanonymous/ComfyUI)**
-   - Releases a new stable version (e.g., v0.7.0) roughly every week.
-   - Starting from v0.4.0 patch versions will be used for fixes backported onto the current stable release.
-   - Minor versions will be used for releases off the master branch.
-   - Patch versions may still be used for releases on the master branch in cases where a backport would not make sense.
-   - Commits outside of the stable release tags may be very unstable and break many custom nodes.
-   - Serves as the foundation for the desktop release
-
-2. **[ComfyUI Desktop](https://github.com/Comfy-Org/desktop)**
-   - Builds a new release using the latest stable core version
-
-3. **[ComfyUI Frontend](https://github.com/Comfy-Org/ComfyUI_frontend)**
-   - Weekly frontend updates are merged into the core repository
-   - Features are frozen for the upcoming core release
-   - Development continues for the next release cycle
-
 ## Shortcuts

 | Keybind                            | Explanation                                                                                                        |
@@ -173,39 +133,6 @@ ComfyUI follows a weekly release cycle targeting Monday but this regularly chang

 # Installing

-## Windows Portable
-
-There is a portable standalone build for Windows that should work for running on Nvidia GPUs or for running on your CPU only on the [releases page](https://github.com/comfyanonymous/ComfyUI/releases).
-
-### [Direct link to download](https://github.com/comfyanonymous/ComfyUI/releases/latest/download/ComfyUI_windows_portable_nvidia.7z)
-
-Simply download, extract with [7-Zip](https://7-zip.org) or with the windows explorer on recent windows versions and run. For smaller models you normally only need to put the checkpoints (the huge ckpt/safetensors files) in: ComfyUI\models\checkpoints but many of the larger models have multiple files. Make sure to follow the instructions to know which subfolder to put them in ComfyUI\models\
-
-If you have trouble extracting it, right click the file -> properties -> unblock
-
-The portable above currently comes with python 3.13 and pytorch cuda 13.0. Update your Nvidia drivers if it doesn't start.
-
-#### Alternative Downloads:
-
-[Experimental portable for AMD GPUs](https://github.com/comfyanonymous/ComfyUI/releases/latest/download/ComfyUI_windows_portable_amd.7z)
-
-[Portable with pytorch cuda 12.8 and python 3.12](https://github.com/comfyanonymous/ComfyUI/releases/latest/download/ComfyUI_windows_portable_nvidia_cu128.7z).
-
-[Portable with pytorch cuda 12.6 and python 3.12](https://github.com/comfyanonymous/ComfyUI/releases/latest/download/ComfyUI_windows_portable_nvidia_cu126.7z) (Supports Nvidia 10 series and older GPUs).
-
-#### How do I share models between another UI and ComfyUI?
-
-See the [Config file](extra_model_paths.yaml.example) to set the search paths for models. In the standalone windows build you can find this file in the ComfyUI directory. Rename this file to extra_model_paths.yaml and edit it with your favorite text editor.
-
-
-## [comfy-cli](https://docs.comfy.org/comfy-cli/getting-started)
-
-You can install and start ComfyUI using comfy-cli:
-```bash
-pip install comfy-cli
-comfy install
-```
-
 ## Manual Install (Windows, Linux)

 Python 3.14 works but some custom nodes may have issues. The free threaded variant works but some dependencies will enable the GIL so it's not fully supported.
@@ -229,9 +156,9 @@ AMD users can install rocm and pytorch with pip if you don't have it already ins

 ```pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm7.1```

-This is the command to install the nightly with ROCm 7.1 which might have some performance improvements:
+This is the command to install the nightly with ROCm 7.2 which might have some performance improvements:

-```pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/rocm7.1```
+```pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/rocm7.2```


 ### AMD GPUs (Experimental: Windows and Linux), RDNA 3, 3.5 and 4 only.
@@ -282,24 +209,24 @@ And install it again with the command above.

 ### Dependencies

-Install the dependencies by opening your terminal inside the ComfyUI folder and:
+Install the dependencies by opening your terminal inside the Hanzo Studio folder and:

 ```pip install -r requirements.txt```

-After this you should have everything installed and can proceed to running ComfyUI.
+After this you should have everything installed and can proceed to running Hanzo Studio.

 ### Others:

 #### Apple Mac silicon

-You can install ComfyUI in Apple Mac silicon (M1 or M2) with any recent macOS version.
+You can install Hanzo Studio in Apple Mac silicon (M1 or M2) with any recent macOS version.

 1. Install pytorch nightly. For instructions, read the [Accelerated PyTorch training on Mac](https://developer.apple.com/metal/pytorch/) Apple Developer guide (make sure to install the latest pytorch nightly).
-1. Follow the [ComfyUI manual installation](#manual-install-windows-linux) instructions for Windows and Linux.
-1. Install the ComfyUI [dependencies](#dependencies). If you have another Stable Diffusion UI [you might be able to reuse the dependencies](#i-already-have-another-ui-for-stable-diffusion-installed-do-i-really-have-to-install-all-of-these-dependencies).
-1. Launch ComfyUI by running `python main.py`
+1. Follow the [Hanzo Studio manual installation](#manual-install-windows-linux) instructions for Windows and Linux.
+1. Install the Hanzo Studio [dependencies](#dependencies). If you have another Stable Diffusion UI you might be able to reuse the dependencies.
+1. Launch Hanzo Studio by running `python main.py`

-> **Note**: Remember to add your models, VAE, LoRAs etc. to the corresponding Comfy folders, as discussed in [ComfyUI manual installation](#manual-install-windows-linux).
+> **Note**: Remember to add your models, VAE, LoRAs etc. to the corresponding folders, as discussed in [Hanzo Studio manual installation](#manual-install-windows-linux).

 #### Ascend NPUs

@@ -308,7 +235,7 @@ For models compatible with Ascend Extension for PyTorch (torch_npu). To get star
 1. Begin by installing the recommended or newer kernel version for Linux as specified in the Installation page of torch-npu, if necessary.
 2. Proceed with the installation of Ascend Basekit, which includes the driver, firmware, and CANN, following the instructions provided for your specific platform.
 3. Next, install the necessary packages for torch-npu by adhering to the platform-specific instructions on the [Installation](https://ascend.github.io/docs/sources/pytorch/install.html#pytorch) page.
-4. Finally, adhere to the [ComfyUI manual installation](#manual-install-windows-linux) guide for Linux. Once all components are installed, you can run ComfyUI as described earlier.
+4. Finally, adhere to the [Hanzo Studio manual installation](#manual-install-windows-linux) guide for Linux. Once all components are installed, you can run Hanzo Studio as described earlier.

 #### Cambricon MLUs

@@ -316,19 +243,19 @@ For models compatible with Cambricon Extension for PyTorch (torch_mlu). Here's a

 1. Install the Cambricon CNToolkit by adhering to the platform-specific instructions on the [Installation](https://www.cambricon.com/docs/sdk_1.15.0/cntoolkit_3.7.2/cntoolkit_install_3.7.2/index.html)
 2. Next, install the PyTorch(torch_mlu) following the instructions on the [Installation](https://www.cambricon.com/docs/sdk_1.15.0/cambricon_pytorch_1.17.0/user_guide_1.9/index.html)
-3. Launch ComfyUI by running `python main.py`
+3. Launch Hanzo Studio by running `python main.py`

 #### Iluvatar Corex

 For models compatible with Iluvatar Extension for PyTorch. Here's a step-by-step guide tailored to your platform and installation method:

 1. Install the Iluvatar Corex Toolkit by adhering to the platform-specific instructions on the [Installation](https://support.iluvatar.com/#/DocumentCentre?id=1&nameCenter=2&productId=520117912052801536)
-2. Launch ComfyUI by running `python main.py`
+2. Launch Hanzo Studio by running `python main.py`


-## [ComfyUI-Manager](https://github.com/Comfy-Org/ComfyUI-Manager/tree/manager-v4)
+## Manager

-**ComfyUI-Manager** is an extension that allows you to easily install, update, and manage custom nodes for ComfyUI.
+The **Manager** extension allows you to easily install, update, and manage custom nodes for Hanzo Studio.

 ### Setup

@@ -337,7 +264,7 @@ For models compatible with Iluvatar Extension for PyTorch. Here's a step-by-step
   pip install -r manager_requirements.txt
   ```

-2. Enable the manager with the `--enable-manager` flag when running ComfyUI:
+2. Enable the manager with the `--enable-manager` flag when running Hanzo Studio:
   ```bash
   python main.py --enable-manager
   ```
@@ -346,7 +273,7 @@ For models compatible with Iluvatar Extension for PyTorch. Here's a step-by-step

 | Flag | Description |
 |------|-------------|
-| `--enable-manager` | Enable ComfyUI-Manager |
+| `--enable-manager` | Enable the Manager |
 | `--enable-manager-legacy-ui` | Use the legacy manager UI instead of the new UI (requires `--enable-manager`) |
 | `--disable-manager-ui` | Disable the manager UI and endpoints while keeping background features like security checks and scheduled installation completion (requires `--enable-manager`) |

@@ -365,7 +292,7 @@ For AMD 7600 and maybe other RDNA3 cards: ```HSA_OVERRIDE_GFX_VERSION=11.0.0 pyt

 ### AMD ROCm Tips

-You can enable experimental memory efficient attention on recent pytorch in ComfyUI on some AMD GPUs using this command, it should already be enabled by default on RDNA3. If this improves speed for you on latest pytorch on your GPU please report it so that I can enable it by default.
+You can enable experimental memory efficient attention on recent pytorch on some AMD GPUs using this command, it should already be enabled by default on RDNA3. If this improves speed for you on latest pytorch on your GPU please report it so that we can enable it by default.

 ```TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL=1 python main.py --use-pytorch-cross-attention```

@@ -379,9 +306,9 @@ Only parts of the graph that change from each execution to the next will be exec

 Dragging a generated png on the webpage or loading one will give you the full workflow including seeds that were used to create it.

-You can use () to change emphasis of a word or phrase like: (good code:1.2) or (bad code:0.8). The default emphasis for () is 1.1. To use () characters in your actual prompt escape them like \\( or \\).
+You can use () to change emphasis of a word or phrase like: (good code:1.2) or (bad code:0.8). The default emphasis for () is 1.1. To use () characters in your actual prompt escape them like \( or \).

-You can use {day|night}, for wildcard/dynamic prompts. With this syntax "{wild|card|test}" will be randomly replaced by either "wild", "card" or "test" by the frontend every time you queue the prompt. To use {} characters in your actual prompt escape them like: \\{ or \\}.
+You can use {day|night}, for wildcard/dynamic prompts. With this syntax "{wild|card|test}" will be randomly replaced by either "wild", "card" or "test" by the frontend every time you queue the prompt. To use {} characters in your actual prompt escape them like: \{ or \}.

