nodes/chflame163-ComfyUI_LayerStyle_Advance
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
97 Commits 1 Branch 0 Tags
810e34d85933235d64aba52a20b3a2e2cf3ff10c
Commit Graph
97 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Gang WenandClaude Opus 4.6 810e34d859 Add transformers 5.x model loading path for Florence2 
Uses local Florence2 modules with accelerate-based weight loading and
a custom Florence2Processor for transformers >= 5.0.0, while keeping
the existing loading path for older versions.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-04-07 08:15:29 +02:00
Gang Wen c8b2ec0b59 fix again 2026-04-06 22:06:50 +02:00
Gang Wen e1dbbca003 added fix 2026-04-06 22:01:39 +02:00
Gang Wen d55bd6acbb Revert "Fix Florence2 config compatibility with transformers 5.x" 
This reverts commit 31ab0275de.
 2026-04-06 21:34:45 +02:00
Gang WenandClaude Opus 4.6 31ab0275de Fix Florence2 config compatibility with transformers 5.x 
In transformers 5.x, forced_bos_token_id was moved from PretrainedConfig
to GenerationConfig. Florence2's custom config accesses this attribute
during init, causing an AttributeError that prevents model loading and
leads to a NoneType crash when the processor is later called.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-04-06 21:26:57 +02:00
chflame163 2b020b7430 Merge pull request #145 from facok/patch-1 
fix BBoxJoin merging bboxes at image-index level instead of per-image
 2026-03-30 09:01:14 +08:00
facok d91c938fdd fix BBoxJoin merging bboxes at image-index level instead of per-image 
The old code used list.extend() on the outer (image-index) dimension,causing bboxes from different inputs to be treated as separate images rather than merged into the same image's bbox list.
 2026-03-30 07:42:43 +08:00
chflame163 6292ad867e Merge pull request #142 from artokun/fix/transformers5-bertwarper-compat 
Fix GroundingDINO bertwarper for transformers 5.x + PyTorch 2.9+
 2026-02-22 18:32:26 +08:00
Arthur R LongbottomandClaude Opus 4.6 2130085440 Fix GroundingDINO bertwarper for transformers 5.x + PyTorch 2.9+ 
transformers 5.x introduced two breaking changes that affect the
bundled GroundingDINO BertModelWarper:

1. `BertModel.get_head_mask()` was removed. Added a standalone
   `_get_head_mask()` fallback with a `hasattr` check so both
   transformers 4.x and 5.x work.

2. `BertModel.get_extended_attention_mask()` changed its 3rd
   positional argument from `device` to `dtype`. The old call-site
   passes a `torch.device`, which newer transformers interprets as
   `dtype=torch.device` → TypeError. Replaced with a standalone
   `_get_extended_attention_mask()` static method that also handles
   PyTorch 2.9's prohibition of `1.0 - bool_tensor` by explicitly
   casting to float32 first.

