---
title: AIdongzhuo
canonical_url: "https://www.modelscope.cn/models/a837226547/AIdongzhuo"
md_url: "https://www.modelscope.cn/models/a837226547/AIdongzhuo.md"
repository: a837226547/AIdongzhuo
chinese_name: "AI动作"
last_updated: 2026-08-31
license: "Apache License 2.0"
base_model:
  - MiniMax/MiniMax-H3
base_model_relation: adapter
parameters: 812.6M
tensor_type:
  - BF16
library_name:
  - pytorch
  - lora
  - safetensors
downloads: 744
stars: 10
tags:
  - LoRA
---

# AIdongzhuo

> AIdongzhuo - a837226547 在 ModelScope 开源的模型。本模型依托魔搭社区（ModelScope）AIGC专区模型训练环境与算力完成训练。

a837226547/AIdongzhuo 是 ModelScope 魔搭社区上的 812.6M 参数机器学习模型，采用 Apache License 2.0 许可，基于 MiniMax/MiniMax-H3 构建。

- **Repository**: a837226547/AIdongzhuo
- **License**: Apache License 2.0
- **Parameters**: 812.6M
- **Base model**: MiniMax/MiniMax-H3
- **Tags**: LoRA
- **Downloads**: 744
- **Stars**: 10
- **Last updated**: 2026-08-31

Source: https://www.modelscope.cn/models/a837226547/AIdongzhuo

---

# AI动作

## 模型介绍

本模型依托魔搭社区（ModelScope）AIGC专区[模型训练](https://modelscope.cn/aigc/modelTraining)环境与算力完成训练。

* 模型类型：LoRA
* 基础模型：[MiniMax/MiniMax-H3](https://modelscope.cn/models/MiniMax/MiniMax-H3)
* 训练代码：[DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio)
* 训练数据量：5
* 总训练步数：2000
* 开源协议：Apache-2.0

## 推理代码

安装 [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio)：

```bash
pip install diffsynth
```

开始推理：

```python
import torch
from diffsynth.pipelines.minimax_h3_audio_video import MiniMaxH3Pipeline, ModelConfig
from diffsynth.utils.data.audio_video import write_video_audio

vram_config = {
    "offload_dtype": "disk",
    "offload_device": "disk",
    "onload_dtype": "disk",
    "onload_device": "disk",
    "preparing_dtype": torch.bfloat16,
    "preparing_device": "cuda",
    "computation_dtype": torch.bfloat16,
    "computation_device": "cuda",
}
pipe = MiniMaxH3Pipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
        ModelConfig(model_id="MiniMax/MiniMax-H3", origin_file_pattern="FL2VA/text_encoder/model*.safetensors", **vram_config),
        ModelConfig(model_id="MiniMax/MiniMax-H3", origin_file_pattern="FL2VA/transformer/model*.safetensors", **vram_config),
        ModelConfig(model_id="MiniMax/MiniMax-H3", origin_file_pattern="FL2VA/video_vae/source/model.safetensors", **vram_config),
        ModelConfig(model_id="MiniMax/MiniMax-H3", origin_file_pattern="FL2VA/audio_vae/model.safetensors", **vram_config),
    ],
    processor_config=ModelConfig(model_id="MiniMax/MiniMax-H3", origin_file_pattern="FL2VA/processor/"),
    vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 2,
)
pipe.load_lora(pipe.dit, ModelConfig(model_id="a837226547/AIdongzhuo", origin_file_pattern="AIdongzhuo_c2-st2000.safetensors"))

prompt = "A cat"
video, audio = pipe(
    prompt=prompt,
    height=480, width=832, num_frames=124, num_inference_steps=50, seed=0,
)
write_video_audio(
    video=video, audio=audio,
    output_path="t2va.mp4", fps=24, audio_sample_rate=32000,
)
```