Instructions to use OpenDriveLab/SparseVideoNav_VGM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use OpenDriveLab/SparseVideoNav_VGM with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("OpenDriveLab/SparseVideoNav_VGM", 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": "SVNModel", | |
| "_diffusers_version": "0.35.1", | |
| "vgm_dim": 1536, | |
| "vgm_ffn_dim": 8960, | |
| "vgm_num_heads": 12, | |
| "vgm_num_layers": 30, | |
| "vgm_qformer_config": { | |
| "depth": 4, | |
| "dim": 512, | |
| "heads": 8, | |
| "language_dim": 4096, | |
| "num_latents": 10240, | |
| "video_feature_dim": 16 | |
| }, | |
| "vgm_video_former_config": { | |
| "depth": 6, | |
| "dim": 512, | |
| "heads": 8, | |
| "language_dim": 4096, | |
| "num_frame": 10, | |
| "num_latents": 2560, | |
| "video_feature_dim": 512 | |
| } | |
| } |