Instructions to use Yang-Tian/StereoWorldModel with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Yang-Tian/StereoWorldModel 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/StereoWorldModel", 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": "Wan2_2Transformer3DModel", | |
| "_diffusers_version": "0.35.1", | |
| "add_control_adapter": true, | |
| "add_ref_conv": false, | |
| "attn_compress": 1, | |
| "cam_method": "prope", | |
| "cam_self_attn_layers": null, | |
| "control_adapter_type": "baseline", | |
| "cross_attn_norm": true, | |
| "cross_attn_type": "cross_attn", | |
| "dim": 3072, | |
| "downscale_factor_control_adapter": 16, | |
| "eps": 1e-06, | |
| "ffn_dim": 14336, | |
| "freq_dim": 256, | |
| "hidden_size": 3072, | |
| "in_channels": 48, | |
| "in_dim": 48, | |
| "in_dim_control_adapter": 24, | |
| "in_dim_ref_conv": 16, | |
| "model_type": "ti2v", | |
| "num_heads": 24, | |
| "num_layers": 30, | |
| "out_dim": 48, | |
| "patch_size": [ | |
| 1, | |
| 2, | |
| 2 | |
| ], | |
| "prope_compress_mode": "none", | |
| "prope_compress_ratio": 2, | |
| "qk_norm": true, | |
| "text_dim": 4096, | |
| "text_len": 512, | |
| "traning": false, | |
| "window_size": [ | |
| -1, | |
| -1 | |
| ] | |
| } | |