MiniMax H3 Max Image-to-Video
MiniMax H3 Max image-to-video: animate a first-frame image (optionally with a last frame) driven by a text prompt. Supports 480P、768P, 5-15s.
What it does
MiniMax H3 Max Image-to-Video, in practice.
MiniMax H3 Max Image-to-Video brings a static image to life at speed. Provide a first-frame image — and, optionally, a last frame — plus a prompt describing the motion, and the model generates a complete 24fps clip with audio that starts (and optionally ends) exactly on your images. A 5-second 768P clip renders in under 3 seconds, so you can try several motion directions in the time a single render usually takes.
- Near-instant generation A 5s 768P clip in under 3 seconds; 15s clips in about 15 seconds.
- Image-driven generation Animate any image with natural, controllable motion.
- First & last frame control Set the opening frame, and optionally pin the closing frame for a precise transition.
- Audio included Every clip is generated as complete audio-video at 24fps — no separate scoring or sound pass.
- Aspect ratio from your image Automatically determined by the input image (always adaptive).
- Selectable duration Produce 5–15s clips at 480P or 768P.
Run MiniMax H3 Max Image-to-Video
from $0.072/secParameters
What you can set.
| Parameter | What it does | Options |
|---|---|---|
prompt | The text prompt describing the motion / action for the video. | |
image | First frame of the video. Public URL or Base64. Formats: png, jpeg, jpg, webp. | |
end_image | Optional last frame of the video. Public URL or Base64. Formats: png, jpeg, jpg, webp. | |
resolution | Native 480P or 768P output, or SR-enhanced 1440P or 4K short edge. | 480P 768P 1440p-sr 4k-sr |
duration | The duration of the generated video in seconds. | 5 6 7 8 9 10 11 12 13 14 15 |
ratio | The aspect ratio of the generated video. Use 'adaptive' to let the model choose. | adaptive |
prompt_expansion | Whether to expand the prompt for better results. | default |
Sample prompt
The prompt behind the sample.
A cinematic sci-fi spacecraft races through a massive golden cosmic vortex, following the curvature of an enormous glowing ring. The spacecraft accelerates rapidly into the distance, leaving long trails of white-blue engine light behind it. Golden energy streams and luminous particles sweep past the camera at extreme speed, creating powerful parallax and a strong sense of motion. The camera dynamically tracks alongside and slightly behind the spacecraft, then slowly pushes forward as the ship dives deeper into the vortex. Massive arcs of golden light bend across the dark universe, while clouds
resolution: 768Pduration: 8ratio: adaptiveprompt_expansion: FAQ
Short answers.
How much does MiniMax H3 Max Image-to-Video cost?
Pricing starts at $0.072 per second of video at the base resolution; higher resolutions and longer durations cost more. An 8-second clip at the base tier is about $0.58. Usage is billed per request from your balance — no subscription.
Is this the uncensored route?
Yes. This is the MiniMax H3 route served here without an extra platform refusal layer on top of the model. Lawful prompts and outputs are your responsibility; anyone under 18 is out of scope.
What does MiniMax H3 Max Image-to-Video take as input?
It is a image-to-video model. MiniMax H3 Max image-to-video: animate a first-frame image (optionally with a last frame) driven by a text prompt. Supports 480P、768P, 5-15s.
How do I use it?
Enter an invite code to open Chat with the model loaded, or join the waitlist. We open seats in batches and track which models are requested most.
Related