minimaxiH3 Get access
MiniMaxImage-to-videoSpicy route · no extra filter

MiniMax H3-Developer Reference-to-Video

MiniMax H3-Developer self-hosted reference-to-video: generate a video that keeps the subject from one or more reference images/videos, driven by a text prompt, with generated audio. Supports 480P768P/2K.

$0.030per secondStarting price at the base resolution and quality tier.
$0.24Typical 8-second clip at the base tier. Longer or higher-resolution outputs scale with duration and tier.
Pay per useBilled per request from your balance. No subscription, no minimum.
Sample output · prompt: “The race car driver raises a hand in celebration of the victory.”

What it does

MiniMax H3-Developer Reference-to-Video, in practice.

MiniMax H3-Developer Reference-to-Video keeps a subject consistent — with sound. Provide one or more reference materials (images and/or videos of a person, animal, or object) plus a prompt. Generate native 480P or 768P video, or select an ESR tier to enhance the output to a 1080P, 1440P, or 4K short edge while preserving the referenced subject's identity, complete with a synchronized soundtrack generated from the described scene.

  • Subject-consistent generation Keep the referenced subject's identity across the whole shot.
  • Multi-modal references Drive generation with images and/or videos in a single request.
  • Native audio A matching soundtrack is generated alongside the video — no separate audio input needed.
  • Enhanced resolution output Generate native 480P or 768P video, or use ESR for a 1080P, 1440P, or 4K short edge.
  • Selectable duration Produce 5–15s clips.

Run MiniMax H3-Developer Reference-to-Video

from $0.030/sec
Drop an image hereor click to choose a fileFiles stay in your project. Nothing is trained on.
resolution
duration
ratio
Invite code opens Chat with this model loaded. No code yet? Join the waitlist — we count which models people ask for.

Parameters

What you can set.

ParameterWhat it doesOptions
promptThe text prompt describing the video to generate.
refersReference materials that anchor the generation. Any mix of reference images, videos, and audio, each as a public URL. At least one image OR video is required (audio alone is not allowed). Image formats: png, jpeg, jpg, webp; video: mp4, mov
resolutionThe resolution of the generated video.480P 768P 1440p-sr 4k-sr
durationThe duration of the generated video in seconds.4 5 6 7 8 9 10 11 12 13 14 15
ratioThe aspect ratio of the generated video. Use 'adaptive' to let the model choose.adaptive 21:9 16:9 4:3 1:1 3:4 9:16
prompt_expansionWhether to expand the prompt for better results.default

Sample prompt

The prompt behind the sample.

The race car driver raises a hand in celebration of the victory.
resolution: 480Pduration: 5seed: -1num_inference_steps: 50

FAQ

Short answers.

How much does MiniMax H3-Developer Reference-to-Video cost?

Pricing starts at $0.030 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 $0.24. 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-Developer Reference-to-Video take as input?

It is a image-to-video model. MiniMax H3-Developer self-hosted reference-to-video: generate a video that keeps the subject from one or more reference images/videos, driven by a text prompt, with generated audio. Supports 480P768P/2K.

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

Models people compare with this one.

Run MiniMax H3-Developer Reference-to-Video.

Invite code opens Chat with the model loaded. No code — join the waitlist and we will count the request.

Get access Browse models