 Dynamic prompts also support C-style comments, like `// comment` or `/* comment */`.

@@ -394,7 +321,7 @@ To use a textual inversion concepts/embeddings in a text prompt put them in the

 Use ```--preview-method auto``` to enable previews.

-The default installation includes a fast latent preview method that's low-resolution. To enable higher-quality previews with [TAESD](https://github.com/madebyollin/taesd), download the [taesd_decoder.pth, taesdxl_decoder.pth, taesd3_decoder.pth and taef1_decoder.pth](https://github.com/madebyollin/taesd/) and place them in the `models/vae_approx` folder. Once they're installed, restart ComfyUI and launch it with `--preview-method taesd` to enable high-quality previews.
+The default installation includes a fast latent preview method that's low-resolution. To enable higher-quality previews with [TAESD](https://github.com/madebyollin/taesd), download the [taesd_decoder.pth, taesdxl_decoder.pth, taesd3_decoder.pth and taef1_decoder.pth](https://github.com/madebyollin/taesd/) and place them in the `models/vae_approx` folder. Once they're installed, restart Hanzo Studio and launch it with `--preview-method taesd` to enable high-quality previews.

 ## How to use TLS/SSL?
 Generate a self-signed certificate (not appropriate for shared/production use) and key by running the command: `openssl req -x509 -newkey rsa:4096 -keyout key.pem -out cert.pem -sha256 -days 3650 -nodes -subj "/C=XX/ST=StateName/L=CityName/O=CompanyName/OU=CompanySectionName/CN=CommonNameOrHostname"`
@@ -406,55 +333,6 @@ Use `--tls-keyfile key.pem --tls-certfile cert.pem` to enable TLS/SSL, the app w

 ## Support and dev channel

-[Discord](https://comfy.org/discord): Try the #help or #feedback channels.
+[Discord](https://discord.gg/hanzoai): Try the #help or #feedback channels.

-[Matrix space: #comfyui_space:matrix.org](https://app.element.io/#/room/%23comfyui_space%3Amatrix.org) (it's like discord but open source).
-
-See also: [https://www.comfy.org/](https://www.comfy.org/)
-
-## Frontend Development
-
-As of August 15, 2024, we have transitioned to a new frontend, which is now hosted in a separate repository: [ComfyUI Frontend](https://github.com/Comfy-Org/ComfyUI_frontend). This repository now hosts the compiled JS (from TS/Vue) under the `web/` directory.
-
-### Reporting Issues and Requesting Features
-
-For any bugs, issues, or feature requests related to the frontend, please use the [ComfyUI Frontend repository](https://github.com/Comfy-Org/ComfyUI_frontend). This will help us manage and address frontend-specific concerns more efficiently.
-
-### Using the Latest Frontend
-
-The new frontend is now the default for ComfyUI. However, please note:
-
-1. The frontend in the main ComfyUI repository is updated fortnightly.
-2. Daily releases are available in the separate frontend repository.
-
-To use the most up-to-date frontend version:
-
-1. For the latest daily release, launch ComfyUI with this command line argument:
-
-   ```
-   --front-end-version Comfy-Org/ComfyUI_frontend@latest
-   ```
-
-2. For a specific version, replace `latest` with the desired version number:
-
-   ```
-   --front-end-version Comfy-Org/ComfyUI_frontend@1.2.2
-   ```
-
-This approach allows you to easily switch between the stable fortnightly release and the cutting-edge daily updates, or even specific versions for testing purposes.
-
-### Accessing the Legacy Frontend
-
-If you need to use the legacy frontend for any reason, you can access it using the following command line argument:
-
-```
--front-end-version Comfy-Org/ComfyUI_legacy_frontend@latest
-```
-
-This will use a snapshot of the legacy frontend preserved in the [ComfyUI Legacy Frontend repository](https://github.com/Comfy-Org/ComfyUI_legacy_frontend).
-
-# QA
-
-### Which GPU should I buy for this?
-
-[See this page for some recommendations](https://github.com/comfyanonymous/ComfyUI/wiki/Which-GPU-should-I-buy-for-ComfyUI)
+See also: [https://www.hanzo.ai/](https://www.hanzo.ai/)
@@ -63,7 +63,7 @@ version_path_separator = os
 # are written from script.py.mako
 # output_encoding = utf-8

-sqlalchemy.url = sqlite:///user/comfyui.db
+sqlalchemy.url = sqlite:///user/hanzo_studio.db


 [post_write_hooks]
@@ -1,3 +1,3 @@
-# ComfyUI Internal Routes
+# Hanzo Studio Internal Routes

-All routes under the `/internal` path are designated for **internal use by ComfyUI only**. These routes are not intended for use by external applications may change at any time without notice.
+All routes under the `/internal` path are designated for **internal use by Hanzo Studio only**. These routes are not intended for use by external applications may change at any time without notice.
@@ -8,7 +8,7 @@ import os
 class InternalRoutes:
    '''
    The top level web router for internal routes: /internal/*
-    The endpoints here should NOT be depended upon. It is for ComfyUI frontend use only.
+    The endpoints here should NOT be depended upon. It is for Hanzo Studio frontend use only.
    Check README.md for more information.
    '''

@@ -12,7 +12,7 @@ class AppSettings():
        try:
            file = self.user_manager.get_request_user_filepath(
                request,
-                "comfy.settings.json"
+                "studio.settings.json"
            )
        except KeyError as e:
            logging.error("User settings not found.")
@@ -29,7 +29,7 @@ class AppSettings():

    def save_settings(self, request, settings):
        file = self.user_manager.get_request_user_filepath(
-            request, "comfy.settings.json")
+            request, "studio.settings.json")
        with open(file, "w") as f:
            f.write(json.dumps(settings, indent=4))

@@ -37,7 +37,7 @@ def list_tree(base_dir: str) -> list[str]:
 def prefixes_for_root(root: RootType) -> list[str]:
    if root == "models":
        bases: list[str] = []
-        for _bucket, paths in get_comfy_models_folders():
+        for _bucket, paths in get_studio_models_folders():
            bases.extend(paths)
        return [os.path.abspath(p) for p in bases]
    if root == "input":
@@ -74,16 +74,16 @@ def utcnow() -> datetime:
    """Naive UTC timestamp (no tzinfo). We always treat DB datetimes as UTC."""
    return datetime.now(timezone.utc).replace(tzinfo=None)

-def get_comfy_models_folders() -> list[tuple[str, list[str]]]:
+def get_studio_models_folders() -> list[tuple[str, list[str]]]:
    """Build a list of (folder_name, base_paths[]) categories that are configured for model locations.

    We trust `folder_paths.folder_names_and_paths` and include a category if
-    *any* of its base paths lies under the Comfy `models_dir`.
+    *any* of its base paths lies under the Studio `models_dir`.
    """
    targets: list[tuple[str, list[str]]] = []
    models_root = os.path.abspath(folder_paths.models_dir)
    for name, values in folder_paths.folder_names_and_paths.items():
-        paths, _exts = values[0], values[1]  # NOTE: this prevents nodepacks that hackily edit folder_... from breaking ComfyUI
+        paths, _exts = values[0], values[1]  # NOTE: this prevents nodepacks that hackily edit folder_... from breaking Hanzo Studio
        if any(os.path.abspath(p).startswith(models_root + os.sep) for p in paths):
            targets.append((name, paths))
    return targets
@@ -152,7 +152,7 @@ def get_relative_to_root_category_path_of_asset(file_path: str) -> tuple[Literal
    """Given an absolute or relative file path, determine which root category the path belongs to:
      - 'input' if the file resides under `folder_paths.get_input_directory()`
      - 'output' if the file resides under `folder_paths.get_output_directory()`
-      - 'models' if the file resides under any base path of categories returned by `get_comfy_models_folders()`
+      - 'models' if the file resides under any base path of categories returned by `get_studio_models_folders()`

    Returns:
        (root_category, relative_path_inside_that_root)
@@ -185,7 +185,7 @@ def get_relative_to_root_category_path_of_asset(file_path: str) -> tuple[Literal

    # 3) models (check deepest matching base to avoid ambiguity)
    best: tuple[int, str, str] | None = None  # (base_len, bucket, rel_inside_bucket)
-    for bucket, bases in get_comfy_models_folders():
+    for bucket, bases in get_studio_models_folders():
        for b in bases:
            base_abs = os.path.abspath(b)
            if not _is_within(fp_abs, base_abs):
@@ -232,7 +232,7 @@ def normalize_tags(tags: list[str] | None) -> list[str]:

 def collect_models_files() -> list[str]:
    out: list[str] = []
-    for folder_name, bases in get_comfy_models_folders():
+    for folder_name, bases in get_studio_models_folders():
        rel_files = folder_paths.get_filename_list(folder_name) or []
        for rel_path in rel_files:
            abs_path = folder_paths.get_full_path(folder_name, rel_path)
@@ -3,7 +3,7 @@ import os
 import shutil
 from app.logger import log_startup_warning
 from utils.install_util import get_missing_requirements_message
-from comfy.cli_args import args
+from studio.cli_args import args

 _DB_AVAILABLE = False
 Session = None
@@ -24,7 +24,7 @@ except ImportError as e:
 ------------------------------------------------------------------------
 Error importing dependencies: {e}
 {get_missing_requirements_message()}
-This error is happening because ComfyUI now uses a local sqlite database.
+This error is happening because Hanzo Studio now uses a local sqlite database.
 ------------------------------------------------------------------------
 """.strip()
    )
@@ -19,7 +19,7 @@ from typing_extensions import NotRequired

 from utils.install_util import get_missing_requirements_message, requirements_path

-from comfy.cli_args import DEFAULT_VERSION_STRING
+from studio.cli_args import DEFAULT_VERSION_STRING
 import app.logger


@@ -27,7 +27,7 @@ def frontend_install_warning_message():
    return f"""
 {get_missing_requirements_message()}

-This error is happening because the ComfyUI frontend is no longer shipped as part of the main repo but as a pip package instead.
+This error is happening because the Hanzo Studio frontend is no longer shipped as part of the main repo but as a pip package instead.
 """.strip()

 def parse_version(version: str) -> tuple[int, int, int]:
@@ -87,7 +87,7 @@ ________________________________________________________________________
 """.strip()
            )
        else:
-            logging.info("ComfyUI frontend version: {}".format(frontend_version_str))
+            logging.info("Hanzo Studio frontend version: {}".format(frontend_version_str))
    except Exception as e:
        logging.error(f"Failed to check frontend version: {e}")

