---
title: Z-Image-ancient_chinese-character_illustration-ink_wash-1772082134.940298
canonical_url: "https://www.modelscope.cn/models/diffsynth-i2L-gallery/Z-Image-ancient_chinese-character_illustration-ink_wash-1772082134.940298"
md_url: "https://www.modelscope.cn/models/diffsynth-i2L-gallery/Z-Image-ancient_chinese-character_illustration-ink_wash-1772082134.940298.md"
repository: diffsynth-i2L-gallery/Z-Image-ancient_chinese-character_illustration-ink_wash-1772082134.940298
chinese_name: "古风、人物插画、水墨"
last_updated: 2026-02-26
license: "Apache License 2.0"
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - Tongyi-MAI/Z-Image
base_model_relation: adapter
parameters: 19.8M
tensor_type:
  - BF16
library_name:
  - pytorch
  - lora
  - safetensors
supports_inference: txt2img
downloads: 24
stars: 3
tags:
  - LoRA
  - text-to-image
---

# Z-Image-ancient_chinese-character_illustration-ink_wash-1772082134.940298

> Z-Image-ancient_chinese-character_illustration-ink_wash-1772082134.940298 - diffsynth-i2L-gallery 在 ModelScope 开源的模型。本模型使用 Z-Image-i2L 从 7 张图像生成。

diffsynth-i2L-gallery/Z-Image-ancient_chinese-character_illustration-ink_wash-1772082134.940298 是 ModelScope 魔搭社区上的 19.8M 参数text-to-image-synthesis模型，采用 Apache License 2.0 许可，基于 Tongyi-MAI/Z-Image 构建，并支持在线推理（txt2img）。

- **Repository**: diffsynth-i2L-gallery/Z-Image-ancient_chinese-character_illustration-ink_wash-1772082134.940298
- **License**: Apache License 2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 19.8M
- **Base model**: Tongyi-MAI/Z-Image
- **Online inference**: txt2img
- **Tags**: LoRA, text-to-image
- **Downloads**: 24
- **Stars**: 3
- **Last updated**: 2026-02-26

Source: https://www.modelscope.cn/models/diffsynth-i2L-gallery/Z-Image-ancient_chinese-character_illustration-ink_wash-1772082134.940298

---

# 古风、人物插画、水墨

本模型使用 [**Z-Image-i2L**](https://modelscope.cn/models/DiffSynth-Studio/Z-Image-i2L) 从 7 张图像生成。

## 安装

```bash
git clone https://github.com/modelscope/DiffSynth-Studio.git  
cd DiffSynth-Studio
pip install -e .
```

## 使用本模型

```python
from modelscope import snapshot_download
from diffsynth.pipelines.z_image import ZImagePipeline, ModelConfig
import torch

vram_config = {
    "offload_dtype": torch.bfloat16,
    "offload_device": "cuda",
    "onload_dtype": torch.bfloat16,
    "onload_device": "cuda",
    "preparing_dtype": torch.bfloat16,
    "preparing_device": "cuda",
    "computation_dtype": torch.bfloat16,
    "computation_device": "cuda",
}
pipe = ZImagePipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
        ModelConfig(model_id="Tongyi-MAI/Z-Image", origin_file_pattern="transformer/*.safetensors", **vram_config),
        ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="text_encoder/*.safetensors"),
        ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
        ModelConfig(model_id="DiffSynth-Studio/General-Image-Encoders", origin_file_pattern="SigLIP2-G384/model.safetensors"),
        ModelConfig(model_id="DiffSynth-Studio/General-Image-Encoders", origin_file_pattern="DINOv3-7B/model.safetensors"),
    ],
    tokenizer_config=ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="tokenizer/"),
)
lora_path = snapshot_download(model_id="diffsynth-i2L-gallery/Z-Image-ancient_chinese-character_illustration-ink_wash-1772082134.940298")
pipe.load_lora(pipe.dit, f"{lora_path}/model.safetensors")
image = pipe("中国古风人物插画，身着华丽传统服饰（如宽袖长袍、铠甲、襦裙），头戴精致冠饰或发簪，动态飘逸的衣带与背景水墨飞溅效果，角色姿态优雅或威武，包含文臣、武将、仕女等形象，色彩浓烈典雅，水彩与工笔结合风格", seed=0, height=1024, width=1024, num_inference_steps=30, cfg_scale=4.0, sigma_shift=8.0)
image.save("image.jpg")
```


## 相关链接
- i2L 模型：https://modelscope.cn/models/DiffSynth-Studio/Z-Image-i2L
- 代码仓库：https://github.com/modelscope/DiffSynth-Studio

## License

Apache-2.0