valiantcat Qwen-Image-Edit-2511 LoRA

Introduction

valiantcat Qwen-Image-Edit-2511 LoRA is designed for high-definition image magnification. It's trained on Qwen/Qwen-Image-Edit-2511 and primarily helps enlarge images to roughly 2K resolution without losing quality.

How to Use

• Trigger word: No specific trigger word is needed.
• Recommended prompt: Use "Upscale this picture to 4K resolution."
• ComfyUI: This LoRA works with a modified version of ComfyUI's Qwen/Qwen-Image-Edit-2511 workflow. You can find the specific workflow file in the repo's Downloads section.
• Direct Python Use: You can integrate it into your Python scripts using the diffusers library. Load the base QwenImageEditPipeline, then load the LoRA weights. The example code in the repo shows recommended settings for true_cfg_scale (4.0) and num_inference_steps (50).

FAQ

Q: What's the trigger word?

A: No trigger word required.

Q: What does this LoRA do?

A: It's for high-definition magnification, mainly enlarging images to approximately 2K size.

Q: What's the recommended prompt?

A: Use "Upscale this picture to 4K resolution."

Q: How do I use it with ComfyUI?

A: You'll need the modified workflow provided in the repo. Look for Upscale.json in the Downloads section.

Technical Details

• Base model: Qwen/Qwen-Image-Edit-2511
• Training info: Trained by the AI Laboratory of Chongqing Valiant Cat Technology Co., LTD.
• Source: Hugging Face