Fixes #140

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-21 10:55:47 -08:00
chflame163 f0fe35bd6d fix import issue on Transformers 5.x 2026-01-30 16:31:44 +08:00
chflame163 f16192bfa7 Ultra nodes support vitmatte-base-composition-1k 2026-01-30 14:31:25 +08:00
chflame163 c31de7030c MediapipeFacialSegment node support face_landmarker to compatible Python 3.12 and 3.13 2026-01-22 10:11:17 +08:00
chflame163 42f9dbae84 update imagefunc.py 2026-01-08 17:55:19 +08:00
chflame163 86cc56bbcf fix bug of converting BF16 tensor to pillow image 2025-12-29 15:52:17 +08:00
chflame163 dc3ffd8953 Merge pull request #134 from comfyui-wiki/Update-project-name 
Update project name
 2025-12-26 21:53:40 +08:00
chflame163 c79949d69d Merge pull request #133 from ihmily/main 
Fix mask broadcasting error for MediaPipe ≥0.10.30
 2025-12-26 21:51:28 +08:00
ComfyUI Wiki 3c3bb10847 Update project name 2025-12-26 21:42:09 +08:00
ihmily 67adbfdcae Fix mask broadcasting error for MediaPipe ≥0.10.30 2025-12-24 17:03:20 +08:00
chflame163 09a7701ef1 Merge pull request #131 from comfyui-wiki/revert-workflow-changes 
Revert workflow changes and bump version to 2.0.32
 2025-12-24 15:03:58 +08:00
ComfyUI Wiki 6a4306b7fd Bump version to 2.0.32 2025-12-24 06:57:20 +00:00
ComfyUI Wiki 1528516a21 Revert workflow changes 2025-12-24 06:56:55 +00:00
chflame163 c64b66632d Bump version to 2.0.31 2025-12-24 14:46:19 +08:00
chflame163 8d4c4285d4 Merge pull request #129 from comfyui-wiki/update-workflow 
更新自动发布工作流，只在版本变更时执行发布
 2025-12-23 22:37:21 +08:00
ComfyUI Wiki a0adff4148 Only run the workflow when the version is bumped. 2025-12-23 22:31:53 +08:00
chflame163 dc561e53c3 Merge pull request #128 from comfyui-wiki/Add-icon 
Add icon
 2025-12-23 21:41:23 +08:00
ComfyUI Wiki 07c235962e Add icon 2025-12-23 21:39:32 +08:00
chflame163 6e21d31260 Merge pull request #127 from comfyui-wiki/Bump-version-to-2.0.30 
Bump version to 2.0.30
 2025-12-23 21:32:34 +08:00
ComfyUI Wiki 6e9dbf37f2 Bump version to 2.0.30 2025-12-23 21:31:31 +08:00
chflame163 2e75c4c8cd Merge pull request #126 from comfyui-wiki/Bump-version-to-2.0.29 
Bump version to 2.0.29
 2025-12-23 21:19:52 +08:00
ComfyUI Wiki 2fb46f06b8 Bump version to 2.0.29 2025-12-23 21:19:07 +08:00
chflame163 deceda8f8a Merge pull request #125 from comfyui-wiki/feat/add-node-publish-workflow 
Add auto-publish workflow
 2025-12-23 21:17:55 +08:00
ComfyUI Wiki 7aa2777c73 Add auto-publish workflow 2025-12-23 21:14:42 +08:00
chflame163 18435772d1 fix bug of Lama node 2025-12-11 21:28:45 +08:00
chflame163 1a1928f5ae fix florence can not run with high version of TRANSFROMERS 2025-12-11 20:09:10 +08:00
chflame163 d79adcd6d2 Merge pull request #121 from jmjoy/feat 
Enhance YoloV8Detect node with additional parameters for detection
 2025-11-07 17:44:04 +08:00
jmjoy 49895abbc7 Enhance YoloV8Detect node with additional parameters for detection configuration 2025-11-07 14:44:05 +08:00
chflame163 64c8317ab3 fix import bug of deepseek.py 2025-09-10 17:27:29 +08:00
chflame163 74cd15f502 Merge pull request #107 from Semonxue/feature/update-gemini-models 
Update Gemini models and fix inline_data check
 2025-08-31 21:08:55 +08:00
Semon Xue c1e8dd7f7b Update Gemini models and fix inline_data check 2025-08-31 00:39:38 +08:00
chflame163 86db1ac8f2 add support GLM-4.5V model of ZhipuGLM4V node 2025-08-13 11:56:41 +08:00
chflame163 5f8c6f29c4 update ZhipuGLM4 node to support glm-4.5 series model 2025-08-10 18:42:24 +08:00
chflame163 d2093fe100 commit JimengI2I_API node 2025-08-09 20:50:26 +08:00
chflame163 0affa0ccac fix JoyCaptionBetaOne model CPU offload bug 2025-08-04 20:43:44 +08:00
chflame163 b5d2c94637 support JoyCaptionBetaOne model CPU offload 2025-06-28 10:35:58 +08:00
chflame163 0f9184100e commit SAM2UltraV2 and LoadSAM2Model nodes 2025-05-17 20:57:21 +08:00
chflame163 3352dada3c update readme 2025-05-16 14:51:53 +08:00
chflame163 75260b88cd add saveimageplusv2 image for readme 2025-05-15 21:40:48 +08:00
chflame163 c7cb249330 commit JoyCaption2Split, LoadJoyCaption2Model and JoyCaption2ExtraOptions nodes 2025-05-15 21:31:43 +08:00
chflame163 9ed67eb919 commit SaveImagePlusV2 node 2025-05-14 20:02:35 +08:00
chflame163 fe35b54bd2 Add multiple languages support 2025-04-09 13:34:20 +08:00