---
title: Z-Image-portrait-photorealistic-fashion-201a64
canonical_url: "https://www.modelscope.ai/models/diffsynth-i2L-gallery/Z-Image-portrait-photorealistic-fashion-201a64"
md_url: "https://www.modelscope.ai/models/diffsynth-i2L-gallery/Z-Image-portrait-photorealistic-fashion-201a64.md"
repository: diffsynth-i2L-gallery/Z-Image-portrait-photorealistic-fashion-201a64
chinese_name: "人像摄影、写实、时尚"
last_updated: 2026-06-22
license: "Apache License 2.0"
base_model:
  - Tongyi-MAI/Z-Image
base_model_relation: adapter
parameters: 9.9M
tensor_type:
  - BF16
library_name:
  - pytorch
  - lora
  - safetensors
downloads: 24
stars: 1
tags:
  - LoRA
---

# Z-Image-portrait-photorealistic-fashion-201a64

> Z-Image-portrait-photorealistic-fashion-201a64 - An open-source model by diffsynth-i2L-gallery on ModelScope. 本模型由模型 DiffSynth-Studio/ZImage-i2L-v2 生成

diffsynth-i2L-gallery/Z-Image-portrait-photorealistic-fashion-201a64 is a 9.9M-parameter machine learning model on ModelScope. licensed under Apache License 2.0. derived from Tongyi-MAI/Z-Image.

- **Repository**: diffsynth-i2L-gallery/Z-Image-portrait-photorealistic-fashion-201a64
- **License**: Apache License 2.0
- **Parameters**: 9.9M
- **Base model**: Tongyi-MAI/Z-Image
- **Tags**: LoRA
- **Downloads**: 24
- **Stars**: 1
- **Last updated**: 2026-06-22

Source: https://www.modelscope.ai/models/diffsynth-i2L-gallery/Z-Image-portrait-photorealistic-fashion-201a64

---

# 人像摄影、写实、时尚

## 模型介绍

本模型由模型 [DiffSynth-Studio/ZImage-i2L-v2](https://modelscope.ai/models/DiffSynth-Studio/ZImage-i2L-v2) 生成

## 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="diffsynth-i2L-gallery/Z-Image-portrait-photorealistic-fashion-201a64", origin_file_pattern="1782140486.773361-d32d83d9-fae8-487a-bda6-33653026ae83.safetensors"))
prompt = "a cat"
image = pipe(prompt=prompt, num_inference_steps=50, cfg_scale=4)
image.save("image.jpg")
```