infery
← All models

Wan Text to Video

wan-v2.7-text-to-video

Video generationby Alibaba

Wan 2.7 is the latest generation AI video model, delivering enhanced motion smoothness, superior scene fidelity, and greater visual coherence.

Example

Details

Accepts
text + image

Pricing

Price
12.5 cr / second

Prices in credits (1 credit = $0.01).

Data schema

Input

FieldTypeDescription
seedRandom seed for reproducibility (0-2147483647).
promptText prompt describing the desired video. Max 5000 characters.
durationintegerenum: 2, 3, 4, 5, 6, 7Output video duration in seconds (2-15).
audio_urlURL of driving audio. Supports WAV and MP3. Duration: 2-30s. Max 15 MB.
image_urlURL of the first frame image. Formats: JPEG, JPG, PNG, BMP, WEBP. Max 20 MB.
video_urlURL of a video clip to continue from. Format: MP4, MOV. Duration: 2-10s. Max 100 MB. Cannot be combined with image_url.
resolutionstringenum: 720p, 1080pOutput video resolution tier.
end_image_urlURL of the last frame image for first-and-last-frame-to-video. Same constraints as image_url.
negative_promptContent to avoid in the video. Max 500 characters.
enable_safety_checkerbooleanEnable content moderation for input and output. Disabling it requires account authorization; unauthorized requests are always checked.
enable_prompt_expansionbooleanEnable intelligent prompt rewriting.
aspect_ratiostringenum: 16:9, 9:16, 1:1, 4:3, 3:4Aspect ratio of the generated video.
multi_shotsbooleanWhen true, enables intelligent multi-shot segmentation. When false (default), generates a single continuous shot.
reference_image_urlsReference image URLs for character/object appearance. Pass multiple images for multi-subject generation. Max 20 MB each.
reference_video_urlsReference video URLs for character/object appearance and motion. Pass multiple videos for multi-subject generation. Max 100 MB each.

Output

FieldTypeDescription
seedintegerThe seed used for generation.
videoThe generated video file.
actual_promptThe actual prompt used if prompt rewriting was enabled.