An H3 X reference scene accepts 9 images, 2 videos totalling 15 seconds and 3 audio clips at most; name their roles with Image 1, Video 1 and Audio 1. For an H3 X sequence, choose 2–15 whole seconds; the default is 5 and the output runs at 24 fps.
Workbench
These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.
- Output7s
boutique-trench-fitting Three references in order: a portrait, a coat photo and a fitting room. The prompt calls them Image 1, 2 and 3.
- 720p
- 16:9
- 6s
- Output5s
dance-move-transfer One portrait and one short motion clip. "Copy only the motion from Video 1" and "keep his face and white tank top from Image 1" separate the two jobs; the clip repeats the spin and side-step.
- 720p
- 16:9
- 5s
- Output5s
elevator-loosened-tie Two portraits, each referred to by position, and one slow action in a 9:16 elevator: loosening a tie, a kiss, the doors opening. Both faces and suits were kept.
- 720p
- 9:16
- 5s
This example starts at $0.022 per output second. The Playground updates the estimate when you change the settings.