Qwen-Image-Edit-2509_clear

tumbnail_image_anime
tumbnail_image_photoreal

A fine-tuned version of Qwen-Image-Edit-2511 model, designed to produce clearer and more vibrant outputs.

Compared to Qwen-Image-Edit-2511, 2509

compare_photoreal
compare_anime

Compared to the original, Qwen-Image-Edit-2511_clear generates illustrations with higher contrast and richer colors.

Qwen-Image_clear_vae is adjusted to produce healthier skin tones by enhancing the red spectrum. If you’re trying out the Qwen-Image-Edit-2511_clear model, we recommend using this VAE alongside it.


Compare to Nano Banana Pro, GPT-Image-1.5

View from above

Image_Edit_AI_compare_photoreal

Change to Japanese anime illustration

Image_Edit_AI_compare_anime

Focusing on color, both Nano Banana Pro and GPT-Image-1.5 tend toward muted, sepia-like tones, whereas Qwen-Image-Edit-2511_clear maintains vibrant colors, creating more convincing and lively illustrations.


Workflow

Text to Image

text_to_image_workflow

This PNG image contains a ComfyUI workflow.

Image to Image

image_to_image_workflow

Recommended Settings

General

  • CFG scale: 2.5
  • Sampler:
    • euler (Speed)
    • heunpp2 (Quality)
  • Scheduler: beta
  • Steps: 14 (12-24)
  • ModelSamplingAuraFlow: shift 4 (3-6)

Upscaler

your choice, examples:


Tips (External site)


License

Downloads last month
2,282
GGUF
Model size
20B params
Architecture
qwen_image
Hardware compatibility
Log In to add your hardware

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support