prunaai/flux.1-dev 🔢📝❓ → 🖼️

▶️ 26.8M runs 📅 May 2025 ⚙️ Cog 0.14.7 🔗 GitHub 📄 Paper ⚖️ License
fast-inference text-to-image

About

This is the fastest Flux Dev endpoint in the world, contact us for more at pruna.ai

Example Output

Prompt:

"black forest gateau cake spelling out the words "FLUX DEV", tasty, food photography, dynamic shot"

Output

Example output

Performance Metrics

0.78s Prediction Time
0.78s Total Time
All Input Parameters 
{
  "seed": -1,
  "prompt": "black forest gateau cake spelling out the words \"FLUX DEV\", tasty, food photography, dynamic shot",
  "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: Juiced 🔥 (default)
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']
  0%|          | 0/28 [00:00<?, ?it/s]
 54%|█████▎    | 15/28 [00:00<00:00, 53.61it/s]
100%|██████████| 28/28 [00:00<00:00, 46.36it/s]
Inference took 0.76 seconds
Version Details
Version ID
b0306d92aa025bb747dc74162f3c27d6ed83798e08e5f8977adf3d859d0536a3
Version Created
July 25, 2025
Run on Replicate →