FastVideo/FastWan2.2-TI2V-5B-FullAttn-Diffusers
A fast, high-quality text-to-video model — 5-second clips at 24 fps in 720p or 480p, landscape or portrait, from a text prompt. A 3-step DMD distillation of Wan2.2-TI2V-5B by FastVideo (Hao AI Lab).
Try the model with a sample request using the same API shape shown in the reference page.
Output orientation: landscape (1280x704) or portrait (704x1280).
Clip duration: always 5 seconds (fixed/required for this model).
Output resolution class. 720p renders 1280x704 (704 on the short side: the Wan2.2 VAE needs multiples of 32, the industry-standard convention for this model family); 480p renders 832x480.
Text prompt describing the image
specify a seed for reproducible output (Default: empty)
Adjust settings and run the demo to see the model output generated here in real-time.
