PixVerse V6 Max

PixVerse · Video Generation
POST /v1/videos/generationsText- and image-to-video up to 15 seconds at 1080p, with 5,000-character prompts, shot-by-shot direction, and native synchronized audio.
At a glance
Pricing
Example request
Parameters
Notes
Text-to-video and image-to-video up to 15 seconds at 1080p, with native synchronized audio. Prompts can run to 5,000 characters, so one prompt can direct performance, camera movement and shot design in detail.
Modes
t2v: text to video.i2v: animate a single image.auto, the default, usesi2vwhen an image is attached andt2votherwise.
Output
- 360p, 540p, 720p and 1080p, 1 to 15 seconds.
- Aspect ratios 16:9, 4:3, 1:1, 3:4, 9:16, 2:3, 3:2 and 21:9 on text-to-video. Image-to-video follows the source image.
- Set
generate_audio_switchto true for native synchronized audio. - For several shots in one clip, describe them in order in the prompt, for example “Shot 1: … Shot 2: …”.
Billing
- Billed per second of generated video at the rate for the output resolution, with a higher rate when audio is on.
Input limits
- One image: PNG, JPEG or WebP, up to 20MB and 10000px on the long edge.
- First and last frame, reference images, video input and clip extension are not available on this model. Use PixVerse V6 for those.
Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/pixverse-v6-max.
