Instructions to use Yang-Tian/StereoWorld with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Yang-Tian/StereoWorld with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Yang-Tian/StereoWorld", 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 StereoWorldInpaintModel/vae/config.json from Yang-Tian/StereoWorld: direct link, hf CLI and curl.
- Browser
- Download file 317 Bytes
-
https://huggingface.co/Yang-Tian/StereoWorld/resolve/main/StereoWorldInpaintModel/vae/config.json
- Command line
-
hf download hf://Yang-Tian/StereoWorld/StereoWorldInpaintModel/vae/config.json
-
curl -L -o config.json https://huggingface.co/Yang-Tian/StereoWorld/resolve/main/StereoWorldInpaintModel/vae/config.json
317 Bytes
| { | |
| "_class_name": "AutoencoderKLWan3_8", | |
| "_diffusers_version": "0.38.0", | |
| "c_dim": 160, | |
| "dim_mult": [ | |
| 1, | |
| 2, | |
| 4, | |
| 4 | |
| ], | |
| "latent_channels": 48, | |
| "spatial_compression_ratio": 16, | |
| "temperal_downsample": [ | |
| false, | |
| true, | |
| true | |
| ], | |
| "temporal_compression_ratio": 4, | |
| "vae_pth": null | |
| } | |