@@ -7,7 +7,7 @@ import time
 import logging
 import folder_paths
 import glob
-import comfy.utils
+import studio.utils
 from aiohttp import web
 from PIL import Image
 from io import BytesIO
@@ -180,7 +180,7 @@ class ModelFileManager:

        if safetensors_file:
            safetensors_filepath = os.path.join(dirname, safetensors_file)
-            header = comfy.utils.safetensors_header(safetensors_filepath, max_size=8*1024*1024)
+            header = studio.utils.safetensors_header(safetensors_filepath, max_size=8*1024*1024)
            if header:
                safetensors_metadata = json.loads(header)
        safetensors_images = safetensors_metadata.get("__metadata__", {}).get("ssmd_cover_images", None)
@@ -0,0 +1,105 @@
+from __future__ import annotations
+
+from aiohttp import web
+
+from typing import TYPE_CHECKING, TypedDict
+if TYPE_CHECKING:
+    from studio_api.latest._io_public import NodeReplace
+
+from studio_execution.graph_utils import is_link
+import nodes
+
+class NodeStruct(TypedDict):
+    inputs: dict[str, str | int | float | bool | tuple[str, int]]
+    class_type: str
+    _meta: dict[str, str]
+
+def copy_node_struct(node_struct: NodeStruct, empty_inputs: bool = False) -> NodeStruct:
+    new_node_struct = node_struct.copy()
+    if empty_inputs:
+        new_node_struct["inputs"] = {}
+    else:
+        new_node_struct["inputs"] = node_struct["inputs"].copy()
+    new_node_struct["_meta"] = node_struct["_meta"].copy()
+    return new_node_struct
+
+
+class NodeReplaceManager:
+    """Manages node replacement registrations."""
+
+    def __init__(self):
+        self._replacements: dict[str, list[NodeReplace]] = {}
+
+    def register(self, node_replace: NodeReplace):
+        """Register a node replacement mapping."""
+        self._replacements.setdefault(node_replace.old_node_id, []).append(node_replace)
+
+    def get_replacement(self, old_node_id: str) -> list[NodeReplace] | None:
+        """Get replacements for an old node ID."""
+        return self._replacements.get(old_node_id)
+
+    def has_replacement(self, old_node_id: str) -> bool:
+        """Check if a replacement exists for an old node ID."""
+        return old_node_id in self._replacements
+
+    def apply_replacements(self, prompt: dict[str, NodeStruct]):
+        connections: dict[str, list[tuple[str, str, int]]] = {}
+        need_replacement: set[str] = set()
+        for node_number, node_struct in prompt.items():
+            class_type = node_struct["class_type"]
+            # need replacement if not in NODE_CLASS_MAPPINGS and has replacement
+            if class_type not in nodes.NODE_CLASS_MAPPINGS.keys() and self.has_replacement(class_type):
+                need_replacement.add(node_number)
+            # keep track of connections
+            for input_id, input_value in node_struct["inputs"].items():
+                if is_link(input_value):
+                    conn_number = input_value[0]
+                    connections.setdefault(conn_number, []).append((node_number, input_id, input_value[1]))
+        for node_number in need_replacement:
+            node_struct = prompt[node_number]
+            class_type = node_struct["class_type"]
+            replacements = self.get_replacement(class_type)
+            if replacements is None:
+                continue
+            # just use the first replacement
+            replacement = replacements[0]
+            new_node_id = replacement.new_node_id
+            # if replacement is not a valid node, skip trying to replace it as will only cause confusion
+            if new_node_id not in nodes.NODE_CLASS_MAPPINGS.keys():
+                continue
+            # first, replace node id (class_type)
+            new_node_struct = copy_node_struct(node_struct, empty_inputs=True)
+            new_node_struct["class_type"] = new_node_id
+            # TODO: consider replacing display_name in _meta as well for error reporting purposes; would need to query node schema
+            # second, replace inputs
+            if replacement.input_mapping is not None:
+                for input_map in replacement.input_mapping:
+                    if "set_value" in input_map:
+                        new_node_struct["inputs"][input_map["new_id"]] = input_map["set_value"]
+                    elif "old_id" in input_map:
+                        new_node_struct["inputs"][input_map["new_id"]] = node_struct["inputs"][input_map["old_id"]]
+            # finalize input replacement
+            prompt[node_number] = new_node_struct
+            # third, replace outputs
+            if replacement.output_mapping is not None:
+                # re-mapping outputs requires changing the input values of nodes that receive connections from this one
+                if node_number in connections:
+                    for conns in connections[node_number]:
+                        conn_node_number, conn_input_id, old_output_idx = conns
+                        for output_map in replacement.output_mapping:
+                            if output_map["old_idx"] == old_output_idx:
+                                new_output_idx = output_map["new_idx"]
+                                previous_input = prompt[conn_node_number]["inputs"][conn_input_id]
+                                previous_input[1] = new_output_idx
+
+    def as_dict(self):
+        """Serialize all replacements to dict."""
+        return {
+            k: [v.as_dict() for v in v_list]
+            for k, v_list in self._replacements.items()
+        }
+
+    def add_routes(self, routes):
+        @routes.get("/node_replacements")
+        async def get_node_replacements(request):
+            return web.json_response(self.as_dict())
@@ -53,7 +53,7 @@ class SubgraphManager:
        return entry_id, entry

    async def load_entry_data(self, entry: SubgraphEntry):
-        with open(entry['path'], 'r') as f:
+        with open(entry['path'], 'r', encoding='utf-8') as f:
            entry['data'] = f.read()
        return entry

@@ -100,7 +100,7 @@ class SubgraphManager:
        if os.path.exists(blueprints_dir):
            for file in glob.glob(os.path.join(blueprints_dir, "*.json")):
                file = file.replace('\\', '/')
-                entry_id, entry = self._create_entry(file, Source.templates, "comfyui")
+                entry_id, entry = self._create_entry(file, Source.templates, "studio")
                subgraphs_dict[entry_id] = entry

        self.cached_blueprint_subgraphs = subgraphs_dict
@@ -8,7 +8,7 @@ import shutil
 import logging
 from aiohttp import web
 from urllib import parse
-from comfy.cli_args import args
+from studio.cli_args import args
 import folder_paths
 from .app_settings import AppSettings
 from typing import TypedDict
@@ -57,8 +57,22 @@ class UserManager():

    def get_request_user_id(self, request):
        user = "default"
-        if args.multi_user and "comfy-user" in request.headers:
-            user = request.headers["comfy-user"]
+
+        # If IAM auth is active, extract user from IAM context
+        iam_user = request.get("iam_user")
+        if iam_user and iam_user.get("sub") and iam_user["sub"] != "local":
+            user = iam_user["sub"]
+            # A token subject must never escape into a System User namespace.
+            if user.startswith(folder_paths.SYSTEM_USER_PREFIX):
+                raise KeyError("Unknown user: " + user)
+            # Auto-register IAM users
+            if user not in self.users:
+                display = iam_user.get("name") or iam_user.get("email") or user
+                self.users[user] = display
+            return user
+
+        if args.multi_user and "studio-user" in request.headers:
+            user = request.headers["studio-user"]
            # Block System Users (use same error message to prevent probing)
            if user.startswith(folder_paths.SYSTEM_USER_PREFIX):
                raise KeyError("Unknown user: " + user)
@@ -68,14 +82,23 @@ class UserManager():

        return user

+    def get_request_org_id(self, request) -> str | None:
+        """Extract org_id from IAM context or fallback to CLI arg."""
+        iam_user = request.get("iam_user")
+        if iam_user and iam_user.get("org_id"):
+            return iam_user["org_id"]
+        return folder_paths.get_org_id()
+
    def get_request_user_filepath(self, request, file, type="userdata", create_dir=True):
        if type == "userdata":
-            root_dir = folder_paths.get_user_directory()
+            # Use org-scoped user directory if multi-tenant
+            org_id = self.get_request_org_id(request)
+            root_dir = folder_paths.get_org_user_directory(org_id)
        else:
            raise KeyError("Unknown filepath type:" + type)

