Instructions to use Wan-AI/Wan2.2-Animate-2-14B-Diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Wan-AI/Wan2.2-Animate-2-14B-Diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Wan-AI/Wan2.2-Animate-2-14B-Diffusers", 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
Commit History
-
Add modular_model_index.json for ModularPipeline.from_pretrained
Verified signature0f53091 -
Use DPMSolverMultistepScheduler (the scheduler the release samples with)
Verified signaturecde15a5 -
Add diffusers-format transformer weights
Verified signatureAdds the diffusers-format Wan-Animate-2 weights for huggingface/diffusers#14413: - `transformer/`: converted from the research state dict (conversion verified bitwise) - `scheduler/scheduler_config.json`: the scheduler the release samples with (the current file says `UniPCMultistepScheduler`, which does not match `model_index.json`) - `modular_model_index.json`: enables `ModularPipeline.from_pretrained` on this repo; the `transformer`/`scheduler` specs pin this PR's revision so it is runnable before merging — they can be set to `null` once merged39bbd69
-
Upload folder using huggingface_hub
Verified signaturea84c891
-
Upload folder using huggingface_hub
Verified signature5f20f8d -
initial commit
Verified signaturead35e07