---
license: apache-2.0
language:
- en
base_model:
- Qwen/Qwen-Image-Edit-2509
tags:
- image-generation
- lora
- Qwen-Image
pipeline_tag: image-to-image
library_name: diffusers
widget:
- text: >-
    保持图3的图片和视角不改变，让图1和图2中的人在图三的地铁上的座位坐着一只手抓着扶手上靠着拥抱着激情亲吻 
  output:
    url: result/result1.png
- text: >-
    保持图3的图片和视角不改变，让图1和图2中的人在图三的电梯中的右边角落站着拥抱着激情亲吻
  output:
    url: result/result2.png
- text: >-
    保持图3的图片和视角不改变，让图1和图2中的人在图三的钢琴边上靠着拥抱着激情亲吻  
  output:
    url: result/result3.png
- text: >-
    保持图3的图片和视角不改变，让图1和图2中的人在图三的台球桌上靠着拥抱着激情亲吻 
  output:
    url: result/result4.png
- text: >-
    保持图3的图片和视角不改变，让图1和图2中的人在图三的洗衣房上靠着洗衣机拥抱着激情亲吻 
  output:
    url: result/result5.png
- text: >-
    保持图3的图片和视角不改变，让图1和图2中的人在图三的马路上站立拥抱着激情亲吻  
  output:
    url: result/result6.png
---
# starsfriday Qwen-Image-Edit-2509 LoRA

<Gallery />

## Model Card for Model ID

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

This is a model for generation of embrace and kiss images of the specified person and the specified scene, trained on ```Qwen/Qwen-Image-Edit-2509```, and it is mainly used to generate an image of a hug and kiss in the current scene based on two uploaded character pictures and one scene picture, while maintaining consistency between the characters and the scene.For use in ```ComfyUI```.

<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-Edit-2509-Passionate-kiss/blob/main/Qwen-Edit-2509-LORA.json" style="color: #0366d6; text-decoration: none;">Comfy's Qwen/Qwen-Image-Edit-2509 workflow</a>. The main modification is adding a Qwen/Qwen-Image-Edit-2509 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 QwenImageEditPipeline
import torch
from PIL import Image

# Load the pipeline
pipeline = QwenImageEditPipeline.from_pretrained("Qwen/Qwen-Image-Edit-2509")
pipeline.to(torch.bfloat16)
pipeline.to("cuda")

# Load trained LoRA weights for in-scene editing
pipeline.load_lora_weights("starsfriday/Qwen-Image-Edit-2509-Passionate-kiss", weight_name="qwen_image_edit_2509_Passionate-kiss.safetensors")

# Load input image
image = Image.open("./result/test.jpg").convert("RGB")

# Define in-scene editing prompt
prompt = "Make a shot in the same scene of the left hand securing the edge of the cutting board while the right hand tilts it, causing the chopped tomatoes to slide off into the pan, camera angle shifts slightly to the left to center more on the pan."

# Generate edited image with enhanced scene understanding
inputs = {
    "image": image,
    "prompt": prompt,
    "generator": torch.manual_seed(12345),
    "true_cfg_scale": 4.0,
    "negative_prompt": " ",
    "num_inference_steps": 50,
}

with torch.inference_mode():
    output = pipeline(**inputs)
    output_image = output.images[0]
    output_image.save("edited_image.png")


```

## Trigger phrase

```保持图3的图片和视角不改变，让图1和图2中的人在图三的马路上站立拥抱着激情亲吻.```

There is no fixed trigger word. The specific removal prompt needs to be tested more

## Download model

Weights for this model are available in Safetensors format.

[Download](https://huggingface.co/starsfriday/Qwen-Image-Edit-2509-Passionate-kiss)

## 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