---
tags:
- lora
- diffusers
- template:diffusion-lora
- Image-to-Image
widget:
- output:
    url: images/edited_117.png
  text: Convert this image into 3D Chibi Style
- output:
    url: images/edited_126.png
  text: Convert this image into 3D Chibi Style
- output:
    url: images/edited_031.png
  text: Convert this image into 3D Chibi Style
base_model: Qwen/Qwen-Image-Edit-2509
instance_prompt: 3D Chibi Style
license: apache-2.0
datasets:
- showlab/OmniConsistency
pipeline_tag: image-to-image
---
# Qwen-Edit-3DChibi-LoRA

<Gallery />

## Model description 
This is a Low-Rank Adaptation (LoRA) checkpoint trained on the powerful Qwen-Image-Edit-2509 base model. It specializes in generating high-quality, highly detailed 3D Chibi Style images.


## Inference Example

```python
import torch
from diffusers import QwenImageEditPlusPipeline
from diffusers.utils import load_image

pipeline = QwenImageEditPlusPipeline.from_pretrained(
    "Qwen/Qwen-Image-Edit-2509",
    torch_dtype=torch.bfloat16
)
pipeline.load_lora_weights(
    "rsshekhawat/Qwen-Edit-3DChibi-LoRA", 
    weight_name="qwen_3d_chibi_lora_v1_000000820.safetensors"
)
pipeline.enable_sequential_cpu_offload()
image = load_image("Image.png").convert("RGB")

generator = torch.Generator(device="cuda").manual_seed(42)

prompt = "Convert this image into 3D Chibi Style"
image = pipeline(
    image=image, 
    prompt=prompt, 
    negative_prompt="",
    height=1024, 
    width=1024, 
    num_inference_steps=25,
    true_cfg_scale=5.0, 
    generator=generator
).images[0]
image.save("Edited_Image.png")
```

## Trigger words

You should use `3D Chibi Style` to trigger the image generation.


## Download model


[Download](/rsshekhawat/Qwen-Edit-3DChibi-LoRA/tree/main) them in the Files & versions tab.