GGUF models for BiRefNet
RMBG-2.0 is a model for dichotomous image segmentation (background removal). The weights in this repository are converted for lightweight inference on consumer hardware with vision.cpp.
- Original weights: briaai/RMBG-2.0 (HuggingFace)
Run
Example inference with vision.cpp:
CLI
vision-cli birefnet -m RMBG-2.0-F16.gguf -i input.png -o mask.png --composite comp.png
Distribution of images:
| Category | Distribution |
|---|---|
| Objects only | 45.11% |
| People with objects/animals | 25.24% |
| People only | 17.35% |
| people/objects/animals with text | 8.52% |
| Text only | 2.52% |
| Animals only | 1.89% |
| Category | Distribution |
|---|---|
| Photorealistic | 87.70% |
| Non-Photorealistic | 12.30% |
| Category | Distribution |
|---|---|
| Non Solid Background | 52.05% |
| Solid Background | 47.95% |
| Category | Distribution |
|---|---|
| Single main foreground object | 51.42% |
| Multiple objects in the foreground | 48.58% |
Architecture
RMBG-2.0 is developed on the BiRefNet architecture enhanced with our proprietary dataset and training scheme. This training data significantly improves the model’s accuracy and effectiveness for background-removal task.
- Downloads last month
- 92
Hardware compatibility
Log In to add your hardware
16-bit
32-bit
Model tree for gobeldan/RMBG-2.0-GGUF
Base model
briaai/RMBG-2.0