Start Now
Dreamina Seedance 2.0 image-to-video model. Generate video from a text prompt, optionally conditioned on a first or last frame, up to nine reference images, and up to three reference audio tracks. Outputs 480p, 720p, or 1080p with configurable aspect ratio.
Input
Text describing the video to generate. Reference optional inputs with placeholders such as `[Image 1]` or `[Audio 1]` when applicable. Recommended prompt length: under 1000 words. Lengthy text will lead to scattered information, and the model may ignore details and only focus on key points, resulting in missing elements in the generated video.
Optional. Up to 3 reference audio URLs (e.g., for rhythm or voice style).
Hint: Drag and drop files, paste from clipboard (Ctrl/Cmd+V), or provide a URL.
Whether to keep the camera fixed during generation.
Video duration in seconds (4-15 seconds).
5
Task expiration time in seconds.
Optional. URL or Base64 of the starting frame. Do not use together with `reference_images` in the same request.
Hint: Drag and drop files, paste from clipboard (Ctrl/Cmd+V), or provide a URL.
Whether to generate audio for the video.
Optional. URL or Base64 of the ending frame. Do not use together with `reference_images` in the same request.
Hint: Drag and drop files, paste from clipboard (Ctrl/Cmd+V), or provide a URL.
Aspect ratio of the generated video.
1:1
Optional. Up to 9 reference images for style or subject guidance. Do not use together with `first_frame_image` or `last_frame_image`.
Hint: Drag and drop files, paste from clipboard (Ctrl/Cmd+V), or provide a URL.
Output resolution of the video.
720p
Whether to return the last frame of the generated video.
Random seed for reproducible generation. Use -1 for random.
Result
No results yet
Run the model to preview the output here.
