Add new open-source model and built-in tool blueprints#13980
Merged
Conversation
comfyui-wiki
requested review from
Kosinkadink,
alexisrolland,
comfyanonymous,
guill,
kijai and
rattus128
as code owners
|
Note Reviews pausedIt looks like this branch is under active development. To avoid overwhelming you with review comments due to an influx of new commits, CodeRabbit has automatically paused this review. You can configure this behavior by changing the Use the following commands to manage reviews:
Use the checkboxes below for quick actions:
📝 WalkthroughWalkthroughThis PR adds many new ComfyUI blueprints (audio generation Stable Audio 3 base/medium with optional Qwen reprompting; Image/Video pose mapping via SDPose; Merge Videos; Split Image Grid; Select Per-Line Text; Text to Image Anima; MoGe geometry and depth estimators for image and video; Image/Video face detection via MediaPipe) and applies category metadata reclassifications to several existing blueprints. No exported code/API signatures were changed. 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://cdn.statically.io/img/avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 3
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@blueprints/Merge` Videos.json:
- Around line 362-365: The blueprint currently hardcodes EmptyAudio via
widgets_values: [60, 44100, 2] which causes AV desync; update the switch logic
so that when drop_audio is true the CreateVideo node receives either a generated
EmptyAudio whose duration is computed from the merged output (duration =
frame_count / fps, derived from the images list and fps) or, preferably, no
audio at all by routing a None/omitted value into CreateVideo.audio; modify the
ComfySwitchNode/PrimitiveBoolean branch that selects on_true to produce either a
dynamically-sized EmptyAudio (use the same frame_count and fps inputs used by
CreateVideo to compute seconds) or change the wiring so the switch returns
null/undefined for audio when drop_audio is true, ensuring
CreateVideo.execute(..., audio: Optional[Input.Audio] = None) receives no audio.
In `@blueprints/Select` Per-Line Text by Index.json:
- Around line 295-303: The "First Group" regex (currently
(?:[^\n]*\n){index}([^\n]+)) fails on empty indexed lines; update both
occurrences of the "First Group" pattern in blueprints/Select Per-Line Text by
Index.json to an anchored, empty-tolerant version by switching the capture to
allow zero-length matches and anchoring the start (e.g. replace the existing
pattern with one that begins with ^ and uses [^\n]* for the captured group) so
an empty line at the target index is correctly returned.
In `@blueprints/Text` to Image (Anima).json:
- Line 910: Fix the typo in the JSON group's title by removing the extra closing
parenthesis in the "title" value currently set to "Image Size(1MP))"; update the
string (e.g., to "Image Size (1MP)" or "Image Size(1MP)" per project style) in
the same JSON object where the "title" key appears so the group title no longer
contains the stray ')'.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
Run ID: 7bfd35ad-d43d-4448-accf-b0b5948ef5fa
📒 Files selected for processing (13)
blueprints/Audio Generation (Stable Audio 3 Medium Base).jsonblueprints/Audio Generation (Stable Audio 3 Medium).jsonblueprints/Depth to Video (ltx 2.0).jsonblueprints/Image to Depth Map (Lotus).jsonblueprints/Image to Pose Map (SDPose Multi-Person).jsonblueprints/Image to Pose Map (SDPose-OOD).jsonblueprints/Merge Videos.jsonblueprints/Select Per-Line Text by Index.jsonblueprints/Split Image Grid to Tiles.jsonblueprints/Text to Image (Anima).jsonblueprints/Video Inpaint (VOID).jsonblueprints/Video Inpainting (Wan2.1 VACE).jsonblueprints/Video to Pose Map (SDPose Multi-Person).json
alexisrolland
previously approved these changes
May 25, 2026
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@blueprints/Video` Face Detection (Mediapipe).json:
- Line 225: The "description" field in the Video Face Detection (Mediapipe)
blueprint currently says it detects landmarks "from an image" but the workflow
consumes video; update the description string to say it detects facial landmarks
from a video (e.g., "Detects facial landmarks from a video using MediaPipe,
outputting landmark data, face bounding boxes, and an optional face-region
mask.") so it accurately reflects the input modality referenced in the
blueprint's "description" property.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
Run ID: efe99e4e-35f2-49c5-9913-90498cca4842
📒 Files selected for processing (28)
blueprints/Canny to Image (Z-Image-Turbo).jsonblueprints/Canny to Video (LTX 2.0).jsonblueprints/ControlNet (Z-Image-Turbo).jsonblueprints/Depth to Image (Z-Image-Turbo).jsonblueprints/Depth to Video (ltx 2.0).jsonblueprints/First-Last-Frame to Video (LTX-2.3).jsonblueprints/First-Last-Frame to Video.jsonblueprints/Geometry Estimation (MoGe).jsonblueprints/Image Captioning (gemini).jsonblueprints/Image Depth Estimation (MoGe).jsonblueprints/Image Face Detection (Mediapipe).jsonblueprints/Image Segmentation (SAM3).jsonblueprints/Image Upscale(Z-image-Turbo).jsonblueprints/Image to Depth Map (Lotus).jsonblueprints/Image to Pose Map (SDPose Multi-Person).jsonblueprints/Image to Pose Map (SDPose-OOD).jsonblueprints/Pose to Image (Z-Image-Turbo).jsonblueprints/Pose to Video (LTX 2.0).jsonblueprints/Prompt Enhance.jsonblueprints/Remove Background (BiRefNet).jsonblueprints/Video Captioning (Gemini).jsonblueprints/Video Depth Estimation (MoGe).jsonblueprints/Video Face Detection (Mediapipe).jsonblueprints/Video Inpaint (VOID).jsonblueprints/Video Inpaint(Wan2.1 VACE).jsonblueprints/Video Segmentation (SAM3).jsonblueprints/Video Upscale(GAN x4).jsonblueprints/Video to Pose Map (SDPose Multi-Person).json
💤 Files with no reviewable changes (1)
- blueprints/Video Inpaint(Wan2.1 VACE).json
✅ Files skipped from review due to trivial changes (15)
- blueprints/Image Segmentation (SAM3).json
- blueprints/Pose to Image (Z-Image-Turbo).json
- blueprints/First-Last-Frame to Video (LTX-2.3).json
- blueprints/Canny to Video (LTX 2.0).json
- blueprints/Video Captioning (Gemini).json
- blueprints/ControlNet (Z-Image-Turbo).json
- blueprints/First-Last-Frame to Video.json
- blueprints/Canny to Image (Z-Image-Turbo).json
- blueprints/Depth to Image (Z-Image-Turbo).json
- blueprints/Pose to Video (LTX 2.0).json
- blueprints/Remove Background (BiRefNet).json
- blueprints/Image Upscale(Z-image-Turbo).json
- blueprints/Image Captioning (gemini).json
- blueprints/Image to Depth Map (Lotus).json
- blueprints/Depth to Video (ltx 2.0).json
comfyui-wiki
changed the title
alexisrolland
approved these changes
May 25, 2026
simonri
pushed a commit
to simonri/ComfyUI-flash-attention-3
that referenced
this pull request
May 26, 2026
This was referenced May 28, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
New Blueprints
Open-source model blueprints
Built-in tool
Update blueprint category