        user = self.get_request_user_id(request)
-        user_root = folder_paths.get_public_user_directory(user)
+        user_root = folder_paths.get_public_user_directory(user, org_id)
        if user_root is None:
            return None
        path = user_root
@@ -0,0 +1,44 @@
+#version 300 es
+precision highp float;
+
+uniform sampler2D u_image0;
+uniform float u_float0; // Brightness slider -100..100
+uniform float u_float1; // Contrast slider -100..100
+
+in vec2 v_texCoord;
+out vec4 fragColor;
+
+const float MID_GRAY = 0.18;  // 18% reflectance
+
+// sRGB gamma 2.2 approximation
+vec3 srgbToLinear(vec3 c) {
+    return pow(max(c, 0.0), vec3(2.2));
+}
+
+vec3 linearToSrgb(vec3 c) {
+    return pow(max(c, 0.0), vec3(1.0/2.2));
+}
+
+float mapBrightness(float b) {
+    return clamp(b / 100.0, -1.0, 1.0);
+}
+
+float mapContrast(float c) {
+    return clamp(c / 100.0 + 1.0, 0.0, 2.0);
+}
+
+void main() {
+    vec4 orig = texture(u_image0, v_texCoord);
+
+    float brightness = mapBrightness(u_float0);
+    float contrast   = mapContrast(u_float1);
+
+    vec3 lin = srgbToLinear(orig.rgb);
+
+    lin = (lin - MID_GRAY) * contrast + brightness + MID_GRAY;
+
+    // Convert back to sRGB
+    vec3 result = linearToSrgb(clamp(lin, 0.0, 1.0));
+
+    fragColor = vec4(result, orig.a);
+}
@@ -0,0 +1,72 @@
+#version 300 es
+precision highp float;
+
+uniform sampler2D u_image0;
+uniform vec2 u_resolution;
+uniform int u_int0;      // Mode
+uniform float u_float0;  // Amount (0 to 100)
+
+in vec2 v_texCoord;
+out vec4 fragColor;
+
+const int MODE_LINEAR   = 0;
+const int MODE_RADIAL   = 1;
+const int MODE_BARREL   = 2;
+const int MODE_SWIRL    = 3;
+const int MODE_DIAGONAL = 4;
+
+const float AMOUNT_SCALE = 0.0005;
+const float RADIAL_MULT = 4.0;
+const float BARREL_MULT = 8.0;
+const float INV_SQRT2 = 0.70710678118;
+
+void main() {
+    vec2 uv = v_texCoord;
+    vec4 original = texture(u_image0, uv);
+
+    float amount = u_float0 * AMOUNT_SCALE;
+
+    if (amount < 0.000001) {
+        fragColor = original;
+        return;
+    }
+
+    // Aspect-corrected coordinates for circular effects
+    float aspect = u_resolution.x / u_resolution.y;
+    vec2 centered = uv - 0.5;
+    vec2 corrected = vec2(centered.x * aspect, centered.y);
+    float r = length(corrected);
+    vec2 dir = r > 0.0001 ? corrected / r : vec2(0.0);
+    vec2 offset = vec2(0.0);
+
+    if (u_int0 == MODE_LINEAR) {
+        // Horizontal shift (no aspect correction needed)
+        offset = vec2(amount, 0.0);
+    }
+    else if (u_int0 == MODE_RADIAL) {
+        // Outward from center, stronger at edges
+        offset = dir * r * amount * RADIAL_MULT;
+        offset.x /= aspect;  // Convert back to UV space
+    }
+    else if (u_int0 == MODE_BARREL) {
+        // Lens distortion simulation (r² falloff)
+        offset = dir * r * r * amount * BARREL_MULT;
+        offset.x /= aspect;  // Convert back to UV space
+    }
+    else if (u_int0 == MODE_SWIRL) {
+        // Perpendicular to radial (rotational aberration)
+        vec2 perp = vec2(-dir.y, dir.x);
+        offset = perp * r * amount * RADIAL_MULT;
+        offset.x /= aspect;  // Convert back to UV space
+    }
+    else if (u_int0 == MODE_DIAGONAL) {
+        // 45° offset (no aspect correction needed)
+        offset = vec2(amount, amount) * INV_SQRT2;
+    }
+    
+    float red = texture(u_image0, uv + offset).r;
+    float green = original.g;
+    float blue = texture(u_image0, uv - offset).b;
+    
+    fragColor = vec4(red, green, blue, original.a);
+}
@@ -0,0 +1,78 @@
+#version 300 es
+precision highp float;
+
+uniform sampler2D u_image0;
+uniform float u_float0; // temperature (-100 to 100)
+uniform float u_float1; // tint (-100 to 100)
+uniform float u_float2; // vibrance (-100 to 100)
+uniform float u_float3; // saturation (-100 to 100)
+
+in vec2 v_texCoord;
+out vec4 fragColor;
+
+const float INPUT_SCALE = 0.01;
+const float TEMP_TINT_PRIMARY = 0.3;
+const float TEMP_TINT_SECONDARY = 0.15;
+const float VIBRANCE_BOOST = 2.0;
+const float SATURATION_BOOST = 2.0;
+const float SKIN_PROTECTION = 0.5;
+const float EPSILON = 0.001;
+const vec3 LUMA_WEIGHTS = vec3(0.299, 0.587, 0.114);
+
+void main() {
+    vec4 tex = texture(u_image0, v_texCoord);
+    vec3 color = tex.rgb;
+    
+    // Scale inputs: -100/100 → -1/1
+    float temperature = u_float0 * INPUT_SCALE;
+    float tint = u_float1 * INPUT_SCALE;
+    float vibrance = u_float2 * INPUT_SCALE;
+    float saturation = u_float3 * INPUT_SCALE;
+    
+    // Temperature (warm/cool): positive = warm, negative = cool
+    color.r += temperature * TEMP_TINT_PRIMARY;
+    color.b -= temperature * TEMP_TINT_PRIMARY;
+    
+    // Tint (green/magenta): positive = green, negative = magenta
+    color.g += tint * TEMP_TINT_PRIMARY;
+    color.r -= tint * TEMP_TINT_SECONDARY;
+    color.b -= tint * TEMP_TINT_SECONDARY;
+    
+    // Single clamp after temperature/tint
+    color = clamp(color, 0.0, 1.0);
+    
+    // Vibrance with skin protection
+    if (vibrance != 0.0) {
+        float maxC = max(color.r, max(color.g, color.b));
+        float minC = min(color.r, min(color.g, color.b));
+        float sat = maxC - minC;
+        float gray = dot(color, LUMA_WEIGHTS);
+        
+        if (vibrance < 0.0) {
+            // Desaturate: -100 → gray
+            color = mix(vec3(gray), color, 1.0 + vibrance);
+        } else {
+            // Boost less saturated colors more
+            float vibranceAmt = vibrance * (1.0 - sat);
+            
+            // Branchless skin tone protection
+            float isWarmTone = step(color.b, color.g) * step(color.g, color.r);
+            float warmth = (color.r - color.b) / max(maxC, EPSILON);
+            float skinTone = isWarmTone * warmth * sat * (1.0 - sat);
+            vibranceAmt *= (1.0 - skinTone * SKIN_PROTECTION);
+            
+            color = mix(vec3(gray), color, 1.0 + vibranceAmt * VIBRANCE_BOOST);
+        }
+    }
+    
+    // Saturation
+    if (saturation != 0.0) {
+        float gray = dot(color, LUMA_WEIGHTS);
+        float satMix = saturation < 0.0
+            ? 1.0 + saturation                      // -100 → gray
+            : 1.0 + saturation * SATURATION_BOOST;  // +100 → 3x boost
+        color = mix(vec3(gray), color, satMix);
+    }
+    
+    fragColor = vec4(clamp(color, 0.0, 1.0), tex.a);
+}
@@ -0,0 +1,94 @@
+#version 300 es
+precision highp float;
+
+uniform sampler2D u_image0;
+uniform float u_float0;   // Blur radius (0–20, default ~5)
+uniform float u_float1;   // Edge threshold (0–100, default ~30)
+uniform int u_int0;       // Step size (0/1 = every pixel, 2+ = skip pixels)
+
+in vec2 v_texCoord;
+out vec4 fragColor;
+
+const int MAX_RADIUS = 20;
+const float EPSILON = 0.0001;
+
+// Perceptual luminance
+float getLuminance(vec3 rgb) {
+    return dot(rgb, vec3(0.299, 0.587, 0.114));
+}
+
+vec4 bilateralFilter(vec2 uv, vec2 texelSize, int radius,
+                     float sigmaSpatial, float sigmaColor)
+{
+    vec4 center = texture(u_image0, uv);
+    vec3 centerRGB = center.rgb;
+
+    float invSpatial2 = -0.5 / (sigmaSpatial * sigmaSpatial);
+    float invColor2   = -0.5 / (sigmaColor * sigmaColor + EPSILON);
+
+    vec3 sumRGB = vec3(0.0);
+    float sumWeight = 0.0;
+
+    int step = max(u_int0, 1);
+    float radius2 = float(radius * radius);
+
+    for (int dy = -MAX_RADIUS; dy <= MAX_RADIUS; dy++) {
+        if (dy < -radius || dy > radius) continue;
+        if (abs(dy) % step != 0) continue;
+
+        for (int dx = -MAX_RADIUS; dx <= MAX_RADIUS; dx++) {
+            if (dx < -radius || dx > radius) continue;
+            if (abs(dx) % step != 0) continue;
+
+            vec2 offset = vec2(float(dx), float(dy));
+            float dist2 = dot(offset, offset);
+            if (dist2 > radius2) continue;
+
+            vec3 sampleRGB = texture(u_image0, uv + offset * texelSize).rgb;
+
+            // Spatial Gaussian
+            float spatialWeight = exp(dist2 * invSpatial2);
+
+            // Perceptual color distance (weighted RGB)
+            vec3 diff = sampleRGB - centerRGB;
+            float colorDist = dot(diff * diff, vec3(0.299, 0.587, 0.114));
+            float colorWeight = exp(colorDist * invColor2);
+
+            float w = spatialWeight * colorWeight;
+            sumRGB += sampleRGB * w;
+            sumWeight += w;
+        }
+    }
+
+    vec3 resultRGB = sumRGB / max(sumWeight, EPSILON);
+    return vec4(resultRGB, center.a); // preserve center alpha
+}
+
+void main() {
+    vec2 texelSize = 1.0 / vec2(textureSize(u_image0, 0));
+
+    float radiusF = clamp(u_float0, 0.0, float(MAX_RADIUS));
+    int radius = int(radiusF + 0.5);
+
+    if (radius == 0) {
+        fragColor = texture(u_image0, v_texCoord);
+        return;
+    }
+
+    // Edge threshold → color sigma
+    // Squared curve for better low-end control
+    float t = clamp(u_float1, 0.0, 100.0) / 100.0;
+    t *= t;
+    float sigmaColor = mix(0.01, 0.5, t);
+
+    // Spatial sigma tied to radius
+    float sigmaSpatial = max(radiusF * 0.75, 0.5);
+
+    fragColor = bilateralFilter(
+        v_texCoord,
+        texelSize,
+        radius,
+        sigmaSpatial,
+        sigmaColor
+    );
+}
@@ -0,0 +1,124 @@
+#version 300 es
+precision highp float;
+
+uniform sampler2D u_image0;
+uniform vec2 u_resolution;
+uniform float u_float0; // grain amount      [0.0 – 1.0]   typical: 0.2–0.8
