Reprinted from Hugging Face

license: apache-2.0 language:

• en base_model:
• Qwen/Qwen-Image-Edit-2511 tags:
• image-generation
• lora
• Qwen-Image pipeline_tag: image-to-image library_name: diffusers widget:
• text: >- Upscale this picture to 4K resolution. output: url: result/result1.png
• text: >- Upscale this picture to 4K resolution. output: url: result/result2.png
• text: >- Upscale this picture to 4K resolution.
  output: url: result/result3.png

valiantcat Qwen-Image-Edit-2511 LoRA

Model Card for Model ID

This is a model for high-definition image upscaling, trained on Qwen/Qwen-Image-Edit-2511. It is mainly used for losslessly enlarging images to approximately 2K resolution. Intended for use in ComfyUI.

Direct Use

from diffusers import QwenImageEditPipeline
import torch
from PIL import Image

# Load the pipeline
pipeline = QwenImageEditPipeline.from_pretrained("Qwen/Qwen-Image-Edit-2511")
pipeline.to(torch.bfloat16)
pipeline.to("cuda")

# Load trained LoRA weights for in-scene editing
pipeline.load_lora_weights("valiantcat/Qwen-Image-Edit-2511-Upscale2K", weight_name="qwen_image_edit_2511_upscale.safetensors")

# Load input image
image = Image.open("./result/test.jpg").convert("RGB")

# Define in-scene editing prompt
prompt = "Upscale this picture to 4K resolution."

# Generate edited image with enhanced scene understanding
inputs = {
    "image": image,
    "prompt": prompt,
    "generator": torch.manual_seed(12345),
    "true_cfg_scale": 4.0,
    "negative_prompt": " ",
    "num_inference_steps": 50,
}

with torch.inference_mode():
    output = pipeline(**inputs)
    output_image = output.images[0]
    output_image.save("edited_image.png")

Trigger phrase

Upscale this picture to 4K resolution.

There is no fixed trigger word. Specific prompts require further testing.

Download model

Weights for this model are available in Safetensors format.

Download

Training at Chongqing Valiant Cat

This model was trained by the AI Laboratory of Chongqing Valiant Cat Technology Co., Ltd. (https://vvicat.com/). Business inquiries and collaborations are welcome.