Skip to content

Commit b45f87a

Browse files
authored
Update README.md
1 parent 4819c7c commit b45f87a

File tree

1 file changed

+29
-12
lines changed

1 file changed

+29
-12
lines changed

README.md

Lines changed: 29 additions & 12 deletions
Original file line numberDiff line numberDiff line change
@@ -1,32 +1,35 @@
11
# ComfyUI-RMBG
22

3-
A ComfyUI custom node designed for advanced image background removal and object, face, clothes, and fashion segmentation, utilizing multiple models including RMBG-2.0, INSPYRENET, BEN, BEN2, BiRefNet-HR, SAM, and GroundingDINO.
3+
A ComfyUI custom node designed for advanced image background removal and object, face, clothes, and fashion segmentation, utilizing multiple models including RMBG-2.0, INSPYRENET, BEN, BEN2, BiRefNet-HR, SAM, SAM2 and GroundingDINO.
44

55
## News & Updates
66
- **2025/08/11**: Update ComfyUI-RMBG to **v2.8.0** ( [update.md](https://github.com/1038lab/ComfyUI-RMBG/blob/main/update.md#v280-20250811) )
77
![v2 8 0](https://github.com/user-attachments/assets/16c5a67c-1aec-4def-9aa2-db9dcf2354a8)
88

9-
- Added `SAM2Segment` node for text-prompted segmentation with the latest Facebook Research SAM2 technology.
9+
- Added `SAM2Segment`, `SAM2SegmentDiscovery`, and `SAM2SegmentDiscoveryAdv` nodes for text-prompted segmentation with the latest Facebook Research SAM2 technology.
1010
- Enhanced color widget support across all nodes
1111

1212
- **2025/08/06**: Update ComfyUI-RMBG to **v2.7.1** ( [update.md](https://github.com/1038lab/ComfyUI-RMBG/blob/main/update.md#v271-20250806) )
13-
- **2025/07/27**: Update ComfyUI-RMBG to **v2.7.0** ( [update.md](https://github.com/1038lab/ComfyUI-RMBG/blob/main/update.md#v270-20250727) )
1413
![v2.7.0_ImageStitch](https://github.com/user-attachments/assets/3f31fe25-a453-4f86-bf3d-dc12a8affd39)
1514

1615
- Enhanced LoadImage into three distinct nodes to meet different needs, all supporting direct image loading from local paths or URLs
1716
- Completely redesigned ImageStitch node compatible with ComfyUI's native functionality
1817
- Fixed background color handling issues reported by users
1918

2019
- **2025/07/15**: Update ComfyUI-RMBG to **v2.6.0** ( [update.md](https://github.com/1038lab/ComfyUI-RMBG/blob/main/update.md#v260-20250715) )
20+
2121
![ReferenceLatentMaskr](https://github.com/user-attachments/assets/756641b7-0833-4fe0-b32f-2b848a14574e)
2222

2323
- Added `Kontext Refence latent Mask` node, Which uses a reference latent and mask for precise region conditioning.
2424

2525
- **2025/07/11**: Update ComfyUI-RMBG to **v2.5.2** ( [update.md](https://github.com/1038lab/ComfyUI-RMBG/blob/main/update.md#v252-20250711) )
26+
2627
![V 2 5 2](https://github.com/user-attachments/assets/4b41887a-0d8a-4a5a-9128-1e866f410b60)
2728

2829
- **2025/07/07**: Update ComfyUI-RMBG to **v2.5.1** ( [update.md](https://github.com/1038lab/ComfyUI-RMBG/blob/main/update.md#v251-20250707) )
30+
2931
- **2025/07/01**: Update ComfyUI-RMBG to **v2.5.0** ( [update.md](https://github.com/1038lab/ComfyUI-RMBG/blob/main/update.md#v250-20250701) )
32+
3033
![mask_overlay](https://github.com/user-attachments/assets/d82abb5a-9702-4d21-a5cf-e6776c7b4c06)
3134

3235
- Added `MaskOverlay`, `ObjectRemover`, `ImageMaskResize` new nodes.
@@ -156,6 +159,10 @@ https://github.com/user-attachments/assets/7faa00d3-bbe2-42b8-95ed-2c830a1ff04f
156159
- High-precision segmentation with SAM
157160
- Flexible parameter controls
158161

