You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+29-12Lines changed: 29 additions & 12 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,32 +1,35 @@
1
1
# ComfyUI-RMBG
2
2
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.
4
4
5
5
## News & Updates
6
6
-**2025/08/11**: Update ComfyUI-RMBG to **v2.8.0** ( [update.md](https://github.com/1038lab/ComfyUI-RMBG/blob/main/update.md#v280-20250811) )
- 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.
10
10
- Enhanced color widget support across all nodes
11
11
12
12
-**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) )
### Method 2. Clone this repository to your ComfyUI custom_nodes folder:
170
180
```bash
@@ -196,6 +206,7 @@ install requirment.txt in the ComfyUI-RMBG folder
196
206
- 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.
197
207
- 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.
198
208
- 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.
199
210
- 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.
200
211
- 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.
201
212
- 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:
302
313
- Output with background
303
314
- Batch output for video
304
315
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
+
305
322
## GroundingDINO
306
323
GroundingDINO is a model for text-prompted object detection and segmentation, offering:
307
324
- High accuracy in complex environments
@@ -328,15 +345,17 @@ GroundingDINO is a model for text-prompted object detection and segmentation, of
0 commit comments