Wan2.2-T2V

Wan2.2-T2V is an open-source video diffusion model from Alibaba designed for text-to-video generation, producing high-quality video clips directly from text prompts with improved motion dynamics and scene coherence over Wan2.1. As the leading open-weight model for video generation quality, it is well-suited for creative video production, concept visualization, marketing content, and any text-driven video pipeline requiring open-weight flexibility at production scale.

Features

Serverless API

Wan2.2 T2V is available via sciforium' serverless API. Submit text prompts and receive generated video content.

Docs

Cinematic Quality

Produces high-quality video with complex motions, realistic physics, and multilingual text rendering across 5-second clips at up to 720p resolution.

Docs
MiniMax  M2.5
Kimi K2.5
GLM 5
DeepSeek V3.2
gpt-oss-120b
gpt-oss-20b
Qwen3 Instruct
Qwen3 Thinking
Qwen3 Coder
Qwen3.5
Qwen3 VL Instruct
Qwen3 ASR
Qwen-Image
Qwen-Image-Edit
Flux2
Stable Diffusion 3.5
Hunyuan Image
Z-Image
Wan2.2-I2V
Wan2.2-T2V
Hunyuan Image
Z-Image