---
title: AS26818DIAOXINFJ_QW12
canonical_url: "https://www.modelscope.cn/models/AS7033/AS26818DIAOXINFJ_QW12"
md_url: "https://www.modelscope.cn/models/AS7033/AS26818DIAOXINFJ_QW12.md"
repository: AS7033/AS26818DIAOXINFJ_QW12
chinese_name: "调性风景插画_QW12"
last_updated: 2026-08-19
license: "Apache License 2.0"
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - Qwen/Qwen-Image-2512
base_model_relation: adapter
parameters: 2.4B
tensor_type:
  - BF16
library_name:
  - pytorch
  - lora
  - safetensors
supports_inference: txt2img
downloads: 44
stars: 5
tags:
  - LoRA
  - text-to-image
---

# AS26818DIAOXINFJ_QW12

> AS26818DIAOXINFJ_QW12 - AS7033 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。

AS7033/AS26818DIAOXINFJ_QW12 是 ModelScope 魔搭社区上的 2.4B 参数text-to-image-synthesis模型，采用 Apache License 2.0 许可，基于 Qwen/Qwen-Image-2512 构建，并支持在线推理（txt2img）。

- **Repository**: AS7033/AS26818DIAOXINFJ_QW12
- **License**: Apache License 2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 2.4B
- **Base model**: Qwen/Qwen-Image-2512
- **Online inference**: txt2img
- **Tags**: LoRA, text-to-image
- **Downloads**: 44
- **Stars**: 5
- **Last updated**: 2026-08-19

Source: https://www.modelscope.cn/models/AS7033/AS26818DIAOXINFJ_QW12

---

# 调性风景插画_QW12

## 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：[Qwen/Qwen-Image-2512](https://modelscope.cn/models/Qwen/Qwen-Image-2512)
* 训练代码：[DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio)
* 训练数据量：300
* 总训练步数：10000
* 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.qwen_image import QwenImagePipeline, ModelConfig
import torch

pipe = QwenImagePipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
        ModelConfig(model_id="Qwen/Qwen-Image-2512", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"),
        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors"),
        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
    ],
    tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
)
pipe.load_lora(pipe.dit, ModelConfig(model_id="AS7033/AS26818DIAOXINFJ_QW12", origin_file_pattern="AS26818DIAOXINFJ_QW12_c1-st10000.safetensors"))
prompt = "a cat"
image = pipe(prompt)
image.save("image.jpg")
```