Instructions to use jpuri/multi-view-diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use jpuri/multi-view-diffusion with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("jpuri/multi-view-diffusion", 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": "MultiViewUNetModel", | |
| "_diffusers_version": "0.25.0", | |
| "attention_resolutions": [ | |
| 4, | |
| 2, | |
| 1 | |
| ], | |
| "camera_dim": 16, | |
| "channel_mult": [ | |
| 1, | |
| 2, | |
| 4, | |
| 4 | |
| ], | |
| "context_dim": 1024, | |
| "image_size": 32, | |
| "in_channels": 4, | |
| "ip_dim": 16, | |
| "model_channels": 320, | |
| "num_head_channels": 64, | |
| "num_res_blocks": 2, | |
| "out_channels": 4, | |
| "transformer_depth": 1 | |
| } | |