prunaai/flux-fast 🔢📝❓ → 🖼️

⭐ Official ▶️ 35.5M runs 📅 May 2025 ⚙️ Cog 0.16.0 🔗 GitHub 📄 Paper ⚖️ License
flux low-latency text-to-image

About

This is the fastest Flux endpoint in the world.

Example Output

Prompt:

"a man staring into the sunset"

Output

Example output

Performance Metrics

1.35s Prediction Time
2.44s Total Time
All Input Parameters 
{
  "seed": -1,
  "prompt": "a man staring into the sunset",
  "guidance": 3.5,
  "image_size": 1024,
  "speed_mode": "Extra Juiced 🔥 (more speed)",
  "aspect_ratio": "1:1",
  "output_format": "jpg",
  "output_quality": 80,
  "num_inference_steps": 28
}
Input Parameters
seed Type: integerDefault: -1
Seed
prompt (required) Type: string
Prompt
guidance Type: numberDefault: 3.5
Guidance scale
image_size Type: integerDefault: 1024
Base image size (longest side)
speed_mode Default: Extra Juiced 🔥 (more speed)
Speed optimization level
aspect_ratio Default: 1:1
Aspect ratio of the output image
output_format Default: jpg
Output format
output_quality Type: integerDefault: 80Range: 1 - 100
Output quality (for jpg and webp)
num_inference_steps Type: integerDefault: 28
Number of inference steps
Output Schema

Output

Type: string • Format: uri

Example Execution Logs 
Running prediction with args: ['prompt', 'negative_prompt', 'height', 'width', 'guidance_scale', 'num_inference_steps', 'generator']
Inference took 1.34 seconds
Version Details
Version ID
4f22c6cd75e0f95f12f55d1616a4d163e9166087ed4979f5cecc40418a522703
Version Created
November 8, 2025
Run on Replicate →