Instructions to use Vimoo-AI/Vimoo-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Vimoo-AI/Vimoo-1.0 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Vimoo-AI/Vimoo-1.0", 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
Download inference_defaults.json from Vimoo-AI/Vimoo-1.0: direct link, hf CLI and curl.
- Browser
- Download file 543 Bytes
-
https://huggingface.co/Vimoo-AI/Vimoo-1.0/resolve/main/inference_defaults.json
- Command line
-
hf download hf://Vimoo-AI/Vimoo-1.0/inference_defaults.json
-
curl -L -o inference_defaults.json https://huggingface.co/Vimoo-AI/Vimoo-1.0/resolve/main/inference_defaults.json
543 Bytes
| { | |
| "format": "vimoo-inference-defaults-v1", | |
| "task": "t2v", | |
| "model_version": "Vimoo-1.0", | |
| "num_inference_steps": 50, | |
| "solver": "unipc", | |
| "flow_shift": 12.0, | |
| "guidance_scale": 4.5, | |
| "guidance_rescale": 1.2, | |
| "seed": 1234, | |
| "width": 1280, | |
| "height": 720, | |
| "num_frames": 121, | |
| "fps": 24, | |
| "initial_noise": { | |
| "device": "cpu", | |
| "dtype": "bfloat16", | |
| "layout": "BCFHW" | |
| }, | |
| "temporal_rope_ref_fps": 16.0, | |
| "vae_tiling": false, | |
| "block_modulation_rank": 1536, | |
| "block_modulation_precision": "bf16_expand_fp32_bias" | |
| } | |