Skip to content
Explore models

Video

MiniMax (Hailuo AI) Video 01 Subject Reference

Generate video clips maintaining consistent, realistic facial features and identity across dynamic video content

  • Image to video
Create with MiniMax (Hailuo AI) Video 01 Subject Reference
Preview for MiniMax (Hailuo AI) Video 01 Subject Reference

Catalog preview for MiniMax (Hailuo AI) Video 01 Subject Reference. Review your own result before publishing.

A starting point.

Select the operation for your source, upload any required media, and describe the result you want.

Before you publish.

Watch the entire clip and compare motion, identity, transitions and audio with your inputs.

Review the quote before running. A failed generation releases its reserved credits. Download the results you want to keep; stored media is retained for 30 days.

How credits work · Use the API · Content guidelines

Inputs and settings

Use the current input form for this endpoint, then review the credit quote before generating.

Supported inputs

These fields come from the current studio form for minimax/video-01-subject-reference. Other modes may require different inputs.

Input types, requirements and limits for minimax/video-01-subject-reference
InputTypeRequirementOptions and limits
promptTextRequiredMax. characters: 2000
subject_reference_image_urlTextRequired—
prompt_optimizerOn/offOptional—

Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.

Use MiniMax (Hailuo AI) Video 01 Subject Reference through the API.

Start with this model ID for the endpoint featured on this page:

minimax/video-01-subject-reference

Input requirements belong to this model ID. Check a different mode’s schema separately when switching modes.

Check the current model schema for supported inputs and options. Other tasks may use different model IDs.

From quote to result.

Request a credit quote for your input and settings before submitting a generation. A sample output or the price of another model is not a quote for your request.

Follow the generation workflow, then poll the job for its status and result. The API and studio use the same balance.