hewei3/qwen-image-dodge_burn
Introduction
Qwen-Image-Dodge_Burn is a fine-tuned model based on Qwen-Image-Layered, focusing on dodge and burn retouching for photography.
Requirements
- At least one A100 GPU is required for running the inference pipeline.
- Dependencies are listed in
./requirements.txt
Examples
Detailed inference pipeline can refer to https://github.com/jeremywei201-tech/qwen-image-dodge_burn/blob/main/README.md
Comparison of basic and retouched image:
<p> <img src="https://raw.githubusercontent.com/jeremywei201-tech/qwen-image-dodgeburn/main/02738basic.png" width="48%" /> <img src="https://raw.githubusercontent.com/jeremywei201-tech/qwen-image-dodgeburn/main/qwendnboutput/02738dnb_retouch.png" width="48%" /> </p> <p> <em>Left: Basic Right: Retouched </em> </p>
<p> <img src="https://raw.githubusercontent.com/jeremywei201-tech/qwen-image-dodgeburn/main/08002basic.png" width="48%" /> <img src="https://raw.githubusercontent.com/jeremywei201-tech/qwen-image-dodgeburn/main/qwendnboutput/08002dnb_retouch.png" width="48%" /> </p> <p> <em>Left: Basic Right: Retouched </em> </p>
