The Wan image-to-video model can generate videos using prompts and image references, featuring rich artistic styles and cinematic quality. Wan 2.6 introduces multi-shot narrative capabilities and supports both automatic dubbing and uploading custom audio files.
API Key authentication. Format: Bearer YOUR_API_KEY.
First frame image URL (supports HTTP/HTTPS/Base64)
"https://example.com/image.jpg"
Video content description, supports Chinese and English
1 - 800"Camera slowly zooms in"
Negative prompt describing unwanted content
500"blurry, distorted"
Video resolution tier
480P, 720P, 1080P "720P"
Video duration in seconds (integer)
2 <= x <= 155
Whether to generate video with audio (only supported by wan2.6-i2v-flash)
false
Enable prompt intelligent rewriting
false
Random seed for reproducibility
0 <= x <= 214748364742
Custom audio URL (supports wav/mp3, 3-30 seconds, ≤15MB)
"https://example.com/audio.mp3"
Shot type (single-shot or multi-shot narrative)
single, multi "single"