Instructions to use TencentARC/WorldCrafter-Fast with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use TencentARC/WorldCrafter-Fast with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image, export_to_video # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("TencentARC/WorldCrafter-Fast", dtype=torch.bfloat16, device_map="cuda") pipe.to("cuda") prompt = "A man with short gray hair plays a red electric guitar." image = load_image( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png" ) output = pipe(image=image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Notebooks
- Google Colab
- Kaggle
Download adapter_low_noise/repencoder_frozen.json from TencentARC/WorldCrafter-Fast: direct link, hf CLI and curl.
- Browser
- Download file 841 Bytes
-
https://huggingface.co/TencentARC/WorldCrafter-Fast/resolve/main/adapter_low_noise/repencoder_frozen.json
- Command line
-
hf download hf://TencentARC/WorldCrafter-Fast/adapter_low_noise/repencoder_frozen.json
-
curl -L -o repencoder_frozen.json https://huggingface.co/TencentARC/WorldCrafter-Fast/resolve/main/adapter_low_noise/repencoder_frozen.json
841 Bytes
| { | |
| "format": "helios_frozen_repencoder_reference_v1", | |
| "history_contract": "memory4_lagernvs_mid2_recent1", | |
| "repencoder": { | |
| "compute_dtype": "bfloat16", | |
| "format": "helios_repencoder_manifest_v2_unmerged_lora", | |
| "input_boundary": "standardized_wan_latent_source9", | |
| "lora": { | |
| "alpha": 32.0, | |
| "factor_dtype": "float32", | |
| "merged_into_dense_weights": false, | |
| "module_count": 438, | |
| "rank": 64, | |
| "scaling": 0.5 | |
| }, | |
| "model_sha256": "f4bfdad9ac4ec451a5d08ec19d94befc928032574367564143dce1cfe6f91504", | |
| "output_boundary": "standardized_wan_latent_memory4", | |
| "parameter_count": 1141128528, | |
| "source0": "recent[-1]", | |
| "target_slots": [ | |
| 2, | |
| 4, | |
| 6, | |
| 8 | |
| ], | |
| "tensor_count": 2331 | |
| }, | |
| "target_slots": [ | |
| 2, | |
| 4, | |
| 6, | |
| 8 | |
| ], | |
| "trainable": false | |
| } | |