---
license: apache-2.0
language:
  - en
  - zh
base_model:
  - MiniMaxAI/MiniMax-H3
pipeline_tag: image-to-video
library_name: diffusers
tags:
  - t2v
  - i2v
  - r2v
---

# MiniMax-H3 Turbo

Please check [our repository](https://github.com/ModelTC/Minimax-H3-Turbo) or the [LightX2V MiniMax-H3 examples](https://github.com/ModelTC/LightX2V/tree/main/examples/minimax_h3) to reproduce the results.

Please check the [model specifications](https://github.com/ModelTC/Minimax-H3-Turbo#model-specs) for more details.

## Online App

Try the MiniMax-H3 Turbo LoRA directly in LightX2V Studio:

- **LightX2V Studio:** [x2v.light-ai.top](https://x2v.light-ai.top/)

The Studio currently uses the [FL2V 8-step v1.0 768p LoRA](https://huggingface.co/lightx2v/Minimax-h3-Turbo/blob/main/minimax_h3_fl2v_turbo_8step_v1.0_768p_bf16.safetensors), which provides improved video and audio generation quality with 8-step inference.

> The model version deployed in the Studio may be updated over time.

### Studio Preview

<!-- Drag and drop the LightX2V Studio screenshot below this line. -->

![screenshot-20260827-172523](https://cdn-uploads.huggingface.co/production/uploads/680de13385293771bc57400b/SjpJ1h2wuwqZchY18D_8Z.png)

## Online API

Integrate MiniMax-H3 Turbo into your application through the LightX2V API:

- **API Documentation:** [x2v.light-ai.top/api-docs](https://x2v.light-ai.top/api-docs)