qwen/qwen-image-2512 🔢🖼️📝✓❓ → 🖼️

⭐ Official ▶️ 127.6K runs 📅 Dec 2025 ⚙️ Cog 0.16.9 📄 Paper ⚖️ License

About

Qwen Image 2512 is an improved version of Qwen Image with more realistic human generation, finer textures, and stronger text rendering

Example Output

Prompt:

"This is a modern slide with a deep blue gradient background. The title is "Qwen Image 2512 Major Release" in white sans serif bold font.
On the left a female portrait lacks detail. On the right a highly realistic young woman's portrait close to photographic quality. An arrow links the images labeled "2512 Quality Upgrade"
Faint glow effects besides the arrow enhance dynamism
Text below reads: "More realistic texture, finer details, enhanced text rendering""

Output

Performance Metrics

6.91s Prediction Time

6.92s Total Time

All Input Parameters

{
  "prompt": "This is a modern slide with a deep blue gradient background. The title is \"Qwen Image 2512 Major Release\" in white sans serif bold font. \nOn the left a female portrait lacks detail. On the right a highly realistic young woman's portrait close to photographic quality. An arrow links the images labeled \"2512 Quality Upgrade\" \nFaint glow effects besides the arrow enhance dynamism\nText below reads: \"More realistic texture, finer details, enhanced text rendering\"",
  "go_fast": true,
  "guidance": 4,
  "strength": 0.8,
  "aspect_ratio": "16:9",
  "output_format": "webp",
  "output_quality": 95,
  "negative_prompt": " ",
  "num_inference_steps": 40
}

Input Parameters

seed Type: integer: Random seed. Set for reproducible generation.
image Type: string: Input image for image2image generation. The aspect ratio of your output will match this image.
width Type: integerRange: 256 - 2048: Width of the generated image. Only used when aspect_ratio=custom. Must be a multiple of 16.
height Type: integerRange: 256 - 2048: Height of the generated image. Only used when aspect_ratio=custom. Must be a multiple of 16.
prompt (required) Type: string: Text prompt for image generation.
go_fast Type: booleanDefault: true: Use the model with additional optimizations for faster generation.
guidance Type: numberDefault: 4Range: 0 - 10: Guidance for generated image. Use higher values for stronger prompt adherence.
strength Type: numberDefault: 0.8Range: 0 - 1: Strength for image2image generation. 1.0 corresponds to full destruction of information in image.
aspect_ratio Default: 16:9: Aspect ratio for the generated image.
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.
negative_prompt Type: stringDefault:: Negative prompt for image generation.
num_inference_steps Type: integerDefault: 40Range: 20 - 50: Number of denoising steps. Use less steps for faster generation.
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

Using seed: 399179
Generation took 6.77 seconds
Total safe images: 1 out of 1

Version Details

Version ID: 47c060e80055269a615f9636df2d51fd50239dc439f5ecde465a7d513a0abda6
Version Created: December 31, 2025

Run on Replicate →