bria/image-3.2 🔢📝❓✓ → 🖼️

⭐ Official ▶️ 27.9K runs 📅 Jul 2025 ⚙️ Cog 0.16.7 📄 Paper ⚖️ License

licensed-data text-rendering text-to-image

About

Commercial-ready, trained entirely on licensed data, text-to-image model. With only 4B parameters provides exceptional aesthetics and text rendering. Evaluated to be on par to other leading models in the market

Example Output

Prompt:

"Praying mantis on a wet leaf"

Output

Performance Metrics

8.74s Prediction Time

8.75s Total Time

All Input Parameters

{
  "seed": 738027405,
  "prompt": "Praying mantis on a wet leaf",
  "num_results": 1,
  "aspect_ratio": "1:1",
  "enhance_image": false,
  "prompt_enhancement": false
}

Input Parameters

seed Type: integer: Random seed. Set for reproducible generation
prompt (required) Type: string: Text prompt for image generation
aspect_ratio Default: 1:1: Aspect ratio for expansion.
enhance_image Type: booleanDefault: false: Enhance image details and clarity
guidance_scale Type: number: Guidance scale (1-10)
negative_prompt Type: string: Negative prompt for image generation
prompt_enhancement Type: booleanDefault: false: Enhance prompt for more creative output

Output Schema

Output

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

Example Execution Logs

Using seed: 738027405
Generating... (model_version=3.2)
Generated 1 image(s) in 8.4sec
Downloading 1262047 bytes
Downloaded 1.20MB in 0.09sec

Version Details

Version ID: 20c9aac6ff4fb6aca8b404ac4c010dae1abfda825a96c37554d833f0238d892e
Version Created: October 3, 2025

Run on Replicate →