Skip to content

Commit 3a6228f

Browse files
authored
Update README.md
1 parent fb34ec3 commit 3a6228f

File tree

1 file changed

+22
-4
lines changed

1 file changed

+22
-4
lines changed

README.md

Lines changed: 22 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -1,12 +1,16 @@
11
# ComfyUI-RMBG
22

3-
A sophisticated ComfyUI custom node engineered for advanced image background removal and precise segmentation of objects, faces, clothing, and fashion elements. This tool leverages a diverse array of models, including RMBG-2.0, INSPYRENET, BEN, BEN2, BiRefNet models, SAM, SAM2 and GroundingDINO, while also incorporating a new feature for real-time background replacement and enhanced edge detection for improved accuracy.
3+
A sophisticated ComfyUI custom node engineered for advanced image background removal and precise segmentation of objects, faces, clothing, and fashion elements. This tool leverages a diverse array of models, including RMBG-2.0, INSPYRENET, BEN, BEN2, BiRefNet, SDMatte models, SAM, SAM2 and GroundingDINO, while also incorporating a new feature for real-time background replacement and enhanced edge detection for improved accuracy.
44

55
## News & Updates
6+
- **2025/08/18**: Update ComfyUI-RMBG to **v2.9.0** ( [update.md](https://github.com/1038lab/ComfyUI-RMBG/blob/main/update.md#v290-20250818) )
7+
![v2 9 0](https://github.com/user-attachments/assets/05a5d41e-a73c-40cc-a4cc-c10380ecc425)
8+
- Added `SDMatte Matting` node
9+
610
- **2025/08/11**: Update ComfyUI-RMBG to **v2.8.0** ( [update.md](https://github.com/1038lab/ComfyUI-RMBG/blob/main/update.md#v280-20250811) )
711
![v2 8 0](https://github.com/user-attachments/assets/16c5a67c-1aec-4def-9aa2-db9dcf2354a8)
812

9-
- Added `SAM2Segment`, node for text-prompted segmentation with the latest Facebook Research SAM2 technology.
13+
- Added `SAM2Segment` node for text-prompted segmentation with the latest Facebook Research SAM2 technology.
1014
- Enhanced color widget support across all nodes
1115

1216
- **2025/08/06**: Update ComfyUI-RMBG to **v2.7.1** ( [update.md](https://github.com/1038lab/ComfyUI-RMBG/blob/main/update.md#v271-20250806) )
@@ -211,6 +215,7 @@ install requirment.txt in the ComfyUI-RMBG folder
211215
- Manually download the Clothes Segment model by visiting the [link](https://huggingface.co/1038lab/segformer_clothes), then download the files and place them in the `/ComfyUI/models/RMBG/segformer_clothes` folder.
212216
- Manually download the Fashion Segment model by visiting the [link](https://huggingface.co/1038lab/segformer_fashion), then download the files and place them in the `/ComfyUI/models/RMBG/segformer_fashion` folder.
213217
- Manually download BiRefNet models by visiting the [link](https://huggingface.co/1038lab/BiRefNet), then download the files and place them in the `/ComfyUI/models/RMBG/BiRefNet` folder.
218+
- Manually download SDMatte safetensors models by visiting the [link](https://huggingface.co/1038lab/SDMatte), then download the files and place them in the `/ComfyUI/models/RMBG/SDMatte` folder.
214219

215220
## Usage
216221
### RMBG Node
@@ -357,6 +362,20 @@ GroundingDINO is a model for text-prompted object detection and segmentation, of
357362
- omegaconf>=2.3.0
358363
- iopath>=0.1.9
359364

365+
### SDMatte models (manual download)
366+
- Auto-download on first run to `models/RMBG/SDMatte/`
367+
- If network restricted, place weights manually:
368+
- `models/RMBG/SDMatte/SDMatte.safetensors` (standard) or `SDMatte_plus.safetensors` (plus)
369+
- Components (config files) are auto-downloaded; if needed, mirror the structure from the Hugging Face repo to `models/RMBG/SDMatte/` (`scheduler/`, `text_encoder/`, `tokenizer/`, `unet/`, `vae/`)
370+
371+
## Troubleshooting (short)
372+
- 401 error when initializing GroundingDINO / missing `models/sam2`:
373+
- Delete `%USERPROFILE%\.cache\huggingface\token` (and `%USERPROFILE%\.huggingface\token` if present)
374+
- Ensure no `HF_TOKEN`/`HUGGINGFACE_TOKEN` env vars are set
375+
- Re-run; public repos download anonymously (no login required)
376+
- Preview shows "Required input is missing: images":
377+
- Ensure image outputs are connected and upstream nodes ran successfully
378+
360379
## Credits
361380
- RMBG-2.0: https://huggingface.co/briaai/RMBG-2.0
362381
- INSPYRENET: https://github.com/plemeri/InSPyReNet
@@ -366,6 +385,7 @@ GroundingDINO is a model for text-prompted object detection and segmentation, of
366385
- SAM: https://huggingface.co/facebook/sam-vit-base
367386
- GroundingDINO: https://github.com/IDEA-Research/GroundingDINO
368387
- Clothes Segment: https://huggingface.co/mattmdjaga/segformer_b2_clothes
388+
- SDMatte: https://github.com/vivoCameraResearch/SDMatte
369389

370390
- Created by: [AILab](https://github.com/1038lab)
371391

@@ -383,5 +403,3 @@ If this custom node helps you or you like my work, please give me ⭐ on this re
383403

384404
## License
385405
GPL-3.0 License
386-
387-

0 commit comments

Comments
 (0)