# Z-image 勇者
## 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：[Tongyi-MAI/Z-Image](https://modelscope.cn/models/Tongyi-MAI/Z-Image)
* 训练代码：[DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio)
* 训练数据量：11
* 总训练步数：6000
* 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
from diffsynth.pipelines.z_image import ZImagePipeline, ModelConfig
import torch
pipe = ZImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="Tongyi-MAI/Z-Image", origin_file_pattern="transformer/*.safetensors"),
ModelConfig(model_id="Tongyi-MAI/Z-Image", origin_file_pattern="text_encoder/*.safetensors"),
ModelConfig(model_id="Tongyi-MAI/Z-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
],
tokenizer_config=ModelConfig(model_id="Tongyi-MAI/Z-Image", origin_file_pattern="tokenizer/"),
)
pipe.load_lora(pipe.dit, ModelConfig(model_id="Liudef/XB_ZIMAGE_MOTA_YZ", origin_file_pattern="XB_ZIMAGE_MOTA_YZ_c1-st6000.safetensors"))
prompt = "a cat"
image = pipe(prompt=prompt, num_inference_steps=50, cfg_scale=4)
image.save("image.jpg")
```