162+
- SAM2 Segmentation
163+
- Text-prompted segmentation with the latest SAM2 models (Tiny/Small/Base+/Large)
164+
- Automatic model download on first use, with manual download option
165+
159166
![RMBG Demo](https://github.com/user-attachments/assets/f3ffa3c4-5a21-4c0c-a078-b4ffe681c4c4)
160167

161168
## Installation
@@ -165,6 +172,9 @@ install requirment.txt in the ComfyUI-RMBG folder
165172
```bash
166173
./ComfyUI/python_embeded/python -m pip install -r requirements.txt
167174
```
175+
> [!TIP]
176+
> Note: If your environment cannot install dependencies with the system Python, you can use ComfyUI's embedded Python instead.
177+
> Example (embedded Python): `./ComfyUI/python_embeded/python.exe -m pip install --no-user --no-cache-dir -r requirements.txt`
168178
169179
### Method 2. Clone this repository to your ComfyUI custom_nodes folder:
170180
```bash
@@ -196,6 +206,7 @@ install requirment.txt in the ComfyUI-RMBG folder
196206
- Manually download the BEN2 model by visiting the [link](https://huggingface.co/1038lab/BEN2), then download the files and place them in the `/ComfyUI/models/RMBG/BEN2` folder.
197207
- Manually download the BiRefNet-HR by visiting the [link](https://huggingface.co/1038lab/BiRefNet_HR), then download the files and place them in the `/ComfyUI/models/RMBG/BiRefNet-HR` folder.
198208
- Manually download the SAM models by visiting the [link](https://huggingface.co/1038lab/sam), then download the files and place them in the `/ComfyUI/models/SAM` folder.
209+
- Manually download the SAM2 models by visiting the [link](https://huggingface.co/1038lab/sam2), then download the files (e.g., `sam2.1_hiera_tiny.safetensors`, `sam2.1_hiera_small.safetensors`, `sam2.1_hiera_base_plus.safetensors`, `sam2.1_hiera_large.safetensors`) and place them in the `/ComfyUI/models/sam2` folder.
199210
- Manually download the GroundingDINO models by visiting the [link](https://huggingface.co/1038lab/GroundingDINO), then download the files and place them in the `/ComfyUI/models/grounding-dino` folder.
200211
- 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.
201212
- 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.
@@ -302,6 +313,12 @@ SAM is a powerful model for object detection and segmentation, offering:
302313
- Output with background
303314
- Batch output for video
304315

316+
## SAM2
317+
SAM2 is the latest segmentation model family designed for efficient, high-quality text-prompted segmentation:
318+
- Multiple sizes: Tiny, Small, Base+, Large
319+
- Optimized inference with strong accuracy
320+
- Automatic download on first use; manual placement supported in `ComfyUI/models/sam2`
321+
305322
## GroundingDINO
306323
GroundingDINO is a model for text-prompted object detection and segmentation, offering:
307324
- High accuracy in complex environments
@@ -328,15 +345,17 @@ GroundingDINO is a model for text-prompted object detection and segmentation, of
328345
- ComfyUI
329346
- Python 3.10+
330347
- Required packages (automatically installed):
331-
- torch>=2.0.0
332-
- torchvision>=0.15.0
333-
- Pillow>=9.0.0
334-
- numpy>=1.22.0
335348
- huggingface-hub>=0.19.0
336-
- tqdm>=4.65.0
337-
- transformers>=4.35.0
338-
- transparent-background>=1.2.4
349+
- transparent-background>=1.1.2
350+
- segment-anything>=1.0
351+
- groundingdino-py>=0.4.0
339352
- opencv-python>=4.7.0
353+
- onnxruntime>=1.15.0
354+
- onnxruntime-gpu>=1.15.0
355+
- protobuf>=3.20.2,<6.0.0
356+
- hydra-core>=1.3.0
357+
- omegaconf>=2.3.0
358+
- iopath>=0.1.9
340359

341360
## Credits
342361
- RMBG-2.0: https://huggingface.co/briaai/RMBG-2.0
@@ -364,5 +383,3 @@ If this custom node helps you or you like my work, please give me ⭐ on this re
364383

365384
## License
366385
GPL-3.0 License
367-
368-

0 commit comments

Comments
 (0)