Instructions to use SceneWorks/bernini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use SceneWorks/bernini with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("SceneWorks/bernini", 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 q4/bernini_planner.json from SceneWorks/bernini: direct link, hf CLI and curl.
- Browser
- Download file 487 Bytes
-
https://huggingface.co/SceneWorks/bernini/resolve/main/q4/bernini_planner.json
- Command line
-
hf download hf://SceneWorks/bernini/q4/bernini_planner.json
-
curl -L -o bernini_planner.json https://huggingface.co/SceneWorks/bernini/resolve/main/q4/bernini_planner.json
487 Bytes
| { | |
| "num_mask_token": 4096, | |
| "max_sequence_length": 512, | |
| "clip_diff_cfg": { | |
| "model_type": "flow_match", | |
| "z_channels": 3584, | |
| "target_channels": 3584, | |
| "width": 4096, | |
| "diffusion_batch_mul": 16, | |
| "shift": 2.0 | |
| }, | |
| "connector_cfg": { | |
| "model_type": "MLPConnector", | |
| "out_dim_for_gen": 4096, | |
| "enable_gen_branch": true, | |
| "out_dim_for_vit": 3584, | |
| "enable_vit_branch": true, | |
| "gen_head_type": "zerolinear", | |
| "zero_init_proj_gen_last": true | |
| } | |
| } |