Instructions to use 1038lab/RMBG-3.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use 1038lab/RMBG-3.0 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("1038lab/RMBG-3.0", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
|
Download README.md from 1038lab/RMBG-3.0: direct link, hf CLI and curl.
- Browser
- Download file 2.64 kB
-
https://huggingface.co/1038lab/RMBG-3.0/resolve/main/README.md
- Command line
-
hf download hf://1038lab/RMBG-3.0/README.md
-
curl -L -o README.md https://huggingface.co/1038lab/RMBG-3.0/resolve/main/README.md
2.64 kB
| license: other | |
| license_name: bria-fibo | |
| license_link: https://creativecommons.org/licenses/by-nc/4.0/deed.en | |
| library_name: diffusers | |
| pipeline_tag: image-segmentation | |
| base_model: briaai/RMBG-3.0 | |
| tags: | |
| - background-removal | |
| - alpha-matting | |
| - image-matting | |
| - fibo2 | |
| - fp8 | |
| - nvfp4 | |
| - comfyui | |
| <h1 align="center">RMBG-3.0 (1038lab ComfyUI Quantized)</h1> | |
| <p align="center"><b>Quantized single-file safetensors (FP8 / NVFP4 / BF16) of Bria RMBG-3.0 for ComfyUI.</b></p> | |
| <p align="center"> | |
| <a href="https://github.com/1038lab/ComfyUI-RMBG"><img src="https://img.shields.io/badge/ComfyUI--RMBG-1038lab-blue?style=flat-square&logo=github"></a> | |
| <a href="https://huggingface.co/briaai/RMBG-3.0"><img src="https://img.shields.io/badge/Upstream-briaai%2FRMBG--3.0-yellow?style=flat-square"></a> | |
| </p> | |
| This repository hosts quantized single-file `.safetensors` weights of [**briaai/RMBG-3.0**](https://huggingface.co/briaai/RMBG-3.0) formatted for native ComfyUI (`Fibo2` / `Load Diffusion Model`). | |
| ## RMBG-3.0 vs RMBG-2.0 | |
| | Feature | RMBG-2.0 | RMBG-3.0 | | |
| | :--- | :--- | :--- | | |
| | **Architecture** | BiRefNet (single-pass segmentation) | Fibo 2.0 Edit Turbo (4-step Diffusion Transformer) | | |
| | **Output Type** | Segmentation mask | Continuous 8-bit alpha matte (true soft transparency) | | |
| | **Hard Cases** | Good on general subjects | Much stronger on fine hair/fur, glass, mesh/fences, motion blur, and cluttered backgrounds | | |
| | **VRAM / Size** | ~1 GB (fast, runs on 4 GB+ GPUs) | 4.3 GB (NVFP4) / 7.6 GB (FP8) / 15.1 GB (BF16) + Fibo2 CLIP & FLUX.2 VAE | | |
| | **License** | CC-BY-NC-4.0 | Bria FIBO / CC-BY-NC-4.0 (Non-Commercial) | | |
| ## Available Files | |
| - `RMBG-3.0-fp8.safetensors`: FP8 (`float8_e4m3fn`, 7.57 GB) — recommended for RTX 30/40/50 series. | |
| - `RMBG-3.0-nvfp4.safetensors`: NVFP4 (5.43 GB) — optimized for NVIDIA Blackwell (RTX 50 series). | |
| - `RMBG-3.0-bf16.safetensors`: Full BF16 single-file (15.14 GB) — lossless reference. | |
| ## ComfyUI Usage | |
| Place the selected `.safetensors` file into: | |
| ```text | |
| ComfyUI/models/diffusion_models/ | |
| ``` | |
| Paired with Fibo 2.0 components in ComfyUI: | |
| - **Diffusion Model**: `Load Diffusion Model` (`RMBG-3.0-fp8.safetensors` or `RMBG-3.0-nvfp4.safetensors`) | |
| - **Text Encoder**: `Load CLIP` (`qwen3vl_4b_bf16.safetensors`, Type: `fibo2`) in `ComfyUI/models/text_encoders/` | |
| - **VAE**: `Load VAE` (`flux2-vae.safetensors`) in `ComfyUI/models/vae/` | |
| ## License & Attribution | |
| - **License**: [Bria FIBO License / CC-BY-NC-4.0](https://creativecommons.org/licenses/by-nc/4.0/deed.en) (Non-Commercial use only) | |
| - **Upstream Model**: [briaai/RMBG-3.0](https://huggingface.co/briaai/RMBG-3.0) by Bria AI | |