Wan 2.7 I2V
[Core Function] Wan 2.7 I2V is Alibaba’s flagship multimodal image-to-video model. [Strengths] It supports multimodal input (text, image, audio, video) for first-frame, start-and-end-frame (FL2V), and video continuation tasks. [Best For] Highly recommended for: complex image animation, cinematic transitions, and video extension workflows. [Limitations] Do NOT use this model if you only need a quick, simple animation where HappyHorse might be faster. [Routing] Use this model by default for complex image-to-video or video continuation tasks.
Authorizations
API Key authentication. Format: Bearer YOUR_API_KEY.
Body
- Option 1
- Option 2
Flattened media parameters for Wan 2.7 I2V. Task mode must be one of: first_frame, first_frame+last_frame, first_frame+driving_audio, first_frame+last_frame+driving_audio, first_clip, first_clip+last_frame.
First frame image URL. Supports HTTP/HTTPS URL, OSS URL, or image base64 data URI.
^(https?://|oss://|data:image/)"https://example.com/first.png"
"oss://dashscope-instant/example/first.png"
"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNk+M9QDwADhgGAWjR9awAAAABJRU5ErkJggg=="
Optional text prompt, max 5000 chars.
5000Optional negative prompt, max 500 chars.
500Optional last frame image URL. Supports HTTP/HTTPS URL, OSS URL, or image base64 data URI.
^(https?://|oss://|data:image/)Optional driving audio URL (HTTP/HTTPS/OSS).
^(https?://|oss://)Optional first clip URL for continuation mode (HTTP/HTTPS/OSS).
^(https?://|oss://)Output resolution tier.
720P, 1080P Video duration in seconds.
2 <= x <= 15Enable prompt intelligent rewrite.
Random seed for reproducibility.
0 <= x <= 2147483647