prunaai/hidream-l1-fast 🔢📝❓ → 🖼️

▶️ 4.4M runs 📅 Apr 2025 ⚙️ Cog 0.16.0 🔗 GitHub ⚖️ License
speed-optimized text-to-image

About

This is an optimised version of the hidream-l1 model using the pruna ai optimisation toolkit!

Example Output

Prompt:

"a purple cheetah holding a sign that says "pip install pruna""

Output

Example output

Performance Metrics

1.73s Prediction Time
1.73s Total Time
All Input Parameters 
{
  "seed": 10,
  "prompt": "a purple cheetah holding a sign that says \"pip install pruna\"",
  "model_type": "fast",
  "resolution": "1024 × 1024 (Square)",
  "speed_mode": "Extra Juiced 🚀 (even more speed)",
  "output_format": "jpg",
  "output_quality": 80
}
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: Lightly Juiced 🍊 (more consistent)
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 
Running inference...
  0%|          | 0/16 [00:00<?, ?it/s]
 94%|█████████▍| 15/16 [00:01<00:00, 10.96it/s]
100%|██████████| 16/16 [00:01<00:00, 10.23it/s]
Version Details
Version ID
06898b39cb00e42d31666b0dc8b9904f326169768129d756184f65ecf1986c8f
Version Created
August 18, 2025
Run on Replicate →