MiniMax H3 Max is now the first-choice video model

Reference to Video AI Generator

Use multiple reference materials to direct a new scene. The selected workflow accepts visual and audio references alongside your prompt.

Reference images

Reference videos

Ctrl/⌘ + Enter to generate. 0 / 20000

Guide the video with images, video and audio. Refer to Image 1, Video 1 or Audio 1 in your prompt. Audio also needs an image or video.

Enter at least 3 characters to continue.

What you can create with Reference to Video

Assign each reference a role, such as character appearance, camera movement or audio mood. This creates a new clip from your direction; use Recast when the goal is to retain the original footage and replace a person.

When to use this tool

Reference to Video suits a newly directed scene in which different files supply the character appearance, movement style and sound direction.

Provide at least an image or video. You can upload up to 12 files across all reference types, with no more than nine images, three videos or three audio clips within that total; the individual maxima cannot all be used at once. To retain the original sequence and replace its person, use MiniMax H3 Recast; to continue a source clip, use Extend Video.

A prompt to adapt

Use the person from image 1, the alley lighting from image 2, and the tracking movement of video 1 to create a new walking shot.

Tool specifications

Model
MiniMax H3 Max
Workflow
Reference to Video
Output resolution
480P / 768P
Video duration
5–15 seconds
Reference images
Optional; maximum files: 9
Reference videos
Optional; maximum files: 3
Reference audio
Optional; maximum files: 3

How to use Reference to Video

  1. 01

    Prepare your brief

    Describe the intended result and add the files required by the selected workflow.

  2. 02

    Choose and review settings

    The matching model or Agent is already selected. Review its settings, inputs and credit estimate.

  3. 03

    Generate and review

    Sign in to submit the task, follow its progress and review the output or storyboard in your workspace.

Check the quote before generating

The live estimate depends on the model, settings and input materials. Sign in and use generation credits to submit a task; review the quote in the tool before you start.

MiniMax H3 Max reference-to-video credits include output duration and input material usage. Reference image dimensions and video or audio length affect the quote.

View plans and credits

Questions about this tool

Can I generate from audio references alone?

No. Audio references need at least an image or video reference. The combined limit is twelve files; within that total, each type is limited to nine images, three videos or three audio clips. For example, six images, three videos and three audio clips fill the twelve-file total.

Do I need an account?

You can explore the tool and its settings on this page. Sign in to upload task materials, submit generation requests and save results to your workspace.

How are generation credits calculated?

Credits depend on the selected model, duration, resolution and input materials. Review the current estimate before submitting. Agent projects may include several generation tasks, each with its own credit usage. MiniMax H3 Max reference-to-video credits include output duration and input material usage. Reference image dimensions and video or audio length affect the quote.

Where can I find and download my results?

Completed results are available in your workspace. Open the task to preview or download its files. For an Agent project, review the storyboard and the assembled video in the project.

All AI tools