pixverse-v6-max/image-to-video

PixVerse V6 Max is PixVerse's AI video model for cinematic text-to-video and image-to-video generation. It delivers realistic motion and native audio, with up to 15s video at 1080p.

Pricing: From 29 credits for 5 seconds (360p, no audio); with audio 44 credits for 5 seconds, billed on output seconds. Every mode is in the rate card below.

Playground

Pre-filled from the model spec — run it as-is, or tweak any field first.

Ready

FormJSON

Prompt

Use the supplied image as the first frame. The ceramic artist turns the clay bowl in her hands and smiles softly, warm window light, slow push-in.

A text description of the video you want to generate

Reference image

Add imagesRemove

Remove 1

Upload an image file to use as input for the API

Duration4

Video duration in seconds.

Quality

360p540p720p1080p

The output video resolution.

generate_audio_switch

Whether to generate audio switch

Seed

Random seed, Range: 0 - 2147483647.

Balance: —Estimated reservation24 credits(estimated before generation; actual charge shown on completion)

ResetRun

Upload your own image for the required field(s) above first — the pre-filled sample is only a preview and is not sent.

Result

PreviewJSON

HistoryDownload

Sample output for this variant — press Run to generate your own.

curl https://modelfold.ai/v1/videos/generations \
  -H "Authorization: Bearer $MODELFOLD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"pixverse-v6-max/image-to-video","prompt":"...","resolution":"720p","duration":5}'