+uniform float u_float1; // grain size        [0.3 – 3.0]   lower = finer grain
+uniform float u_float2; // color amount      [0.0 – 1.0]   0 = monochrome, 1 = RGB grain
+uniform float u_float3; // luminance bias    [0.0 – 1.0]   0 = uniform, 1 = shadows only
+uniform int   u_int0;   // noise mode        [0 or 1]      0 = smooth, 1 = grainy
+
+in vec2 v_texCoord;
+layout(location = 0) out vec4 fragColor0;
+
+// High-quality integer hash (pcg-like)
+uint pcg(uint v) {
+    uint state = v * 747796405u + 2891336453u;
+    uint word = ((state >> ((state >> 28u) + 4u)) ^ state) * 277803737u;
+    return (word >> 22u) ^ word;
+}
+
+// 2D -> 1D hash input
+uint hash2d(uvec2 p) {
+    return pcg(p.x + pcg(p.y));
+}
+
+// Hash to float [0, 1]
+float hashf(uvec2 p) {
+    return float(hash2d(p)) / float(0xffffffffu);
+}
+
+// Hash to float with offset (for RGB channels)
+float hashf(uvec2 p, uint offset) {
+    return float(pcg(hash2d(p) + offset)) / float(0xffffffffu);
+}
+
+// Convert uniform [0,1] to roughly Gaussian distribution
+// Using simple approximation: average of multiple samples
+float toGaussian(uvec2 p) {
+    float sum = hashf(p, 0u) + hashf(p, 1u) + hashf(p, 2u) + hashf(p, 3u);
+    return (sum - 2.0) * 0.7;  // Centered, scaled
+}
+
+float toGaussian(uvec2 p, uint offset) {
+    float sum = hashf(p, offset) + hashf(p, offset + 1u) 
+              + hashf(p, offset + 2u) + hashf(p, offset + 3u);
+    return (sum - 2.0) * 0.7;
+}
+
+// Smooth noise with better interpolation
+float smoothNoise(vec2 p) {
+    vec2 i = floor(p);
+    vec2 f = fract(p);
+    
+    // Quintic interpolation (less banding than cubic)
+    f = f * f * f * (f * (f * 6.0 - 15.0) + 10.0);
+    
+    uvec2 ui = uvec2(i);
+    float a = toGaussian(ui);
+    float b = toGaussian(ui + uvec2(1u, 0u));
+    float c = toGaussian(ui + uvec2(0u, 1u));
+    float d = toGaussian(ui + uvec2(1u, 1u));
+    
+    return mix(mix(a, b, f.x), mix(c, d, f.x), f.y);
+}
+
+float smoothNoise(vec2 p, uint offset) {
+    vec2 i = floor(p);
+    vec2 f = fract(p);
+    
+    f = f * f * f * (f * (f * 6.0 - 15.0) + 10.0);
+    
+    uvec2 ui = uvec2(i);
+    float a = toGaussian(ui, offset);
+    float b = toGaussian(ui + uvec2(1u, 0u), offset);
+    float c = toGaussian(ui + uvec2(0u, 1u), offset);
+    float d = toGaussian(ui + uvec2(1u, 1u), offset);
+    
+    return mix(mix(a, b, f.x), mix(c, d, f.x), f.y);
+}
+
+void main() {
+    vec4 color = texture(u_image0, v_texCoord);
+    
+    // Luminance (Rec.709)
+    float luma = dot(color.rgb, vec3(0.2126, 0.7152, 0.0722));
+    
+    // Grain UV (resolution-independent)
+    vec2 grainUV = v_texCoord * u_resolution / max(u_float1, 0.01);
+    uvec2 grainPixel = uvec2(grainUV);
+    
+    float g;
+    vec3 grainRGB;
+    
+    if (u_int0 == 1) {
+        // Grainy mode: pure hash noise (no interpolation = no banding)
+        g = toGaussian(grainPixel);
+        grainRGB = vec3(
+            toGaussian(grainPixel, 100u),
+            toGaussian(grainPixel, 200u),
+            toGaussian(grainPixel, 300u)
+        );
+    } else {
+        // Smooth mode: interpolated with quintic curve
+        g = smoothNoise(grainUV);
+        grainRGB = vec3(
+            smoothNoise(grainUV, 100u),
+            smoothNoise(grainUV, 200u),
+            smoothNoise(grainUV, 300u)
+        );
+    }
+    
+    // Luminance weighting (less grain in highlights)
+    float lumWeight = mix(1.0, 1.0 - luma, clamp(u_float3, 0.0, 1.0));
+    
+    // Strength
+    float strength = u_float0 * 0.15;
+    
+    // Color vs monochrome grain
+    vec3 grainColor = mix(vec3(g), grainRGB, clamp(u_float2, 0.0, 1.0));
+    
+    color.rgb += grainColor * strength * lumWeight;
+    fragColor0 = vec4(clamp(color.rgb, 0.0, 1.0), color.a);
+}
@@ -0,0 +1,133 @@
+#version 300 es
+precision mediump float;
+
+uniform sampler2D u_image0;
+uniform vec2 u_resolution;
+uniform int u_int0;      // Blend mode
+uniform int u_int1;      // Color tint
+uniform float u_float0;  // Intensity
+uniform float u_float1;  // Radius
+uniform float u_float2;  // Threshold
+
+in vec2 v_texCoord;
+out vec4 fragColor;
+
+const int BLEND_ADD      = 0;
+const int BLEND_SCREEN   = 1;
+const int BLEND_SOFT     = 2;
+const int BLEND_OVERLAY  = 3;
+const int BLEND_LIGHTEN  = 4;
+
+const float GOLDEN_ANGLE = 2.39996323;
+const int MAX_SAMPLES = 48;
+const vec3 LUMA = vec3(0.299, 0.587, 0.114);
+
+float hash(vec2 p) {
+    p = fract(p * vec2(123.34, 456.21));
+    p += dot(p, p + 45.32);
+    return fract(p.x * p.y);
+}
+
+vec3 hexToRgb(int h) {
+    return vec3(
+        float((h >> 16) & 255),
+        float((h >> 8) & 255),
+        float(h & 255)
+    ) * (1.0 / 255.0);
+}
+
+vec3 blend(vec3 base, vec3 glow, int mode) {
+    if (mode == BLEND_SCREEN) {
+        return 1.0 - (1.0 - base) * (1.0 - glow);
+    }
+    if (mode == BLEND_SOFT) {
+        return mix(
+            base - (1.0 - 2.0 * glow) * base * (1.0 - base),
+            base + (2.0 * glow - 1.0) * (sqrt(base) - base),
+            step(0.5, glow)
+        );
+    }
+    if (mode == BLEND_OVERLAY) {
+        return mix(
+            2.0 * base * glow,
+            1.0 - 2.0 * (1.0 - base) * (1.0 - glow),
+            step(0.5, base)
+        );
+    }
+    if (mode == BLEND_LIGHTEN) {
+        return max(base, glow);
+    }
+    return base + glow;
+}
+
+void main() {
+    vec4 original = texture(u_image0, v_texCoord);
+    
+    float intensity = u_float0 * 0.05;
+    float radius = u_float1 * u_float1 * 0.012;
+    
+    if (intensity < 0.001 || radius < 0.1) {
+        fragColor = original;
+        return;
+    }
+    
+    float threshold = 1.0 - u_float2 * 0.01;
+    float t0 = threshold - 0.15;
+    float t1 = threshold + 0.15;
+    
+    vec2 texelSize = 1.0 / u_resolution;
+    float radius2 = radius * radius;
+    
+    float sampleScale = clamp(radius * 0.75, 0.35, 1.0);
+    int samples = int(float(MAX_SAMPLES) * sampleScale);
+    
+    float noise = hash(gl_FragCoord.xy);
+    float angleOffset = noise * GOLDEN_ANGLE;
+    float radiusJitter = 0.85 + noise * 0.3;
+    
+    float ca = cos(GOLDEN_ANGLE);
+    float sa = sin(GOLDEN_ANGLE);
+    vec2 dir = vec2(cos(angleOffset), sin(angleOffset));
+    
+    vec3 glow = vec3(0.0);
+    float totalWeight = 0.0;
+    
+    // Center tap
+    float centerMask = smoothstep(t0, t1, dot(original.rgb, LUMA));
+    glow += original.rgb * centerMask * 2.0;
+    totalWeight += 2.0;
+    
+    for (int i = 1; i < MAX_SAMPLES; i++) {
+        if (i >= samples) break;
+        
+        float fi = float(i);
+        float dist = sqrt(fi / float(samples)) * radius * radiusJitter;
+        
+        vec2 offset = dir * dist * texelSize;
+        vec3 c = texture(u_image0, v_texCoord + offset).rgb;
+        float mask = smoothstep(t0, t1, dot(c, LUMA));
+        
+        float w = 1.0 - (dist * dist) / (radius2 * 1.5);
+        w = max(w, 0.0);
+        w *= w;
+        
+        glow += c * mask * w;
+        totalWeight += w;
+        
+        dir = vec2(
+            dir.x * ca - dir.y * sa,
+            dir.x * sa + dir.y * ca
+        );
+    }
+    
+    glow *= intensity / max(totalWeight, 0.001);
+    
+    if (u_int1 > 0) {
+        glow *= hexToRgb(u_int1);
+    }
+    
+    vec3 result = blend(original.rgb, glow, u_int0);
+    result += (noise - 0.5) * (1.0 / 255.0);
+    
+    fragColor = vec4(clamp(result, 0.0, 1.0), original.a);
+}
@@ -0,0 +1,222 @@
+#version 300 es
+precision highp float;
+
+uniform sampler2D u_image0;
+uniform int u_int0;      // Mode: 0=Master, 1=Reds, 2=Yellows, 3=Greens, 4=Cyans, 5=Blues, 6=Magentas, 7=Colorize
+uniform int u_int1;      // Color Space: 0=HSL, 1=HSB/HSV
+uniform float u_float0;  // Hue (-180 to 180)
+uniform float u_float1;  // Saturation (-100 to 100)
+uniform float u_float2;  // Lightness/Brightness (-100 to 100)
+uniform float u_float3;  // Overlap (0 to 100) - feathering between adjacent color ranges
+
+in vec2 v_texCoord;
+out vec4 fragColor;
+
+// Color range modes
+const int MODE_MASTER   = 0;
+const int MODE_RED      = 1;
+const int MODE_YELLOW   = 2;
+const int MODE_GREEN    = 3;
+const int MODE_CYAN     = 4;
+const int MODE_BLUE     = 5;
+const int MODE_MAGENTA  = 6;
+const int MODE_COLORIZE = 7;
+
+// Color space modes
+const int COLORSPACE_HSL = 0;
+const int COLORSPACE_HSB = 1;
+
+const float EPSILON = 0.0001;
+
+//=============================================================================
+// RGB <-> HSL Conversions
+//=============================================================================
+
+vec3 rgb2hsl(vec3 c) {
+    float maxC = max(max(c.r, c.g), c.b);
+    float minC = min(min(c.r, c.g), c.b);
+    float delta = maxC - minC;
+
+    float h = 0.0;
+    float s = 0.0;
+    float l = (maxC + minC) * 0.5;
+
+    if (delta > EPSILON) {
+        s = l < 0.5
+            ? delta / (maxC + minC)
+            : delta / (2.0 - maxC - minC);
+
+        if (maxC == c.r) {
+            h = (c.g - c.b) / delta + (c.g < c.b ? 6.0 : 0.0);
+        } else if (maxC == c.g) {
+            h = (c.b - c.r) / delta + 2.0;
+        } else {
+            h = (c.r - c.g) / delta + 4.0;
+        }
+        h /= 6.0;
+    }
+
+    return vec3(h, s, l);
+}
+
+float hue2rgb(float p, float q, float t) {
+    t = fract(t);
+    if (t < 1.0/6.0) return p + (q - p) * 6.0 * t;
+    if (t < 0.5)       return q;
+    if (t < 2.0/3.0)   return p + (q - p) * (2.0/3.0 - t) * 6.0;
+    return p;
+}
+
+vec3 hsl2rgb(vec3 hsl) {
