prunaai/stable-diffusion-cheetah 🔢📝❓ → 🖼️

▶️ 66.8K runs 📅 Nov 2024 ⚙️ Cog 0.16.9
fast-inference speed-optimized stable-diffusion text-to-image

About

This model is an optimised version of stable-diffusion by stability AI that is 3x faster and 3x cheaper.

Example Output

Prompt:

"a red apple on a table"

Output

Example output

Performance Metrics

0.56s Prediction Time
0.57s Total Time
All Input Parameters 
{
  "seed": -1,
  "prompt": "a red apple on a table",
  "go_fast_af": false,
  "num_images": 1,
  "image_width": 512,
  "image_height": 512,
  "guidance_scale": 7.5,
  "num_inference_steps": 50
}
Input Parameters
seed Type: integerDefault: -1
Random seed (-1 for random)
prompt (required) Type: string
Prompt
model_type Default: fast
Model type
resolution Default: 1024 × 1024 (Square)
Output resolution
speed_mode Default: Extra Juiced 🚀 (even more speed)
Speed optimization level
output_format Default: webp
Output format
output_quality Type: integerDefault: 100Range: 1 - 100
Output quality (for jpg and webp)
negative_prompt Type: stringDefault:
Negative prompt for generated image. Leave blank to use the default negative prompt.
Output Schema

Output

Type: string • Format: uri

Example Execution Logs 
0%|          | 0/50 [00:00<?, ?it/s]
 30%|███       | 15/50 [00:00<00:00, 62.21it/s]
 66%|██████▌   | 33/50 [00:00<00:00, 105.02it/s]
100%|██████████| 50/50 [00:00<00:00, 120.93it/s]
Version Details
Version ID
aaad77411c5ab95e281c1e32a4dfd6d1a1c01789b0fbd7d4a37053ab0a1950f2
Version Created
February 16, 2026
Run on Replicate →