prunaai/flux-realtime-experimental 🔢📝❓ → 🖼️

▶️ 303 runs 📅 Jun 2025 ⚙️ Cog 0.14.7
real-time realtime text-to-image

About

Example Output

Prompt:

"a cat holding a sign saying "hello world""

Output

Example output

Performance Metrics

0.52s Prediction Time
0.53s Total Time
All Input Parameters 
{
  "seed": -1,
  "prompt": "a cat holding a sign saying \"hello world\"",
  "guidance": 3.5,
  "image_size": 1024,
  "speed_mode": "Lightly Juiced 🍊 (more consistent)",
  "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: 7.5
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: png
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 
Using txt2img pipeline
Running prediction with args: ['prompt', 'negative_prompt', 'height', 'width', 'guidance_scale', 'num_inference_steps', 'max_sequence_length', 'generator']
  0%|          | 0/28 [00:00<?, ?it/s]
 54%|█████▎    | 15/28 [00:00<00:00, 72.30it/s]
100%|██████████| 28/28 [00:00<00:00, 101.00it/s]
Inference took 0.32 seconds
Version Details
Version ID
7409fd40c4455d5168c33a57768db53b30093171aab9b8e4a6bd9a35d44460c5
Version Created
June 23, 2025
Run on Replicate →