Image-to-Video
Diffusers
Safetensors
Wan2.2
WanAnimatePipeline
wan-animate
character-animation
mxfp4
auto-round
8-bit precision
Instructions to use intel-ai/Wan2.2-Animate-14B-Diffusers-MXFP4-AutoRound with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use intel-ai/Wan2.2-Animate-14B-Diffusers-MXFP4-AutoRound 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("intel-ai/Wan2.2-Animate-14B-Diffusers-MXFP4-AutoRound", 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") - Wan2.2
How to use intel-ai/Wan2.2-Animate-14B-Diffusers-MXFP4-AutoRound with Wan2.2:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Download transformer/quantization_config.json from intel-ai/Wan2.2-Animate-14B-Diffusers-MXFP4-AutoRound: direct link, hf CLI and curl.
- Browser
- Download file 468 Bytes
-
https://huggingface.co/intel-ai/Wan2.2-Animate-14B-Diffusers-MXFP4-AutoRound/resolve/main/transformer/quantization_config.json
- Command line
-
hf download hf://intel-ai/Wan2.2-Animate-14B-Diffusers-MXFP4-AutoRound/transformer/quantization_config.json
-
curl -L -o quantization_config.json https://huggingface.co/intel-ai/Wan2.2-Animate-14B-Diffusers-MXFP4-AutoRound/resolve/main/transformer/quantization_config.json
468 Bytes
| { | |
| "bits": 4, | |
| "act_bits": 4, | |
| "data_type": "mx_fp", | |
| "act_data_type": "mx_fp", | |
| "group_size": 32, | |
| "act_group_size": 32, | |
| "sym": true, | |
| "act_sym": true, | |
| "act_dynamic": true, | |
| "enable_quanted_input": false, | |
| "low_gpu_mem_usage": true, | |
| "autoround_version": "0.17.0", | |
| "block_name_to_quantize": "motion_encoder.res_blocks,motion_encoder.motion_network,blocks,face_adapter", | |
| "quant_method": "auto-round", | |
| "packing_format": "auto_round:llm_compressor" | |
| } |