---
title: DukeG_Qwen_Light_And_Shadow_Public
canonical_url: "https://www.modelscope.cn/models/fireicewolf/DukeG_Qwen_Light_And_Shadow_Public"
md_url: "https://www.modelscope.cn/models/fireicewolf/DukeG_Qwen_Light_And_Shadow_Public.md"
repository: fireicewolf/DukeG_Qwen_Light_And_Shadow_Public
chinese_name: "DukeG 千问光影"
last_updated: 2026-01-22
license: "Apache License 2.0"
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - Qwen/Qwen-Image
base_model_relation: adapter
parameters: 943.7M
tensor_type:
  - BF16
library_name:
  - lora
  - safetensors
supports_inference: txt2img
downloads: 243
stars: 13
tags:
  - LoRA
  - text-to-image
  - "光影"
---

# DukeG_Qwen_Light_And_Shadow_Public

> DukeG_Qwen_Light_And_Shadow_Public - fireicewolf 在 ModelScope 开源的模型。此模型旨在改善千问模型的光影效果。

fireicewolf/DukeG_Qwen_Light_And_Shadow_Public 是 ModelScope 魔搭社区上的 943.7M 参数text-to-image-synthesis模型，采用 Apache License 2.0 许可，基于 Qwen/Qwen-Image 构建，并支持在线推理（txt2img）。

- **Repository**: fireicewolf/DukeG_Qwen_Light_And_Shadow_Public
- **License**: Apache License 2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 943.7M
- **Base model**: Qwen/Qwen-Image
- **Online inference**: txt2img
- **Tags**: LoRA, text-to-image, 光影
- **Downloads**: 243
- **Stars**: 13
- **Last updated**: 2026-01-22

Source: https://www.modelscope.cn/models/fireicewolf/DukeG_Qwen_Light_And_Shadow_Public

---

### [2512版本已发布](https://www.modelscope.cn/models/fireicewolf/DukeG_Qwen_Light_And_Shadow_2512_Public)
### 此LoRA旨在为Qwen Image带来更加自然的光影效果。
### 推荐权重0.4-0.6。