---
title: Qwen-Image-EVA-LoRA
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/Qwen-Image-EVA-LoRA"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/Qwen-Image-EVA-LoRA.md"
repository: AI-ModelScope/Qwen-Image-EVA-LoRA
last_updated: 2026-06-17
license: apache-2.0
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - Qwen/Qwen-Image
base_model_relation: adapter
parameters: 94.4M
tensor_type:
  - BF16
library_name:
  - pytorch
  - lora
  - safetensors
frameworks:
  - pytorch
language:
  - en
supports_inference: txt2img
downloads: 129
stars: 1
tags:
  - image-generation
  - lora
  - Qwen-Image
---

# Qwen-Image-EVA-LoRA

> Qwen-Image-EVA-LoRA - AI-ModelScope 在 ModelScope 开源的模型。starsfriday Qwen-Image LoRA

AI-ModelScope/Qwen-Image-EVA-LoRA 是 ModelScope 魔搭社区上的 94.4M 参数text-to-image-synthesis模型，采用 apache-2.0 许可，基于 Qwen/Qwen-Image 构建，并支持在线推理（txt2img）。

- **Repository**: AI-ModelScope/Qwen-Image-EVA-LoRA
- **License**: apache-2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 94.4M
- **Base model**: Qwen/Qwen-Image
- **Online inference**: txt2img
- **Tags**: image-generation, lora, Qwen-Image
- **Downloads**: 129
- **Stars**: 1
- **Last updated**: 2026-06-17

Source: https://www.modelscope.cn/models/AI-ModelScope/Qwen-Image-EVA-LoRA

---

# starsfriday Qwen-Image LoRA

<Gallery />

## Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->

This is a model for Qwen-Image in Portrait generation, trained on ```Qwen/Qwen-Image```, and it is mainly applicable to generating pictures of various Asuka characters from Japanese anime.For use in through the following code and ```ComfyUI```,The workflow files are in the folder of this project.

<div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
  <h2 style="color: #24292e; margin-top: 0;">ComfyUI Workflow</h2>
  <p>This LoRA works with a modified version of <a href="https://huggingface.co/starsfriday/Qwen-Image-EVA-LoRA/blob/main/Workflow-Qwen-Image-LORA.json" style="color: #0366d6; text-decoration: none;">Comfy's Qwen-Image workflow</a>. The main modification is adding a Qwen-Image LoRA node connected to the base model.</p>
  <p>See the Downloads section above for the modified workflow.</p>
</div>

### Direct Use

```
from diffusers import DiffusionPipeline
import torch

model_name = "Qwen/Qwen-Image"

# Load the pipeline
if torch.cuda.is_available():
    torch_dtype = torch.bfloat16
    device = "cuda"
else:
    torch_dtype = torch.float32
    device = "cpu"

pipe = DiffusionPipeline.from_pretrained(model_name, torch_dtype=torch_dtype)
pipe = pipe.to(device)

# Load LoRA weights
pipe.load_lora_weights('starsfriday/Qwen-Image-Shentianyongmei-LoRA/qwen_image_eva.safetensors', adapter_name="lora")

prompt = '''mrx, The image depicts a young female character with long, reddish-brown hair tied in twin tails, wearing a traditional Japanese yukata. She is seated indoors, likely on a tatami mat, enjoying a slice of watermelon. The setting suggests a tranquil environment, possibly a ryokan or a home with Japanese architectural elements such as sliding doors and paper windows. The presence of a lantern indicates it might be late afternoon or early evening. In the background, through the open door, one can see a serene outdoor scene with greenery and a clear sky, which adds to the overall peaceful ambiance of the scene. This image could evoke feelings of relaxation and leisure, often associated with summer holidays in Japan.   '''
negative_prompt =  " "
image = pipe(
    prompt=prompt,
    negative_prompt=negative_prompt,
    width=1024,
    height=1024,
    num_inference_steps=50,
    true_cfg_scale=5,
    generator=torch.Generator(device="cuda").manual_seed(123456)
)
image = image.images[0]

image.save("output.png")
```


## Trigger phrase

```mrx```


## Download model

Weights for this model are available in Safetensors format.

[Download](https://huggingface.co/starsfriday/Qwen-Image-EVA-LoRA)

## Training at Chongqing Valiant Cat

This model was trained by the AI Laboratory of Chongqing Valiant Cat Technology Co., LTD(```https://vvicat.com/```).Business cooperation is welcome
