recraft-ai/recraft-v3 ❓📝 → 🖼️

⭐ Official ▶️ 7.6M runs 📅 Oct 2024 ⚙️ Cog 0.16.8 📄 Paper ⚖️ License

graphic-design text-in-image text-to-image typography

About

Recraft V3 (code-named red_panda) is a text-to-image model with the ability to generate long texts, and images in a wide list of styles. As of today, it is SOTA in image generation, proven by the Text-to-Image Benchmark by Artificial Analysis

Example Output

Prompt:

"a wildlife photography photo of a red panda using a laptop in a snowy forest"

Output

Performance Metrics

8.82s Prediction Time

8.83s Total Time

1 Images

All Input Parameters

{
  "size": "1365x1024",
  "style": "any",
  "prompt": "a wildlife photography photo of a red panda using a laptop in a snowy forest"
}

Input Parameters

size Default: 1024x1024: Width and height of the generated image. Size is ignored if an aspect ratio is set.
style Default: any: Style of the generated image.
prompt (required) Type: string: Text prompt for image generation
aspect_ratio Default: Not set: Aspect ratio of the generated image

Output Schema

Output

Type: string • Format: uri

Example Execution Logs

Running prediction... 
Starting image generation...
Generated image in 8.53sec

Version Details

Version ID: 9507e61ddace8b3a238371b17a61be203747c5081ea6070fecd3c40d27318922
Version Created: November 7, 2025

Run on Replicate →