Qwen2.1_Anime_consistencyOverview This LoRA is designed to enhance character consistency during anime-style image editing. It was primarily fine-tuned on character model sheets (4-view references) and a variety of facial expression edits.⚠️ Experimental Warning Please note that this LoRA is currently in an experimental phase. It was primarily developed to test and benchmark the optimal training parameters for the Qwen Image 2.1 architecture. As a result, specific editing outcomes, stability, and overall quality are not guaranteed.Recommended to be used for testing and community research purposes.

Qwen2.1_Anime_consistency

Qwen2.1_Anime_consistency.safetensors

v1.0


# Qwen2.1_动漫一致性

## 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-2.1](https://modelscope.cn/models/Qwen/Qwen-Image-2.1)
* 训练代码：[DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio)
* 训练数据量：69
* 总训练步数：5000
* 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_21 import QwenImage21Pipeline, ModelConfig
import torch

pipe = QwenImage21Pipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
        ModelConfig(model_id="Qwen/Qwen-Image-2.1", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"),
        ModelConfig(model_id="Qwen/Qwen-Image-2.1", origin_file_pattern="text_encoder/model*.safetensors"),
        ModelConfig(model_id="Qwen/Qwen-Image-2.1", origin_file_pattern="vae/diffusion_pytorch_model*.safetensors"),
    ],
    processor_config=ModelConfig(model_id="Qwen/Qwen-Image-2.1", origin_file_pattern="processor/"),
)
pipe.load_lora(pipe.dit, ModelConfig(model_id="zhouwenbin1994/Qwen2.1_Anime_consistency", origin_file_pattern="Qwen2.1_Anime_consistency_c1-st5000.safetensors"))

prompt = "a cat"
image = pipe(prompt, seed=0, num_inference_steps=50)
image.save("image.png")
```


Files with SHA256: 0c171eb802ea8051b511f2d93c1743eeadd030316255aa98fa65d40809366752