+    if (hsl.y < EPSILON) return vec3(hsl.z);
+
+    float q = hsl.z < 0.5
+        ? hsl.z * (1.0 + hsl.y)
+        : hsl.z + hsl.y - hsl.z * hsl.y;
+    float p = 2.0 * hsl.z - q;
+
+    return vec3(
+        hue2rgb(p, q, hsl.x + 1.0/3.0),
+        hue2rgb(p, q, hsl.x),
+        hue2rgb(p, q, hsl.x - 1.0/3.0)
+    );
+}
+
+vec3 rgb2hsb(vec3 c) {
+    float maxC = max(max(c.r, c.g), c.b);
+    float minC = min(min(c.r, c.g), c.b);
+    float delta = maxC - minC;
+
+    float h = 0.0;
+    float s = (maxC > EPSILON) ? delta / maxC : 0.0;
+    float b = maxC;
+
+    if (delta > EPSILON) {
+        if (maxC == c.r) {
+            h = (c.g - c.b) / delta + (c.g < c.b ? 6.0 : 0.0);
+        } else if (maxC == c.g) {
+            h = (c.b - c.r) / delta + 2.0;
+        } else {
+            h = (c.r - c.g) / delta + 4.0;
+        }
+        h /= 6.0;
+    }
+
+    return vec3(h, s, b);
+}
+
+vec3 hsb2rgb(vec3 hsb) {
+    vec3 rgb = clamp(abs(mod(hsb.x * 6.0 + vec3(0.0, 4.0, 2.0), 6.0) - 3.0) - 1.0, 0.0, 1.0);
+    return hsb.z * mix(vec3(1.0), rgb, hsb.y);
+}
+
+//=============================================================================
+// Color Range Weight Calculation
+//=============================================================================
+
+float hueDistance(float a, float b) {
+    float d = abs(a - b);
+    return min(d, 1.0 - d);
+}
+
+float getHueWeight(float hue, float center, float overlap) {
+    float baseWidth = 1.0 / 6.0;
+    float feather = baseWidth * overlap;
+
+    float d = hueDistance(hue, center);
+
+    float inner = baseWidth * 0.5;
+    float outer = inner + feather;
+
+    return 1.0 - smoothstep(inner, outer, d);
+}
+
+float getModeWeight(float hue, int mode, float overlap) {
+    if (mode == MODE_MASTER || mode == MODE_COLORIZE) return 1.0;
+
+    if (mode == MODE_RED) {
+        return max(
+            getHueWeight(hue, 0.0, overlap),
+            getHueWeight(hue, 1.0, overlap)
+        );
+    }
+
+    float center = float(mode - 1) / 6.0;
+    return getHueWeight(hue, center, overlap);
+}
+
+//=============================================================================
+// Adjustment Functions
+//=============================================================================
+
+float adjustLightness(float l, float amount) {
+    return amount > 0.0
+        ? l + (1.0 - l) * amount
+        : l + l * amount;
+}
+
+float adjustBrightness(float b, float amount) {
+    return clamp(b + amount, 0.0, 1.0);
+}
+
+float adjustSaturation(float s, float amount) {
+    return amount > 0.0
+        ? s + (1.0 - s) * amount
+        : s + s * amount;
+}
+
+vec3 colorize(vec3 rgb, float hue, float sat, float light) {
+    float lum = dot(rgb, vec3(0.299, 0.587, 0.114));
+    float l = adjustLightness(lum, light);
+
+    vec3 hsl = vec3(fract(hue), clamp(sat, 0.0, 1.0), clamp(l, 0.0, 1.0));
+    return hsl2rgb(hsl);
+}
+
+//=============================================================================
+// Main
+//=============================================================================
+
+void main() {
+    vec4 original = texture(u_image0, v_texCoord);
+
+    float hueShift   = u_float0 / 360.0;   // -180..180 -> -0.5..0.5
+    float satAmount  = u_float1 / 100.0;   // -100..100 -> -1..1
+    float lightAmount= u_float2 / 100.0;   // -100..100 -> -1..1
+    float overlap    = u_float3 / 100.0;   // 0..100 -> 0..1
+
+    vec3 result;
+
+    if (u_int0 == MODE_COLORIZE) {
+        result = colorize(original.rgb, hueShift, satAmount, lightAmount);
+        fragColor = vec4(result, original.a);
+        return;
+    }
+
+    vec3 hsx = (u_int1 == COLORSPACE_HSL)
+        ? rgb2hsl(original.rgb)
+        : rgb2hsb(original.rgb);
+
+    float weight = getModeWeight(hsx.x, u_int0, overlap);
+
+    if (u_int0 != MODE_MASTER && hsx.y < EPSILON) {
+        weight = 0.0;
+    }
+
+    if (weight > EPSILON) {
+        float h = fract(hsx.x + hueShift * weight);
+        float s = clamp(adjustSaturation(hsx.y, satAmount * weight), 0.0, 1.0);
+        float v = (u_int1 == COLORSPACE_HSL)
+            ? clamp(adjustLightness(hsx.z, lightAmount * weight), 0.0, 1.0)
+            : clamp(adjustBrightness(hsx.z, lightAmount * weight), 0.0, 1.0);
+
+        vec3 adjusted = vec3(h, s, v);
+        result = (u_int1 == COLORSPACE_HSL)
+            ? hsl2rgb(adjusted)
+            : hsb2rgb(adjusted);
+    } else {
+        result = original.rgb;
+    }
+
+    fragColor = vec4(result, original.a);
+}
@@ -0,0 +1,111 @@
+#version 300 es
+#pragma passes 2
+precision highp float;
+
+// Blur type constants
+const int BLUR_GAUSSIAN = 0;
+const int BLUR_BOX = 1;
+const int BLUR_RADIAL = 2;
+
+// Radial blur config
+const int RADIAL_SAMPLES = 12;
+const float RADIAL_STRENGTH = 0.0003;
+
+uniform sampler2D u_image0;
+uniform vec2 u_resolution;
+uniform int u_int0;      // Blur type (BLUR_GAUSSIAN, BLUR_BOX, BLUR_RADIAL)
+uniform float u_float0;  // Blur radius/amount
+uniform int u_pass;      // Pass index (0 = horizontal, 1 = vertical)
+
+in vec2 v_texCoord;
+layout(location = 0) out vec4 fragColor0;
+
+float gaussian(float x, float sigma) {
+    return exp(-(x * x) / (2.0 * sigma * sigma));
+}
+
+void main() {
+    vec2 texelSize = 1.0 / u_resolution;
+    float radius = max(u_float0, 0.0);
+
+    // Radial (angular) blur - single pass, doesn't use separable
+    if (u_int0 == BLUR_RADIAL) {
+        // Only execute on first pass
+        if (u_pass > 0) {
+            fragColor0 = texture(u_image0, v_texCoord);
+            return;
+        }
+
+        vec2 center = vec2(0.5);
+        vec2 dir = v_texCoord - center;
+        float dist = length(dir);
+
+        if (dist < 1e-4) {
+            fragColor0 = texture(u_image0, v_texCoord);
+            return;
+        }
+
+        vec4 sum = vec4(0.0);
+        float totalWeight = 0.0;
+        float angleStep = radius * RADIAL_STRENGTH;
+
+        dir /= dist;
+
+        float cosStep = cos(angleStep);
+        float sinStep = sin(angleStep);
+
+        float negAngle = -float(RADIAL_SAMPLES) * angleStep;
+        vec2 rotDir = vec2(
+            dir.x * cos(negAngle) - dir.y * sin(negAngle),
+            dir.x * sin(negAngle) + dir.y * cos(negAngle)
+        );
+
+        for (int i = -RADIAL_SAMPLES; i <= RADIAL_SAMPLES; i++) {
+            vec2 uv = center + rotDir * dist;
+            float w = 1.0 - abs(float(i)) / float(RADIAL_SAMPLES);
+            sum += texture(u_image0, uv) * w;
+            totalWeight += w;
+
+            rotDir = vec2(
+                rotDir.x * cosStep - rotDir.y * sinStep,
+                rotDir.x * sinStep + rotDir.y * cosStep
+            );
+        }
+
+        fragColor0 = sum / max(totalWeight, 0.001);
+        return;
+    }
+
+    // Separable Gaussian / Box blur
+    int samples = int(ceil(radius));
+
+    if (samples == 0) {
+        fragColor0 = texture(u_image0, v_texCoord);
+        return;
+    }
+
+    // Direction: pass 0 = horizontal, pass 1 = vertical
+    vec2 dir = (u_pass == 0) ? vec2(1.0, 0.0) : vec2(0.0, 1.0);
+
+    vec4 color = vec4(0.0);
+    float totalWeight = 0.0;
+    float sigma = radius / 2.0;
+
+    for (int i = -samples; i <= samples; i++) {
+        vec2 offset = dir * float(i) * texelSize;
+        vec4 sample_color = texture(u_image0, v_texCoord + offset);
+
+        float weight;
+        if (u_int0 == BLUR_GAUSSIAN) {
+            weight = gaussian(float(i), sigma);
+        } else {
+            // BLUR_BOX
+            weight = 1.0;
+        }
+
+        color += sample_color * weight;
+        totalWeight += weight;
+    }
+
+    fragColor0 = color / totalWeight;
+}
@@ -0,0 +1,19 @@
+#version 300 es
+precision highp float;
+
+uniform sampler2D u_image0;
+
+in vec2 v_texCoord;
+layout(location = 0) out vec4 fragColor0;
+layout(location = 1) out vec4 fragColor1;
+layout(location = 2) out vec4 fragColor2;
+layout(location = 3) out vec4 fragColor3;
+
+void main() {
+  vec4 color = texture(u_image0, v_texCoord);
+  // Output each channel as grayscale to separate render targets
+  fragColor0 = vec4(vec3(color.r), 1.0);  // Red channel
+  fragColor1 = vec4(vec3(color.g), 1.0);  // Green channel
+  fragColor2 = vec4(vec3(color.b), 1.0);  // Blue channel
+  fragColor3 = vec4(vec3(color.a), 1.0);  // Alpha channel
+}
@@ -0,0 +1,71 @@
+#version 300 es
+precision highp float;
+
+// Levels Adjustment
+// u_int0:   channel      (0=RGB, 1=R, 2=G, 3=B)         default: 0
+// u_float0: input black  (0-255)                        default: 0
+// u_float1: input white  (0-255)                        default: 255
+// u_float2: gamma        (0.01-9.99)                    default: 1.0
+// u_float3: output black (0-255)                        default: 0
+// u_float4: output white (0-255)                        default: 255
+
+uniform sampler2D u_image0;
+uniform int u_int0;
+uniform float u_float0;
+uniform float u_float1;
+uniform float u_float2;
+uniform float u_float3;
+uniform float u_float4;
+
+in vec2 v_texCoord;
+out vec4 fragColor;
+
+vec3 applyLevels(vec3 color, float inBlack, float inWhite, float gamma, float outBlack, float outWhite) {
+    float inRange = max(inWhite - inBlack, 0.0001);
+    vec3 result = clamp((color - inBlack) / inRange, 0.0, 1.0);
+    result = pow(result, vec3(1.0 / gamma));
+    result = mix(vec3(outBlack), vec3(outWhite), result);
+    return result;
+}
+
+float applySingleChannel(float value, float inBlack, float inWhite, float gamma, float outBlack, float outWhite) {
