qwen-edit-apps/qwen-image-edit-plus-lora-upscale 🔢🖼️📝✓❓ → 🖼️

⭐ Official ▶️ 1.1K runs 📅 Nov 2025 ⚙️ Cog 0.16.9 📄 Paper ⚖️ License

image-restoration image-upscaling

About

Upscale – Detail-loving upscale/restore pass that sharpens textures and color fidelity with the Upscale LoRA.

Example Output

Prompt:

"Enhance image quality, sharpen fine textures, restore natural colors and contrast"

Output

Performance Metrics

37.87s Prediction Time

37.88s Total Time

All Input Parameters

{
  "image": "https://replicate.delivery/pbxt/O3fhIq7IY5LbySLNQDgtQ4Kg30Ij8hXra6kCAwQ7z0gOHc5r/image.png",
  "prompt": "Enhance image quality, sharpen fine textures, restore natural colors and contrast",
  "lora_scale": 1,
  "aspect_ratio": "match_input_image",
  "lora_weights": "",
  "output_format": "webp",
  "output_quality": 95,
  "true_guidance_scale": 1
}

Input Parameters

seed Type: integer: Random seed. Set for reproducible generation.
image (required) Type: string: Image file uploaded to Cog (jpeg, png, gif, or webp).
prompt Type: stringDefault: Enhance image quality, sharpen fine textures, restore natural colors and contrast: Prompt hint: `Enhance image quality, sharpen fine textures, restore natural colors` and add a quick scene description so the LoRA knows what details to recover.
go_fast Type: boolean: If num_inference_steps is omitted, true runs the 8-step Lightning preset and false runs the 40-step detailed preset.
lora_scale Type: numberRange: 0 - 4: Strength applied to the selected LoRA. Leave blank for the proxy default.
aspect_ratio Default: match_input_image: Aspect ratio for the generated image
lora_weights Type: stringDefault:: LoRA weights to apply. Leave blank to use the proxy's default adapter.
output_format Default: webp: Format of the output images.
output_quality Type: integerDefault: 95Range: 0 - 100: Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs.
num_inference_steps Type: integerRange: 1 - 40: Explicit denoising step count (1-40). Leave blank to use the go_fast presets (fast = 8 steps, slow = 40 steps).
true_guidance_scale Type: numberDefault: 1Range: 0 - 10: True classifier-free guidance scale passed to the pipeline.
disable_safety_checker Type: booleanDefault: false: Disable safety checker for generated images.

Output Schema

Output

Type: array • Items Type: string • Items Format: uri

Example Execution Logs

Proxy call -> model=qwen/qwen-image-edit-plus-lora, adapter=vafipas663/Qwen-Edit-2509-Upscale-LoRA, scale=1.0

Version Details

Version ID: 23c6dcef1ae2b2a897b37a0f58aac044882c44f711de73225c180e6d52841ae5
Version Created: November 14, 2025

Run on Replicate →