Instructions to use ZeyuLing/vermo_vqvae_smpl_4375 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ZeyuLing/vermo_vqvae_smpl_4375 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ZeyuLing/vermo_vqvae_smpl_4375", 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": "VQVAEWanMotion2DTK", | |
| "_diffusers_version": "0.35.2", | |
| "attn_scales": [], | |
| "base_dim": 96, | |
| "decoder_base_dim": null, | |
| "dim_mult": [ | |
| 1, | |
| 2, | |
| 4, | |
| 4 | |
| ], | |
| "dropout": 0.0, | |
| "in_channels": 6, | |
| "is_residual": false, | |
| "num_res_blocks": 2, | |
| "out_channels": 6, | |
| "quantizer_cfg": { | |
| "dim": 16, | |
| "levels": [ | |
| 7, | |
| 5, | |
| 5, | |
| 5, | |
| 5 | |
| ], | |
| "type": "FSQuantizer" | |
| }, | |
| "scale_factor_temporal": 4, | |
| "temporal_downsample": [ | |
| false, | |
| true, | |
| true | |
| ], | |
| "z_dim": 16 | |
| } | |