qwen image edit node/Mask channel input error #10016
Open
+1
−1
Conversation
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
- Implements Qwen image editing functionality with CLIP text encoding - Features intelligent scaling algorithm selection: - Uses 'area' method for downscaling to preserve details - Uses 'lanczos' method for upscaling for better quality - Supports optional VAE encoding for reference latents - Maintains aspect ratio with 'disabled' crop method - Scales images to target resolution (1024x1024 pixels) with 8-pixel alignment
- Implement automatic algorithm selection: area for downscaling, lanczos for upscaling - Improve image quality by choosing optimal scaling method based on target size - Add Chinese comments for better code documentation - Ensure 8-pixel alignment for better compatibility with diffusion models
- Fix TextEncodeQwenImageEditPlus to ensure only RGB channels are used - Prevents RuntimeError when input images have alpha channels - Ensures proper tensor shape for vision language models
AIGCZero
requested review from
Kosinkadink,
christian-byrne,
guill,
ltdrdata,
pythongosssss,
robinjhuang,
webfiltered and
yoland68
as code owners
Resolved conflict in comfy_extras/nodes_qwen.py by keeping the alpha channel fix: - Retained the fix: images_vl.append(s.movedim(1, -1)[:, :, :, :3]) - This ensures only RGB channels are used for vision processing - Fixes RuntimeError when processing images with alpha channels
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
Mask channel input error：RuntimeError: shape '[-1, 3, 2, 14, 14]' is invalid for input of size 1172864
Modify the node, only take the first 3 channels