import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("hewei3/qwen-image-dodge_burn", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]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:
Left: Basic Right: Retouched
Left: Basic Right: Retouched
- Downloads last month
- 1
Model tree for hewei3/qwen-image-dodge_burn
Base model
Qwen/Qwen-Image