Add description field to blueprint subgraphs#13797
Merged
comfyui-wiki merged 11 commits intoComfy-Org:masterfrom May 9, 2026
Merged
Add description field to blueprint subgraphs#13797comfyui-wiki merged 11 commits intoComfy-Org:masterfrom
comfyui-wiki merged 11 commits intoComfy-Org:masterfrom
Conversation
added 8 commits
May 9, 2026 10:40
Sets the 'description' field on every subgraph blueprint node, which will show on the node preview and tooltip. Covers all 51 blueprint files under blueprints/.
Updates subgraph descriptions across all 51 blueprints with accurate model details drawn from ComfyUI docs, including: - Flux.1 Dev: 12B open-weights, Pro-level quality - Flux.2 Klein 4B: fastest Flux, distilled architecture - Qwen-Image: 20B MMDiT, multilingual text rendering - Z-Image-Turbo: distilled 6B DiT, sub-second inference - LTX-2/2.3: 19B DiT audio-video foundation model - Wan2.2: open-source, 14B/1.3B variants - ACE-Step 1.5: ~1s full-song generation - GPU shader nodes consistently labeled as fragment shaders
- Rename 'Image to Model (Hunyuan3d 2.1)' -> 'Image to 3D Model (Hunyuan3d 2.1)' - Rename 'Image Upscale(Z-image-Turbo)' -> 'Image Upscale (Z-image-Turbo)' - Rename 'Video Inpaint(Wan2.1 VACE)' -> 'Video Inpaint (Wan 2.1 VACE)' - Use 'Black Forest Labs' branding in Flux descriptions - Use 'Google's Gemini' with possessive in captioning nodes - Normalize 'Wan 2.2' and 'Wan 2.1' spacing in descriptions
lin-bot23
force-pushed
the
blueprints/subgraph-description
branch
from
9a80067 to
563ac16
Compare
lin-bot23
commented
May 9, 2026
Contributor
Author
lin-bot23
left a comment
lin-bot23
left a comment
There was a problem hiding this comment.
Thanks for the review, @alexisrolland! 🙏
I've applied all 10 suggestions:
Name changes:
Image to Model (Hunyuan3d 2.1)→Image to 3D Model (Hunyuan3d 2.1)Image Upscale(Z-image-Turbo)→Image Upscale (Z-image-Turbo)Video Inpaint(Wan2.1 VACE)→Video Inpaint (Wan 2.1 VACE)
Description updates:
- Use
Black Forest Labs'branding for Flux models - Use
Google's Geminipossessive form for captioning nodes - Normalize spacing in
Wan 2.1/Wan 2.2 - Various wording refinements
Also cleaned up the branch — all 51 files are now strictly under blueprints/ with zero unrelated changes. Ready for another look when you have a moment!
…ntent Only adds the 'description' field without modifying the shader code (which contained Unicode escape \\u2192 that should be preserved).
comfyui-wiki
requested review from
Kosinkadink,
comfyanonymous,
guill,
kijai and
rattus128
as code owners
|
ℹ️ Recent review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (4)
✅ Files skipped from review due to trivial changes (3)
🚧 Files skipped from review as they are similar to previous changes (1)
📝 WalkthroughWalkthroughThis pull request standardizes and enriches metadata across 56 blueprint JSON files. The changes introduce two complementary updates: first, removing "local-" prefixes from 11 blueprint display names to normalize naming conventions; second, adding human-readable 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. Tip 💬 Introducing Slack Agent: The best way for teams to turn conversations into code.Slack Agent is built on CodeRabbit's deep understanding of your code, so your team can collaborate across the entire SDLC without losing context.
Built for teams:
One agent for your entire SDLC. Right inside Slack. 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://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 4
🧹 Nitpick comments (1)
blueprints/Image to Model (Hunyuan3d 2.1).json (1)
75-75: ⚡ Quick winInconsistent capitalization of "Hunyuan3d" in name vs description.
Line 75 uses
"Hunyuan3d 2.1"while Line 769 uses"Hunyuan3D 2.0/2.1". The HuggingFace repository URL (Line 598) useshunyuan3D_2.1_repackaged, suggesting capital D is the official branding. Consider standardizing to"Hunyuan3D"in both places for consistency.✨ Proposed fix for consistent branding
- "name": "Image to 3D Model (Hunyuan3d 2.1)", + "name": "Image to 3D Model (Hunyuan3D 2.1)",Also applies to: 769-769
🤖 Prompt for 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. In `@blueprints/Image` to Model (Hunyuan3d 2.1).json at line 75, The blueprint uses inconsistent capitalization for the model brand: update the "name" field value "Image to 3D Model (Hunyuan3d 2.1)" to use the official casing "Hunyuan3D 2.1" and search/replace other occurrences (e.g., the description entry currently mentioning "Hunyuan3D 2.0/2.1" and the HuggingFace reference "hunyuan3D_2.1_repackaged") so all instances match the canonical "Hunyuan3D" branding; ensure you only change string literals and keep version numbers intact (e.g., "2.1") in properties like "name" and description fields.
🤖 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/Color` Adjustment.json:
- Around line 599-600: Update the "description" string for the Color Adjustment
blueprint (the object with "category": "Image Tools/Color adjust") to mention
vibrance alongside saturation, temperature, and tint so the tooltip matches the
UI; specifically reference the vibrance parameter exposed in node 6 and the
shader uniform u_float2 and add a short phrase like "and vibrance" to the
existing description.
