wan/2-5-image-to-video
Wan 2.5 API from Alibaba is designed for cinematic AI video generation, supporting both text-to-video (wan2.5-t2v-preview) and image-to-video (wan2.5-i2v-preview). It natively synchronizes visuals with dialogue, ambient sound, and background music. With support for multiple resolutions (720p, 1080p) and aspect ratios (16:9, 9:16, 1:1), the API delivers flexible outputs suitable for social media, advertising, and creative storytelling.
Try the model with a sample request using the same API shape shown in the reference page.
URL of the image to use as the first frame. Must be publicly accessible
Whether to enable prompt rewriting using LLM
The duration of the generated video in seconds
Video resolution.
Negative prompt to describe content to avoid
Text prompt describing the image
Random seed for reproducibility. If None, a random seed is chosen
Adjust settings and run the demo to see the model output generated here in real-time.