+    float inRange = max(inWhite - inBlack, 0.0001);
+    float result = clamp((value - inBlack) / inRange, 0.0, 1.0);
+    result = pow(result, 1.0 / gamma);
+    result = mix(outBlack, outWhite, result);
+    return result;
+}
+
+void main() {
+    vec4 texColor = texture(u_image0, v_texCoord);
+    vec3 color = texColor.rgb;
+    
+    float inBlack = u_float0 / 255.0;
+    float inWhite = u_float1 / 255.0;
+    float gamma = u_float2;
+    float outBlack = u_float3 / 255.0;
+    float outWhite = u_float4 / 255.0;
+    
+    vec3 result;
+    
+    if (u_int0 == 0) {
+        result = applyLevels(color, inBlack, inWhite, gamma, outBlack, outWhite);
+    }
+    else if (u_int0 == 1) {
+        result = color;
+        result.r = applySingleChannel(color.r, inBlack, inWhite, gamma, outBlack, outWhite);
+    }
+    else if (u_int0 == 2) {
+        result = color;
+        result.g = applySingleChannel(color.g, inBlack, inWhite, gamma, outBlack, outWhite);
+    }
+    else if (u_int0 == 3) {
+        result = color;
+        result.b = applySingleChannel(color.b, inBlack, inWhite, gamma, outBlack, outWhite);
+    }
+    else {
+        result = color;
+    }
+    
+    fragColor = vec4(result, texColor.a);
+}
@@ -0,0 +1,28 @@
+# GLSL Shader Sources
+
+This folder contains the GLSL fragment shaders extracted from blueprint JSON files for easier editing and version control.
+
+## File Naming Convention
+
+`{Blueprint_Name}_{node_id}.frag`
+
+- **Blueprint_Name**: The JSON filename with spaces/special chars replaced by underscores
+- **node_id**: The GLSLShader node ID within the subgraph
+
+## Usage
+
+```bash
+# Extract shaders from blueprint JSONs to this folder
+python update_blueprints.py extract
+
+# Patch edited shaders back into blueprint JSONs
+python update_blueprints.py patch
+```
+
+## Workflow
+
+1. Run `extract` to pull current shaders from JSONs
+2. Edit `.frag` files
+3. Run `patch` to update the blueprint JSONs
+4. Test
+5. Commit both `.frag` files and updated JSONs
@@ -0,0 +1,28 @@
+#version 300 es
+precision highp float;
+
+uniform sampler2D u_image0;
+uniform vec2 u_resolution;
+uniform float u_float0;  // strength [0.0 – 2.0] typical: 0.3–1.0
+
+in vec2 v_texCoord;
+layout(location = 0) out vec4 fragColor0;
+
+void main() {
+    vec2 texel = 1.0 / u_resolution;
+    
+    // Sample center and neighbors
+    vec4 center = texture(u_image0, v_texCoord);
+    vec4 top    = texture(u_image0, v_texCoord + vec2( 0.0, -texel.y));
+    vec4 bottom = texture(u_image0, v_texCoord + vec2( 0.0,  texel.y));
+    vec4 left   = texture(u_image0, v_texCoord + vec2(-texel.x,  0.0));
+    vec4 right  = texture(u_image0, v_texCoord + vec2( texel.x,  0.0));
+    
+    // Edge enhancement (Laplacian)
+    vec4 edges = center * 4.0 - top - bottom - left - right;
+    
+    // Add edges back scaled by strength
+    vec4 sharpened = center + edges * u_float0;
+    
+    fragColor0 = vec4(clamp(sharpened.rgb, 0.0, 1.0), center.a);
+}
@@ -0,0 +1,61 @@
+#version 300 es
+precision highp float;
+
+uniform sampler2D u_image0;
+uniform vec2 u_resolution;
+uniform float u_float0;  // amount    [0.0 - 3.0]  typical: 0.5-1.5
+uniform float u_float1;  // radius    [0.5 - 10.0] blur radius in pixels
+uniform float u_float2;  // threshold [0.0 - 0.1]  min difference to sharpen
+
+in vec2 v_texCoord;
+layout(location = 0) out vec4 fragColor0;
+
+float gaussian(float x, float sigma) {
+    return exp(-(x * x) / (2.0 * sigma * sigma));
+}
+
+float getLuminance(vec3 color) {
+    return dot(color, vec3(0.2126, 0.7152, 0.0722));
+}
+
+void main() {
+    vec2 texel = 1.0 / u_resolution;
+    float radius = max(u_float1, 0.5);
+    float amount = u_float0;
+    float threshold = u_float2;
+
+    vec4 original = texture(u_image0, v_texCoord);
+
+    // Gaussian blur for the "unsharp" mask
+    int samples = int(ceil(radius));
+    float sigma = radius / 2.0;
+
+    vec4 blurred = vec4(0.0);
+    float totalWeight = 0.0;
+
+    for (int x = -samples; x <= samples; x++) {
+        for (int y = -samples; y <= samples; y++) {
+            vec2 offset = vec2(float(x), float(y)) * texel;
+            vec4 sample_color = texture(u_image0, v_texCoord + offset);
+
+            float dist = length(vec2(float(x), float(y)));
+            float weight = gaussian(dist, sigma);
+            blurred += sample_color * weight;
+            totalWeight += weight;
+        }
+    }
+    blurred /= totalWeight;
+
+    // Unsharp mask = original - blurred
+    vec3 mask = original.rgb - blurred.rgb;
+
+    // Luminance-based threshold with smooth falloff
+    float lumaDelta = abs(getLuminance(original.rgb) - getLuminance(blurred.rgb));
+    float thresholdScale = smoothstep(0.0, threshold, lumaDelta);
+    mask *= thresholdScale;
+
+    // Sharpen: original + mask * amount
+    vec3 sharpened = original.rgb + mask * amount;
+
+    fragColor0 = vec4(clamp(sharpened, 0.0, 1.0), original.a);
+}
@@ -0,0 +1,159 @@
+#!/usr/bin/env python3
+"""
+Shader Blueprint Updater
+
+Syncs GLSL shader files between this folder and blueprint JSON files.
+
+File naming convention:
+    {Blueprint Name}_{node_id}.frag
+
+Usage:
+    python update_blueprints.py extract   # Extract shaders from JSONs to here
+    python update_blueprints.py patch     # Patch shaders back into JSONs
+    python update_blueprints.py           # Same as patch (default)
+"""
+
+import json
+import logging
+import sys
+import re
+from pathlib import Path
+
+logging.basicConfig(level=logging.INFO, format='%(message)s')
+logger = logging.getLogger(__name__)
+
+GLSL_DIR = Path(__file__).parent
+BLUEPRINTS_DIR = GLSL_DIR.parent
+
+
+def get_blueprint_files():
+    """Get all blueprint JSON files."""
+    return sorted(BLUEPRINTS_DIR.glob("*.json"))
+
+
+def sanitize_filename(name):
+    """Convert blueprint name to safe filename."""
+    return re.sub(r'[^\w\-]', '_', name)
+
+
+def extract_shaders():
+    """Extract all shaders from blueprint JSONs to this folder."""
+    extracted = 0
+    for json_path in get_blueprint_files():
+        blueprint_name = json_path.stem
+
+        try:
+            with open(json_path, 'r') as f:
+                data = json.load(f)
+        except (json.JSONDecodeError, IOError) as e:
+            logger.warning("Skipping %s: %s", json_path.name, e)
+            continue
+
+        # Find GLSLShader nodes in subgraphs
+        for subgraph in data.get('definitions', {}).get('subgraphs', []):
+            for node in subgraph.get('nodes', []):
+                if node.get('type') == 'GLSLShader':
+                    node_id = node.get('id')
+                    widgets = node.get('widgets_values', [])
+
+                    # Find shader code (first string that looks like GLSL)
+                    for widget in widgets:
+                        if isinstance(widget, str) and widget.startswith('#version'):
+                            safe_name = sanitize_filename(blueprint_name)
+                            frag_name = f"{safe_name}_{node_id}.frag"
+                            frag_path = GLSL_DIR / frag_name
+
+                            with open(frag_path, 'w') as f:
+                                f.write(widget)
+
+                            logger.info("  Extracted: %s", frag_name)
+                            extracted += 1
+                            break
+
+    logger.info("\nExtracted %d shader(s)", extracted)
+
+
+def patch_shaders():
+    """Patch shaders from this folder back into blueprint JSONs."""
+    # Build lookup: blueprint_name -> [(node_id, shader_code), ...]
+    shader_updates = {}
+
+    for frag_path in sorted(GLSL_DIR.glob("*.frag")):
+        # Parse filename: {blueprint_name}_{node_id}.frag
+        parts = frag_path.stem.rsplit('_', 1)
+        if len(parts) != 2:
+            logger.warning("Skipping %s: invalid filename format", frag_path.name)
+            continue
+
+        blueprint_name, node_id_str = parts
+
+        try:
+            node_id = int(node_id_str)
+        except ValueError:
+            logger.warning("Skipping %s: invalid node_id", frag_path.name)
+            continue
+
+        with open(frag_path, 'r') as f:
+            shader_code = f.read()
+
+        if blueprint_name not in shader_updates:
+            shader_updates[blueprint_name] = []
+        shader_updates[blueprint_name].append((node_id, shader_code))
+
+    # Apply updates to JSON files
+    patched = 0
+    for json_path in get_blueprint_files():
+        blueprint_name = sanitize_filename(json_path.stem)
+
+        if blueprint_name not in shader_updates:
+            continue
+
+        try:
+            with open(json_path, 'r') as f:
+                data = json.load(f)
+        except (json.JSONDecodeError, IOError) as e:
+            logger.error("Error reading %s: %s", json_path.name, e)
+            continue
+
+        modified = False
+        for node_id, shader_code in shader_updates[blueprint_name]:
+            # Find the node and update
+            for subgraph in data.get('definitions', {}).get('subgraphs', []):
+                for node in subgraph.get('nodes', []):
+                    if node.get('id') == node_id and node.get('type') == 'GLSLShader':
+                        widgets = node.get('widgets_values', [])
+                        if len(widgets) > 0 and widgets[0] != shader_code:
+                            widgets[0] = shader_code
+                            modified = True
