Start Now
Wan image-to-video model generates videos from prompts and images with cinematic quality. Wan 2.6 adds multi-shot narrative, automatic dubbing, and custom audio.
Input
Negative prompt describing unwanted content
Video content description, supports Chinese and English
Whether to generate video with audio (only supported by wan2.6-i2v-flash)
Custom audio URL (supports wav/mp3, 3-30 seconds, ≤15MB)
Hint: Drag and drop files, paste from clipboard (Ctrl/Cmd+V), or provide a URL.
Video duration in seconds (integer)
5
First frame image URL (supports HTTP/HTTPS/Base64)
Hint: Drag and drop files, paste from clipboard (Ctrl/Cmd+V), or provide a URL.
Enable prompt intelligent rewriting
Video resolution tier
resolution
Random seed for reproducibility
Shot type (single-shot or multi-shot narrative)
shot_type
Result
No results yet
Run the model to preview the output here.
