mv-lab/instructir 🔢🖼️📝 → 🖼️

▶️ 14.6K runs 📅 Feb 2024 ⚙️ Cog 0.9.4 🔗 GitHub 📄 Paper ⚖️ License
image-editing image-restoration

About

High-Quality Image Restoration Following Human Instructions

Example Output

Prompt:

"please remove the rain drops, keep the rest untouched"

Output

Example output

Performance Metrics

6.99s Prediction Time
43.03s Total Time
All Input Parameters 
{
  "image": "https://replicate.delivery/pbxt/KKLe7Hb195UNMS5JVasS3aRi21EF9Mz9Y9inDBdPaDeWZJXk/rain-020.png",
  "prompt": "please remove the rain drops, keep the rest untouched"
}
Input Parameters
seed Type: integer
Random seed. Leave blank to randomize the seed
image (required) Type: string
Input image.
prompt (required) Type: string
Input prompt.
Output Schema

Output

Type: string • Format: uri

Example Execution Logs 
Using seed: 58569
Asking to truncate to max_length but no maximum length is provided and the model has no predefined maximum length. Default to no truncation.
Version Details
Version ID
e98baeb90b5cd143a86aa2a9deeffb2852c3bebbd428f3cdf5da1b31fb99d3a3
Version Created
February 1, 2024
Run on Replicate →