+                            logger.info("  Patched: %s (node %d)", json_path.name, node_id)
+                            patched += 1
+
+        if modified:
+            with open(json_path, 'w') as f:
+                json.dump(data, f)
+
+    if patched == 0:
+        logger.info("No changes to apply.")
+    else:
+        logger.info("\nPatched %d shader(s)", patched)
+
+
+def main():
+    if len(sys.argv) < 2:
+        command = "patch"
+    else:
+        command = sys.argv[1].lower()
+
+    if command == "extract":
+        logger.info("Extracting shaders from blueprints...")
+        extract_shaders()
+    elif command in ("patch", "update", "apply"):
+        logger.info("Patching shaders into blueprints...")
+        patch_shaders()
+    else:
+        logger.info(__doc__)
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()
@@ -0,0 +1 @@
+{"revision": 0, "last_node_id": 29, "last_link_id": 0, "nodes": [{"id": 29, "type": "4c9d6ea4-b912-40e5-8766-6793a9758c53", "pos": [1970, -230], "size": [180, 86], "flags": {}, "order": 5, "mode": 0, "inputs": [{"label": "image", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": null}], "outputs": [{"label": "R", "localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": []}, {"label": "G", "localized_name": "IMAGE1", "name": "IMAGE1", "type": "IMAGE", "links": []}, {"label": "B", "localized_name": "IMAGE2", "name": "IMAGE2", "type": "IMAGE", "links": []}, {"label": "A", "localized_name": "IMAGE3", "name": "IMAGE3", "type": "IMAGE", "links": []}], "title": "Image Channels", "properties": {"proxyWidgets": []}, "widgets_values": []}], "links": [], "version": 0.4, "definitions": {"subgraphs": [{"id": "4c9d6ea4-b912-40e5-8766-6793a9758c53", "version": 1, "state": {"lastGroupId": 0, "lastNodeId": 28, "lastLinkId": 39, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Image Channels", "inputNode": {"id": -10, "bounding": [1820, -185, 120, 60]}, "outputNode": {"id": -20, "bounding": [2460, -215, 120, 120]}, "inputs": [{"id": "3522932b-2d86-4a1f-a02a-cb29f3a9d7fe", "name": "images.image0", "type": "IMAGE", "linkIds": [39], "localized_name": "images.image0", "label": "image", "pos": [1920, -165]}], "outputs": [{"id": "605cb9c3-b065-4d9b-81d2-3ec331889b2b", "name": "IMAGE0", "type": "IMAGE", "linkIds": [26], "localized_name": "IMAGE0", "label": "R", "pos": [2480, -195]}, {"id": "fb44a77e-0522-43e9-9527-82e7465b3596", "name": "IMAGE1", "type": "IMAGE", "linkIds": [27], "localized_name": "IMAGE1", "label": "G", "pos": [2480, -175]}, {"id": "81460ee6-0131-402a-874f-6bf3001fc4ff", "name": "IMAGE2", "type": "IMAGE", "linkIds": [28], "localized_name": "IMAGE2", "label": "B", "pos": [2480, -155]}, {"id": "ae690246-80d4-4951-b1d9-9306d8a77417", "name": "IMAGE3", "type": "IMAGE", "linkIds": [29], "localized_name": "IMAGE3", "label": "A", "pos": [2480, -135]}], "widgets": [], "nodes": [{"id": 23, "type": "GLSLShader", "pos": [2000, -330], "size": [400, 172], "flags": {}, "order": 0, "mode": 0, "inputs": [{"label": "image", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": 39}, {"localized_name": "fragment_shader", "name": "fragment_shader", "type": "STRING", "widget": {"name": "fragment_shader"}, "link": null}, {"localized_name": "size_mode", "name": "size_mode", "type": "COMFY_DYNAMICCOMBO_V3", "widget": {"name": "size_mode"}, "link": null}, {"label": "image1", "localized_name": "images.image1", "name": "images.image1", "shape": 7, "type": "IMAGE", "link": null}], "outputs": [{"label": "R", "localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": [26]}, {"label": "G", "localized_name": "IMAGE1", "name": "IMAGE1", "type": "IMAGE", "links": [27]}, {"label": "B", "localized_name": "IMAGE2", "name": "IMAGE2", "type": "IMAGE", "links": [28]}, {"label": "A", "localized_name": "IMAGE3", "name": "IMAGE3", "type": "IMAGE", "links": [29]}], "properties": {"Node name for S&R": "GLSLShader"}, "widgets_values": ["#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\n\nin vec2 v_texCoord;\nlayout(location = 0) out vec4 fragColor0;\nlayout(location = 1) out vec4 fragColor1;\nlayout(location = 2) out vec4 fragColor2;\nlayout(location = 3) out vec4 fragColor3;\n\nvoid main() {\n  vec4 color = texture(u_image0, v_texCoord);\n  // Output each channel as grayscale to separate render targets\n  fragColor0 = vec4(vec3(color.r), 1.0);  // Red channel\n  fragColor1 = vec4(vec3(color.g), 1.0);  // Green channel\n  fragColor2 = vec4(vec3(color.b), 1.0);  // Blue channel\n  fragColor3 = vec4(vec3(color.a), 1.0);  // Alpha channel\n}\n", "from_input"]}], "groups": [], "links": [{"id": 39, "origin_id": -10, "origin_slot": 0, "target_id": 23, "target_slot": 0, "type": "IMAGE"}, {"id": 26, "origin_id": 23, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}, {"id": 27, "origin_id": 23, "origin_slot": 1, "target_id": -20, "target_slot": 1, "type": "IMAGE"}, {"id": 28, "origin_id": 23, "origin_slot": 2, "target_id": -20, "target_slot": 2, "type": "IMAGE"}, {"id": 29, "origin_id": 23, "origin_slot": 3, "target_id": -20, "target_slot": 3, "type": "IMAGE"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Image Tools/Color adjust"}]}}
--- a/Show More
+++ b/Show More
				`@@ -0,0 +1 @@`
				{"revision": 0, "last_node_id": 29, "last_link_id": 0, "nodes": [{"id": 29, "type": "4c9d6ea4-b912-40e5-8766-6793a9758c53", "pos": [1970, -230], "size": [180, 86], "flags": {}, "order": 5, "mode": 0, "inputs": [{"label": "image", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": null}], "outputs": [{"label": "R", "localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": []}, {"label": "G", "localized_name": "IMAGE1", "name": "IMAGE1", "type": "IMAGE", "links": []}, {"label": "B", "localized_name": "IMAGE2", "name": "IMAGE2", "type": "IMAGE", "links": []}, {"label": "A", "localized_name": "IMAGE3", "name": "IMAGE3", "type": "IMAGE", "links": []}], "title": "Image Channels", "properties": {"proxyWidgets": []}, "widgets_values": []}], "links": [], "version": 0.4, "definitions": {"subgraphs": [{"id": "4c9d6ea4-b912-40e5-8766-6793a9758c53", "version": 1, "state": {"lastGroupId": 0, "lastNodeId": 28, "lastLinkId": 39, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Image Channels", "inputNode": {"id": -10, "bounding": [1820, -185, 120, 60]}, "outputNode": {"id": -20, "bounding": [2460, -215, 120, 120]}, "inputs": [{"id": "3522932b-2d86-4a1f-a02a-cb29f3a9d7fe", "name": "images.image0", "type": "IMAGE", "linkIds": [39], "localized_name": "images.image0", "label": "image", "pos": [1920, -165]}], "outputs": [{"id": "605cb9c3-b065-4d9b-81d2-3ec331889b2b", "name": "IMAGE0", "type": "IMAGE", "linkIds": [26], "localized_name": "IMAGE0", "label": "R", "pos": [2480, -195]}, {"id": "fb44a77e-0522-43e9-9527-82e7465b3596", "name": "IMAGE1", "type": "IMAGE", "linkIds": [27], "localized_name": "IMAGE1", "label": "G", "pos": [2480, -175]}, {"id": "81460ee6-0131-402a-874f-6bf3001fc4ff", "name": "IMAGE2", "type": "IMAGE", "linkIds": [28], "localized_name": "IMAGE2", "label": "B", "pos": [2480, -155]}, {"id": "ae690246-80d4-4951-b1d9-9306d8a77417", "name": "IMAGE3", "type": "IMAGE", "linkIds": [29], "localized_name": "IMAGE3", "label": "A", "pos": [2480, -135]}], "widgets": [], "nodes": [{"id": 23, "type": "GLSLShader", "pos": [2000, -330], "size": [400, 172], "flags": {}, "order": 0, "mode": 0, "inputs": [{"label": "image", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": 39}, {"localized_name": "fragment_shader", "name": "fragment_shader", "type": "STRING", "widget": {"name": "fragment_shader"}, "link": null}, {"localized_name": "size_mode", "name": "size_mode", "type": "COMFY_DYNAMICCOMBO_V3", "widget": {"name": "size_mode"}, "link": null}, {"label": "image1", "localized_name": "images.image1", "name": "images.image1", "shape": 7, "type": "IMAGE", "link": null}], "outputs": [{"label": "R", "localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": [26]}, {"label": "G", "localized_name": "IMAGE1", "name": "IMAGE1", "type": "IMAGE", "links": [27]}, {"label": "B", "localized_name": "IMAGE2", "name": "IMAGE2", "type": "IMAGE", "links": [28]}, {"label": "A", "localized_name": "IMAGE3", "name": "IMAGE3", "type": "IMAGE", "links": [29]}], "properties": {"Node name for S&R": "GLSLShader"}, "widgets_values": ["#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\n\nin vec2 v_texCoord;\nlayout(location = 0) out vec4 fragColor0;\nlayout(location = 1) out vec4 fragColor1;\nlayout(location = 2) out vec4 fragColor2;\nlayout(location = 3) out vec4 fragColor3;\n\nvoid main() {\n vec4 color = texture(u_image0, v_texCoord);\n // Output each channel as grayscale to separate render targets\n fragColor0 = vec4(vec3(color.r), 1.0); // Red channel\n fragColor1 = vec4(vec3(color.g), 1.0); // Green channel\n fragColor2 = vec4(vec3(color.b), 1.0); // Blue channel\n fragColor3 = vec4(vec3(color.a), 1.0); // Alpha channel\n}\n", "from_input"]}], "groups": [], "links": [{"id": 39, "origin_id": -10, "origin_slot": 0, "target_id": 23, "target_slot": 0, "type": "IMAGE"}, {"id": 26, "origin_id": 23, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}, {"id": 27, "origin_id": 23, "origin_slot": 1, "target_id": -20, "target_slot": 1, "type": "IMAGE"}, {"id": 28, "origin_id": 23, "origin_slot": 2, "target_id": -20, "target_slot": 2, "type": "IMAGE"}, {"id": 29, "origin_id": 23, "origin_slot": 3, "target_id": -20, "target_slot": 3, "type": "IMAGE"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Image Tools/Color adjust"}]}}