Qwen-Image-Edit-2509_clear

Qwen-Image-Edit-2509_clear

• Guide (External site): English | Japanese
• Civitai
• Qwen-Image-Edit-2511_clear
• qwen_image_clear_vae

<div style="display: flex; justify-content: center; align-items: center; gap: 2em;"> <div> <img src="./images/Qwen-Image-Edit-2509_clear_BF16_upscale_photoreal.png" alt="White Blazer Lady" width="400" height="400"> </div> <div> <img src="./images/Qwen-Image-Edit-2509_clear_BF16_upscale_anime.png" alt="Anime Kimono Girl" width="400" height="400"> </div> </div>

A fine-tuned version of Qwen-Image-Edit-2509 model, designed to produce clearer and more vibrant outputs.

Compared to Qwen Image Edit 2509 (Original)

<div style="display: flex; justify-content: center; align-items: center; gap: 2em;"> <div> <img src="./images/Qwen-Image-Edit-2509_clear_image1.png" alt="Qwen-Image-Edit-2509_clear_image1" width="400" height="400"> </div> <div> <img src="./images/Qwen-Image-Edit-2509_original_image1.png" alt="Qwen-Image-Edit-2509_original_image1" width="400" height="400"> </div> </div> <p style="text-align:center;">Qwen-Image-Edit-2509_clear | Qwen-Image-Edit-2509 (Original)</p> <div style="display: flex; justify-content: center; align-items: center; gap: 2em;"> <div> <img src="./images/Qwen-Image-Edit-2509_clear_image2.png" alt="Qwen-Image-Edit-2509_clear_image2" width="400" height="400"> </div> <div> <img src="./images/Qwen-Image-Edit-2509_original_image2.png" alt="Qwen-Image-Edit-2509_original_image2" width="400" height="400"> </div> </div> <div style="text-align: center; margin-left: auto; margin-right: auto; width: 800px; max-width: 90%;"> <img src="./images/Qwen-Image-Edit-2509_clear_compare2_close_up.png" alt="Qwen-Image-Edit-2509_clear_compare2_close_up" width="800" height="auto"> </div>

Compared to the original, this model generates illustrations with higher contrast, richer colors, and more refined details.

---

Compared to Google Nano Banana

Restore a black-and-white photo (Original: Audrey Hepburn's public domain photo)

<div style="display: flex; justify-content: center; align-items: center; gap: 2em;"> <div> <img src="./images/Qwen-Image-Edit-2509_clear_color_restore.png" alt="Qwen-Image-Edit-2509_clear_color_restore" width="400" height="566"> </div> <div> <img src="./images/nano-banana_color_restre.png" alt="nano-banana_color_restre" width="400" height="566"> </div> </div> <p style="text-align:center;">Qwen-Image-Edit-2509_clear | nano-banana</p>

Anime Illustration

<div style="display: flex; justify-content: center; align-items: center; gap: 2em;"> <div> <img src="./images/Qwen-Image-Edit-2509_anime.png" alt="Qwen-Image-Edit-2509_anime" width="400" height="566"> </div> <div> <img src="./images/nano-banana_anime.png" alt="nano-banana_anime" width="400" height="566"> </div> </div>

Google nano-banana excels in prompt understanding and illustration variation, but Qwen-Image-Edit-2509_clear is superior when it comes to photorealistic texture rendering.

---

Workflow

Text to Image

<div style="text-align: center; margin-left: auto; margin-right: auto; width: 800px; max-width: 90%;"> <img src="./images/Qwen-Image-Edit-2509_clear_t2i_20251121.png" alt="Qwen-Image-Edit-2509_clear_t2i_workflow" width="800"> </div> <p style="text-align:center;">This PNG image contains a ComfyUI workflow.</p>

Image to Image

<div style="text-align: center; margin-left: auto; margin-right: auto; width: 800px; max-width: 90%;"> <img src="./images/Qwen-Image-Edit-2509_clear_i2i_20251121.png" alt="Qwen-Image-Edit-2509_clear_i2i_workflow" width="800"> </div>

---

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:

• 4x-SwinIR-L_GAN
• 4x_NMKD-Superscale-SP_178000_G

LoRAs

Qwen-Image-Edit-2509_clear model is only a fine-tuned version of Qwen-Image-Edit-2509, we believe that LoRAs designed for Qwen-Image-Edit-2509 should still be effective.

---

Tips (External site)

• ComfyUI VRAM management: English | Japanese
• Compare BF16, FP8, GGUF in Flux.1: English | Japanese
• Steps and Scheduler: English | Japanese
• Image Editing AI models: English | Japanese

---

License

• Apache-2.0