Instructions to use dn6/RFDiffusion-3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use dn6/RFDiffusion-3 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("dn6/RFDiffusion-3", 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
| { | |
| "_class_name": "RFDiffusionTransformerModel", | |
| "_diffusers_version": "0.37.0.dev0", | |
| "auto_map": { | |
| "AutoModel": "model_rfdiffusion.RFDiffusionTransformerModel" | |
| }, | |
| "c_s": 384, | |
| "c_z": 128, | |
| "c_atom": 128, | |
| "c_atompair": 16, | |
| "c_token": 768, | |
| "c_t_embed": 256, | |
| "sigma_data": 16.0, | |
| "n_pairformer_block": 2, | |
| "n_diffusion_block": 18, | |
| "n_atom_encoder_block": 3, | |
| "n_atom_decoder_block": 3, | |
| "n_head": 16, | |
| "n_pairformer_head": 16, | |
| "n_recycle": 2, | |
| "p_drop": 0.0 | |
| } | |