
MiniMax H3
vellria-minimaxFast, economical video generation. Straight from text to scene.

Input
Form0 / 10000
Settings
Settings
Output
No generation yet
Cover art
6 credits / s
Your request will cost 30 credits.
Your prompt renders as written; a narrow safety filter refuses prohibited content. Content policy
Overview
An idea gets tested here rather than finished. Run the shot, watch what movement does to it, and find out whether a composition that worked as a still survives being animated at all. Because the point is the decision and not the delivery, change one thing at a time — a verb, a camera word, a light — so you can tell which edit moved the result. What separates the variants is not what they render but how much you have settled beforehand.
Catalog
| Resolution | Credits |
|---|---|
| 480P | 6 credits / s |
| 768P | 6 credits / s |
- Duration
- 4–15s
- Aspect ratio
- 21:9 · 16:9 · 4:3 · 1:1 · 3:4 · 9:16
Variants in this family
Text is the one to reach for while the look is still negotiable: you are asking for a composition as well as movement. The image variant closes that question — what you attach is the opening frame, and the render goes entirely into motion. Reference sits between them. You hand over evidence of who should appear rather than a frame, so composing the shot is still the model's job.
| Variant | What it does | Credits |
|---|---|---|
| MiniMax H3 Image | Takes the image you provide as the first frame and animates it. | 6 credits / s |
| MiniMax H3 Reference | Generates video that keeps character consistency across several references. | 6 credits / s |