prunaai/sdxl-lightning 🔢📝❓ → 🖼️

▶️ 3.3K runs 📅 Mar 2025 ⚙️ Cog 0.14.7
fast-inference low-latency sdxl sdxl-lightning text-to-image

About

This is the fastest sdxl-lightning endpoint in the world on A100, contact us for more at pruna.ai

Example Output

Prompt:

"self-portrait of a woman, lightning in the background"

Output

Example output

Performance Metrics

0.41s Prediction Time
0.41s Total Time
All Input Parameters 
{
  "seed": 42,
  "prompt": "self-portrait of a woman, lightning in the background",
  "num_images": 1,
  "image_width": 1024,
  "image_height": 1024,
  "output_format": "jpg",
  "guidance_scale": 0,
  "output_quality": 80,
  "num_inference_steps": 4
}
Input Parameters
seed Type: integerDefault: 42
Seed
prompt (required) Type: string
Prompt
num_images Type: integerDefault: 1
Number of images to generate
image_width Type: integerDefault: 1024
Image width
image_height Type: integerDefault: 1024
Image height
output_format Default: jpg
Output format
guidance_scale Type: numberDefault: 0
Guidance scale
output_quality Type: integerDefault: 80Range: 1 - 100
Output quality (for jpg and webp)
num_inference_steps Type: integerDefault: 4
Number of inference steps
Output Schema

Output

Type: string • Format: uri

Example Execution Logs 
0%|          | 0/4 [00:00<?, ?it/s]
100%|██████████| 4/4 [00:00<00:00, 30.27it/s]
Version Details
Version ID
123d4264aec4d1c81d8bf142e0d90d6fd4c346f1a869406019f6d1653882d7c3
Version Created
June 10, 2025
Run on Replicate →