In `@blueprints/Image` Blur.json:
- Line 378: The Image Blur blueprint's "description" property currently mentions
only Gaussian blur; update the description string in the Image Blur JSON so it
reflects all supported modes (Gaussian, Box, and Radial), e.g., broaden to
something like "Applies Gaussian, Box, or Radial blur to soften an image or
simulate depth-of-field effects" to ensure preview/tooltip text accurately
represents the blueprint's capabilities.
In `@blueprints/Image` Edit (Flux.2 Klein 4B).json:
- Line 1476: The description string for the "Image Edit (Flux.2 Klein 4B)"
blueprint overstates capability; update the "description" value (the JSON key
named "description" in this blueprint) to clearly state that this subgraph is an
image-editing flow (not a full T2I + editing combo), e.g., narrow wording to
indicate it supports image edits via text instructions using FLUX.2 [klein] 4B
rather than both T2I and image generation. Locate the "description" property in
the blueprint JSON and replace the current sentence with a concise edit-only
formulation.
In `@blueprints/Text` to Image (NetaYume Lumina).json:
- Around line 1107-1108: Update the "description" field for the NetaYume Lumina
blueprint to correctly reference its upstream model: change the phrase "a
Lumina-Next variant" to a line clarifying it is a Neta Lumina fine-tune built on
Lumina-Image-2.0 (Lumina2) or simply "based on Lumina-Image-2.0"; edit the JSON
entry where "description" is set for "NetaYume Lumina" to use that corrected
wording so references to model lineage are accurate.
---
Nitpick comments:
In `@blueprints/Image` to Model (Hunyuan3d 2.1).json:
- Line 75: The blueprint uses inconsistent capitalization for the model brand:
update the "name" field value "Image to 3D Model (Hunyuan3d 2.1)" to use the
official casing "Hunyuan3D 2.1" and search/replace other occurrences (e.g., the
description entry currently mentioning "Hunyuan3D 2.0/2.1" and the HuggingFace
reference "hunyuan3D_2.1_repackaged") so all instances match the canonical
"Hunyuan3D" branding; ensure you only change string literals and keep version
numbers intact (e.g., "2.1") in properties like "name" and description fields.
🪄 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: b206db5c-89fa-4418-b8e2-f1f1d142e65d
📒 Files selected for processing (51)
blueprints/Brightness and Contrast.jsonblueprints/Canny to Image (Z-Image-Turbo).jsonblueprints/Canny to Video (LTX 2.0).jsonblueprints/Chromatic Aberration.jsonblueprints/Color Adjustment.jsonblueprints/Color Balance.jsonblueprints/Color Curves.jsonblueprints/Crop Images 2x2.jsonblueprints/Crop Images 3x3.jsonblueprints/Depth to Image (Z-Image-Turbo).jsonblueprints/Depth to Video (ltx 2.0).jsonblueprints/Edge-Preserving Blur.jsonblueprints/Film Grain.jsonblueprints/First-Last-Frame to Video (LTX-2.3).jsonblueprints/Glow.jsonblueprints/Hue and Saturation.jsonblueprints/Image Blur.jsonblueprints/Image Captioning (gemini).jsonblueprints/Image Channels.jsonblueprints/Image Edit (FireRed Image Edit 1.1).jsonblueprints/Image Edit (Flux.2 Klein 4B).jsonblueprints/Image Edit (LongCat Image Edit).jsonblueprints/Image Edit (Qwen 2511).jsonblueprints/Image Inpainting (Flux.1 Fill Dev).jsonblueprints/Image Inpainting (Qwen-image).jsonblueprints/Image Levels.jsonblueprints/Image Outpainting (Qwen-Image).jsonblueprints/Image Upscale(Z-image-Turbo).jsonblueprints/Image to Depth Map (Lotus).jsonblueprints/Image to Layers(Qwen-Image-Layered).jsonblueprints/Image to Model (Hunyuan3d 2.1).jsonblueprints/Image to Video (LTX-2.3).jsonblueprints/Image to Video (Wan 2.2).jsonblueprints/Pose to Image (Z-Image-Turbo).jsonblueprints/Pose to Video (LTX 2.0).jsonblueprints/Prompt Enhance.jsonblueprints/Sharpen.jsonblueprints/Text to Audio (ACE-Step 1.5).jsonblueprints/Text to Image (Flux.1 Dev).jsonblueprints/Text to Image (Flux.1 Krea Dev).jsonblueprints/Text to Image (NetaYume Lumina).jsonblueprints/Text to Image (Qwen-Image 2512).jsonblueprints/Text to Image (Qwen-Image).jsonblueprints/Text to Image (Z-Image-Turbo).jsonblueprints/Text to Video (LTX-2.3).jsonblueprints/Text to Video (Wan 2.2).jsonblueprints/Unsharp Mask.jsonblueprints/Video Captioning (Gemini).jsonblueprints/Video Inpaint(Wan2.1 VACE).jsonblueprints/Video Stitch.jsonblueprints/Video Upscale(GAN x4).json
alexisrolland
previously approved these changes
May 9, 2026
- Color Adjustment: include vibrance in description - Image Blur: expand to Gaussian/Box/Radial modes - Flux.2 Klein 4B: narrow to image edit only (no T2I) - NetaYume Lumina: correct model base (Neta Lumina, not Lumina-Next)
lin-bot23
force-pushed
the
blueprints/subgraph-description
branch
from
d0f03de to
22fcf61
Compare
alexisrolland
approved these changes
May 9, 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
3 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.
Sets the
descriptionfield on every subgraph blueprint node, which will show on the node preview and tooltip.Covers all 51 blueprint files under
blueprints/.