Instructions to use briaai/erase with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use briaai/erase 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/erase", 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: cc-by-nc-4.0 | |
| # Bria Erase (BYOC) — model weights | |
| Model weights for Bria's **Erase** object-removal / inpainting BYOC pipeline. Access is gated — request access and, once approved, download with your Hugging Face token. | |
| - `lama/model.pt` — stage 1 (LaMa coarse fill) | |
| - `vae/`, `controlnet_xl_eraser/`, `BRIA-2.3-FAST-LORA-FUSED/` — stage 2 (SDXL ControlNet) | |