Text-to-Image
Diffusers
lora
stable-diffusion
cosplay
image-editing
ai-image-generation
template:diffusion-lora
Instructions to use joyfox/Qwen-Image-Edit-Cosplay with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use joyfox/Qwen-Image-Edit-Cosplay with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Qwen/Qwen-Image-Edit-2509", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("joyfox/Qwen-Image-Edit-Cosplay") prompt = "-" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Update README.md
Browse files
README.md
CHANGED
|
@@ -3,6 +3,10 @@ tags:
|
|
| 3 |
- text-to-image
|
| 4 |
- lora
|
| 5 |
- diffusers
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
- template:diffusion-lora
|
| 7 |
widget:
|
| 8 |
- output:
|
|
@@ -21,31 +25,40 @@ base_model: Qwen/Qwen-Image-Edit-2509
|
|
| 21 |
instance_prompt: 把图2中动漫人物中的发型,服饰和装扮道具迁移到图1的真实人物,图1真实人物保持高度人脸一致性
|
| 22 |
license: apache-2.0
|
| 23 |
---
|
| 24 |
-
|
|
|
|
| 25 |
|
| 26 |
<Gallery />
|
| 27 |
|
| 28 |
## 🎨 效果对比展示
|
| 29 |
|
| 30 |
-
|
| 31 |
-
| 控制图1 | 控制图2 | 生成结果 |
|
| 32 |
|:---:|:---:|:---:|
|
| 33 |
|  |  |  |
|
| 34 |
|  |  |  |
|
| 35 |
|  |  |  |
|
| 36 |
|  |  |  |
|
| 37 |
|
| 38 |
-
##
|
| 39 |
|
| 40 |
-
|
| 41 |
-
Let the person wear the anime character cloth and decoration.
|
| 42 |
|
| 43 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
|
| 45 |
-
|
| 46 |
|
|
|
|
|
|
|
| 47 |
|
| 48 |
-
##
|
| 49 |
|
|
|
|
| 50 |
|
| 51 |
-
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
- text-to-image
|
| 4 |
- lora
|
| 5 |
- diffusers
|
| 6 |
+
- stable-diffusion
|
| 7 |
+
- cosplay
|
| 8 |
+
- image-editing
|
| 9 |
+
- ai-image-generation
|
| 10 |
- template:diffusion-lora
|
| 11 |
widget:
|
| 12 |
- output:
|
|
|
|
| 25 |
instance_prompt: 把图2中动漫人物中的发型,服饰和装扮道具迁移到图1的真实人物,图1真实人物保持高度人脸一致性
|
| 26 |
license: apache-2.0
|
| 27 |
---
|
| 28 |
+
|
| 29 |
+
# Qwen-Image-Edit-Cosplay LoRA:动漫角色装扮迁移模型
|
| 30 |
|
| 31 |
<Gallery />
|
| 32 |
|
| 33 |
## 🎨 效果对比展示
|
| 34 |
|
| 35 |
+
| 真实人物原图 | 动漫角色参考 | AI生成效果 |
|
|
|
|
| 36 |
|:---:|:---:|:---:|
|
| 37 |
|  |  |  |
|
| 38 |
|  |  |  |
|
| 39 |
|  |  |  |
|
| 40 |
|  |  |  |
|
| 41 |
|
| 42 |
+
## 模型描述
|
| 43 |
|
| 44 |
+
Qwen-Image-Edit-Cosplay LoRA 是一个基于Qwen-Image-Edit-2509图像编辑模型的微调版本,专门用于动漫角色装扮迁移任务。该模型能够将动漫人物的发型、服饰和装饰道具精准地迁移到真实人物图像上,同时保持原始人物的面部特征高度一致。
|
|
|
|
| 45 |
|
| 46 |
+
**核心功能特点:**
|
| 47 |
+
- 实现从动漫到真实人物的装扮风格转换
|
| 48 |
+
- 保持原始人脸识别特征不变
|
| 49 |
+
- 支持发型、服装、配饰等多种元素的迁移
|
| 50 |
+
- 基于Qwen-Image-Edit-2509基础模型优化
|
| 51 |
|
| 52 |
+
## 触发提示词
|
| 53 |
|
| 54 |
+
使用以下中文提示词来激活图像生成功能:
|
| 55 |
+
`把图2中动漫人物中的发型,服饰和装扮道具迁移到图1的真实人物,图1真实人物保持高度人脸一致性`
|
| 56 |
|
| 57 |
+
## 模型下载与使用
|
| 58 |
|
| 59 |
+
您可以在 [模型文件页面](/valiantcat/Qwen-Image-Edit-Cosplay/tree/main) 下载并使用这个LoRA模型。该模型兼容主流的diffusers库,便于集成到现有的AI图像生成工作流中。
|
| 60 |
|
| 61 |
+
**许可证:** Apache-2.0
|
| 62 |
+
|
| 63 |
+
---
|
| 64 |
+
*适用于角色扮演、创意设计和图像编辑等场景*
|