MiniMax H3 Reference-to-Video
MiniMax H3 reference-to-video: generate a video that keeps the subject from a reference image, driven by a text prompt. Supports 2K, 5-15s.
What it does
MiniMax H3 Reference-to-Video, in practice.
MiniMax H3 Reference-to-Video generates a video that keeps the subjects from your reference materials consistent throughout, driven by your text prompt. Instead of animating a fixed frame, it uses the references as identity anchors — ideal for placing a character, product, or style into new scenes and motions. References can be any mix of images, videos, and an audio track (e.g. a music beat) to sync the motion to.
- Subject consistency Preserve one or several people, characters, or objects' identities across the whole clip.
- Mix reference types Combine reference images, reference videos, and reference audio in a single request.
- Audio sync (optional) Provide a reference audio track and sync the action to the beat.
- Prompt-driven scenes Put the reference subjects into any scene or action you describe.
- High resolution output Generate videos in 2K quality.
- Flexible aspect ratios adaptive, 21:9, 16:9, 4:3, 1:1, 3:4, or 9:16.
Product photo workspace
This page is a model reference. The workspace supports white backgrounds, scene changes, packaging text edits and model try-on using Qwen Image Edit.
Parameters
What you can set.
| Parameter | What it does | Options |
|---|---|---|
prompt | The text prompt describing the video to generate. | |
refers | Reference 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 | |
resolution | The resolution of the generated video. | 480P 768P 2K |
duration | The duration of the generated video in seconds. | 4 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 21:9 16:9 4:3 1:1 3:4 9:16 |
prompt_expansion | Whether to expand the prompt for better results. | default |
Sample prompt
The prompt behind the sample.
Little Bear straightened his clothes, getting ready to look cool.
resolution: 768Pduration: 8ratio: adaptiveFAQ
Short answers.
How much does MiniMax H3 Reference-to-Video cost?
List price starts at $0.057 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 $0.46. Per-use pricing, no subscription. Model prices are reference prices. The prompt workspace is free during the period shown on the homepage; no automatic charges.
Can I use MiniMax H3 Reference-to-Video for product videos?
Yes. MiniMax Hailuo H3 is the product-video model on this site: start from a clean product photo (image-to-video) or a short brief, describe one camera move, and use the clip on a listing, a TikTok Shop card or a paid social ad. Standard commercial-use content rules apply.
What does MiniMax H3 Reference-to-Video take as input?
It is a image-to-video model. MiniMax H3 reference-to-video: generate a video that keeps the subject from a reference image, driven by a text prompt. Supports 2K, 5-15s.
How do I use MiniMax H3 Reference-to-Video?
Supply the first frame and describe only the motion. The still is the contract: identity, wardrobe, light and framing stay, so keep the prompt about camera and movement, not about changing the subject. Aspect ratio should match the still. Register or sign in to edit product photos with Qwen Image Edit. Other models on this page are catalog references.
Related