Wan

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

17291 stars · 2193 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Wan is an open-source family of large-scale video generation models (Wan2.1/Wan2.2) with Python inference code and pretrained weights for text-to-video and image-to-video generation. Wan2.2 adds a Mixture-of-Experts diffusion architecture, cinematic aesthetic control, and a 5B model that runs 720P@24fps on consumer GPUs.

Use cases

• generate videos from text prompts
• animate an image into a video
• run video generation locally on a 4090
• control cinematic style of generated videos
• research video diffusion model architectures
• fine-tune open video generation models

When to choose

• you need open weights for text-to-video or image-to-video generation
• you want 720P@24fps generation on consumer GPUs
• you need controllable cinematic aesthetics in generated video

When to avoid

• you need a hosted API without GPU infrastructure
• you only need image generation, not video
• you lack a CUDA-capable GPU

Facets

library · maturity active

video-processing machine-learning deep-learning llm-inference artificial-intelligence deep-learning media python cross-platform video-generation text-to-video image-to-video diffusion-models mixture-of-experts aigc model-weights video gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Wan-Video/Wan2.2")