H3 X image-to-video uses image_url as the opening composition and optionally last_image_url as the ending; reference collections belong to a separate endpoint. 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
vinyl-bar-last-call A 16:9 frame at 720p. The prompt starts after the frame and puts the spoken line in quotes; the clip has quiet music under it.
- 720p
- 6s
- Output5s
cedar-sauna-glance One action, a wiped stripe on a fogged panel and a look to camera. The clip has a low synth drone and no speech.
- 720p
- 5s
- Output5s
balcony-dawn-coffee A frame of two women and a prompt that asks for one slow action. Keep a two-person clip to one beat so both stay steady.
- 720p
- 5s
This example starts at $0.022 per output second. The Playground updates the estimate when you change the settings.