fofr/qwen-shou-xin 📝✓🔢❓ → 🖼️

▶️ 202 runs 📅 Aug 2025 ⚙️ Cog 0.14.0
fast-prediction image-generation sketch-style stylized-images text-to-image

About

Qwen fine-tuned on Shou Xin's cat sketches

Example Output

Prompt:

"a sketch of a neon cyberpunk using a highlighter, a handwritten caption says "Here's a quick sketch I made with a qwen lora""

Output

Example output

Performance Metrics

8.14s Prediction Time
8.45s Total Time
All Input Parameters 
{
  "prompt": "a sketch of a neon cyberpunk using a highlighter, a handwritten caption says \"Here's a quick sketch I made with a qwen lora\"",
  "go_fast": true,
  "guidance": 4,
  "aspect_ratio": "3:4",
  "output_format": "webp",
  "output_quality": 80,
  "num_inference_steps": 50
}
Input Parameters
prompt (required) Type: string
Prompt for generated image
go_fast Type: booleanDefault: true
Run faster predictions with additional optimizations
guidance Type: numberDefault: 4Range: 0 - 10
Guidance for generated image. Lower values can give more realistic images. Good values to try are 2, 2.5, 3 and 3.5
aspect_ratio Default: 16:9
Aspect ratio for the generated image
output_format Default: webp
Format of the output images
output_quality Type: integerDefault: 80Range: 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: integerDefault: 50Range: 1 - 50
Number of denoising steps. Recommended range is 28-50
disable_safety_checker Type: booleanDefault: false
Disable safety checker for generated images
Output Schema

Output

Type: string • Format: uri

Version Details
Version ID
8291bf62effcb6aa209a3c93064b67a34dd92a20714d32a6bc6081f5eada2697
Version Created
August 18, 2025
Run on Replicate →