prunaai/flux-2-fast 🔢📝❓🖼️ → 🖼️

▶️ 128.6K runs 📅 Nov 2025 ⚙️ Cog 0.16.9
image-editing text-to-image

About

A step-distilled version of flux 2 down to 1s.

Example Output

Prompt:

"a cat"

Output

Example output

Performance Metrics

1.72s Prediction Time
1.73s Total Time
All Input Parameters 
{
  "width": 1024,
  "height": 768,
  "prompt": "a cat",
  "num_outputs": 1,
  "output_format": "jpg",
  "output_quality": 80,
  "num_inference_steps": 4
}
Input Parameters
seed Type: integer
Random seed. Set for reproducible generation
width Type: integerDefault: 1024Range: 256 - 2048
Width of the output image. Only used when aspect_ratio=custom.
height Type: integerDefault: 1024Range: 256 - 2048
Height of the output image. Only used when aspect_ratio=custom.
prompt (required) Type: string
Text prompt for image generation or editing
num_outputs Type: integerDefault: 1Range: 1 - 4
Number of outputs to generate
aspect_ratio Default: 16:9
Aspect ratio for the generated image. Use 'match_input_image' to match the first input image's aspect ratio.
input_images Type: arrayDefault:
List of input images for image editing. If provided, the model will perform image editing instead of text-to-image generation. Maximum 5 images.
output_format Default: jpg
Format of the output images
output_quality Type: integerDefault: 80Range: 0 - 100
Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
Output Schema

Output

Type: array • Items Type: string • Items Format: uri

Example Execution Logs 
0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:01,  2.64it/s]
 50%|█████     | 2/4 [00:00<00:00,  2.62it/s]
 75%|███████▌  | 3/4 [00:01<00:00,  2.55it/s]
100%|██████████| 4/4 [00:01<00:00,  2.58it/s]
100%|██████████| 4/4 [00:01<00:00,  2.58it/s]
Version Details
Version ID
7fbd6197df31149fd65a673011a4d9f70f67e0a96149ab522b2040b0b31cd154
Version Created
December 22, 2025
Run on Replicate →