Wan2.2-I2V-A14B-Diffusers is the Diffusers-format release of Wan 2.2 image-to-video, so Hugging Face Diffusers is the official route to run it locally 2. Replicate hosts a PrunaAI-optimized Wan 2.2 A14B image-to-video action for cloud use 15.
- 1
Hugging Face Diffusershuggingface.coverified and signed
Pretrained diffusion pipelines with few-line inference and LoRA adapters for image, video and audio generation, usable as the SDK route to run the Wan 2.2 Diffusers checkpoint locally 26.
official:SDK · diffusers+25 community tools built for it
for agents: stable · diffusion · deep
- 2
- 3
Sources
- 1Replicate - Run AI with an APIreplicate.com · read 2026-10-29
- 2Diffusers · Hugging Facehuggingface.co · read 2026-10-29
- 4Generative AI API Platform | Run FLUX, Kling & Seedance | Muapimuapi.ai · read 2026-10-29
- 5wan-video/wan-2.2-i2v-fast: declares "wan-video/wan-2.2-i2v-fast" (the record we read and signed)unfragile.ai · read 2026-10-24
- 6diffusers: declares "stable" (the record we read and signed)unfragile.ai · read 2026-10-24
- 8Muapi: declares "muapi_video_from_image" (the record we read and signed)unfragile.ai · read 2026-10-24
For agents: the 10 actions behind this answer
wan-video/wan-2.2-i2v-fast · wan-video/wan-2.2-i2v-fast verified and signed
A very fast and cheap PrunaAI optimized version of Wan 2.2 A14B image-to-video
wan-video/wan-2.2-i2v-a14b · wan-video/wan-2.2-i2v-a14b verified and signed
Image-to-video at 720p and 480p with Wan 2.2 A14B
wavespeedai/wan-2.1-i2v-480p · wavespeedai/wan-2.1-i2v-480p verified and signed
Accelerated inference for Wan 2.1 14B image to video, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation.
wavespeedai/wan-2.1-i2v-720p · wavespeedai/wan-2.1-i2v-720p verified and signed
Accelerated inference for Wan 2.1 14B image to video with high resolution, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation.
wan-video/wan-2.2-t2v-fast · wan-video/wan-2.2-t2v-fast verified and signed
A very fast and cheap PrunaAI optimized version of Wan 2.2 A14B text-to-video
wan-video/wan-2.2-5b-fast · wan-video/wan-2.2-5b-fast verified and signed
The fastest Wan 2.2 text-to-image and image-to-video model
wavespeedai/wan-2.1-t2v-480p · wavespeedai/wan-2.1-t2v-480p verified and signed
Accelerated inference for Wan 2.1 14B text to video, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation.
lucataco/wan2.1-4step · lucataco/wan2.1-4step verified and signed
Wan 2.1 I2V (14B) 480p with CausVid LoRA
wavespeedai/wan-2.1-t2v-720p · wavespeedai/wan-2.1-t2v-720p verified and signed
Accelerated inference for Wan 2.1 14B text to video with high resolution, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation.
stable · diffusers verified and signed
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.