Instructions to use FastVideo/HY-WorldPlay-AR-Diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use FastVideo/HY-WorldPlay-AR-Diffusers 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("FastVideo/HY-WorldPlay-AR-Diffusers", 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
| { | |
| "_class_name": "HYWorldPipeline", | |
| "_diffusers_version": "0.36.0.dev0", | |
| "feature_extractor": [ | |
| "transformers", | |
| "SiglipImageProcessor" | |
| ], | |
| "guider": [ | |
| "diffusers", | |
| "ClassifierFreeGuidance" | |
| ], | |
| "image_encoder": [ | |
| "transformers", | |
| "SiglipVisionModel" | |
| ], | |
| "scheduler": [ | |
| "diffusers", | |
| "FlowMatchEulerDiscreteScheduler" | |
| ], | |
| "text_encoder": [ | |
| "transformers", | |
| "Qwen2_5_VLTextModel" | |
| ], | |
| "text_encoder_2": [ | |
| "transformers", | |
| "T5EncoderModel" | |
| ], | |
| "tokenizer": [ | |
| "transformers", | |
| "Qwen2TokenizerFast" | |
| ], | |
| "tokenizer_2": [ | |
| "transformers", | |
| "ByT5Tokenizer" | |
| ], | |
| "transformer": [ | |
| "diffusers", | |
| "HYWorldTransformer3DModel" | |
| ], | |
| "vae": [ | |
| "diffusers", | |
| "AutoencoderKLHYWorld" | |
| ] | |
| } | |