nodes/chflame163-ComfyUI_LayerStyle_Advance
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
94 Commits 1 Branch 0 Tags
d55bd6acbbc8a479c8d25d13d37b97d8276c1d63
Commit Graph
49 Commits
Author SHA1 Message Date
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
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
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
ihmily 67adbfdcae Fix mask broadcasting error for MediaPipe ≥0.10.30 2025-12-24 17:03:20 +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
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
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 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 7d599ea867 commit GeminiImageEdit,GeminiV2,ObjectDetectorGeminiV2 nodes 2025-04-04 19:50:36 +08:00
chflame163 725986d718 support numpy 2.x 2025-03-12 13:51:37 +08:00
chflame163 9252a061b1 commit DeepSeek API V2 node 2025-02-23 12:33:29 +08:00
chflame163 81412d350f commit Collage node 2025-02-13 13:41:27 +08:00
xuminglong 6d315e7dc1 add use_global_model for JoyCaption2. 
Avoid the problem of multiple nodes loading each time when the model is the same and the problem of GPU memory release.
 2025-01-23 19:57:54 +08:00
chflame163 2b53568983 fix bug of image_beauty 2025-01-15 22:48:20 +08:00
Mara Robin B. 1b8f5183c0 load sam_hq to cpu if cuda is unavailable 
fixes RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.
 2025-01-05 07:42:14 +01:00
chflame163 b0336283f7 Merge branch 'main' of https://github.com/chflame163/ComfyUI_LayerStyle_Advance 2025-01-02 12:29:23 +08:00
chflame163 4db54ed047 commit DeepSeekAPI node 2025-01-02 12:28:56 +08:00
TK 83290932c8 structured json save workflow 2024-12-31 18:55:15 +02:00
chflame163 c7034112ee requirements.txt add zhipuai 2024-12-28 20:39:05 +08:00
chflame163 b17bfc5e2d commit ZhipuGLM4,ZhipuGLM4V,SegmentAnythingUltraV3,LoadSegmentAnythingModels nodes 2024-12-28 12:10:14 +08:00
chflame163 20db9ad2a8 commit ZhipuGLM4,ZhipuGLM4V,SegmentAnythingUltraV3,LoadSegmentAnythingModels nodes 2024-12-28 10:54:13 +08:00
chflame163 1b52c5d89b support for short format hexcolor strings of imagefunc.py 2024-12-20 14:29:25 +08:00
chflame163 2aac37ab8a update imagefunc.py 2024-12-19 19:18:21 +08:00
chflame163 c63bf607f9 fix bug of function mask_area 2024-12-17 21:02:35 +08:00
chflame163 dc38ccbea8 fix ObjectDetectorGemini return empty bbox 2024-12-17 19:33:22 +08:00
chflame163 4dec7e9899 commit Gemini and ObjectDetectorGemini nodes 2024-12-17 18:43:07 +08:00
chflame163 662f10c151 commit DrawBBOXMaskV2 node 2024-12-16 17:10:14 +08:00
chflame163 6003899937 fix checkmodelpath function 2024-12-11 20:32:47 +08:00
chflame163 fcf0ee92ba fix vitmatte model loader 2024-12-11 20:18:10 +08:00
chflame163 25a6931c34 commit SmolLM2 and SmolVLM nodes 2024-12-11 16:05:42 +08:00
chflame163 a4f3112cbe Florence2 nodes support Florence-2-Flux and Florence-2-Flus-Large 2024-12-10 22:21:12 +08:00
chflame163 61660a4b55 move BenUltra and LoadBenModel to LayerStyleAdvance 2024-12-07 13:34:37 +08:00
macro chen ed796d25c6 fix ImageReward node name to Advance 2024-12-05 22:49:24 +08:00
macro chen b9757d4988 first commit 2024-12-05 17:11:26 +08:00