Instructions to use Wan-AI/Wan2.2-S2V-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Wan-AI/Wan2.2-S2V-14B 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("Wan-AI/Wan2.2-S2V-14B", 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
Request: DOI
i'd like to use this on kaggle and it's blocked.
EntryNotFoundError: 404 Client Error. (Request ID: Root=1-694937fd-51bd2fde522938241a22e214;bf2946fb-47e3-4b1d-9243-9afe8000afe8)
Entry Not Found for url: https://huggingface.co/Wan-AI/Wan2.2-S2V-14B/resolve/main/model_index.json.
->Issue with diffusers.DiffusionPipeline.from_pretrained due to missing model_index.json
Dear Wan-AI Team,
I am writing to report an issue when trying to load your Wan2.2-S2V-14B model using the diffusers library's DiffusionPipeline.from_pretrained() method.
Users are consistently encountering an EntryNotFoundError with the message: Entry Not Found for url: https://huggingface.co/Wan-AI/Wan2.2-S2V-14B/resolve/main/model_index.json.
After inspecting the repository files, it appears that the model_index.json file, which is crucial for diffusers to properly identify and load the pipeline components, is missing from the root of your model's repository.
This absence prevents the DiffusionPipeline from initializing the model correctly, even when users are authenticated and have accepted the gated model's terms.
Could you please either:
Add the "model_index.json" file to the repository if the model is intended to be loaded directly via diffusers.DiffusionPipeline.from_pretrained().
Provide clear instructions in the model card (README.md) on the correct method to load and use this model, especially if it requires a different approach or specific component loading outside of the standard diffusers pipeline API.
Many thanks for your work on this model, and we look forward to being able to use it effectively.
Best,
Anssi