Instructions to use briaai/RMBG-3.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use briaai/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("briaai/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
License
Are the generated assets also considered NC (non-commercial)? Or is it just the model—meaning you do not allow inference as a service.
If you need the assets for commercial use, create them via a commercially approved API (Bria/Fal etc)
Didn't get the purpose... So open source community will/could work on those improve your model then you able to get their work and sell as commercially while they can not...
Anyway... already lost my interest. There are millions improvement new advancement in tech so no need to waste NC licensed things.
If you want the weight for commercial use: https://platform.bria.ai/licensing/pricing?model=rmbg-3.0
We train on licensed data, so we are paying back to data owners for commercial use