prunaai/p-image-edit 🔢✓🖼️📝❓ → 🖼️

⭐ Official ▶️ 36.3M runs 📅 Oct 2025 ⚙️ Cog 0.16.12
image-editing image-re-lighting image-style-transfer image-upscaling

Performance

1.1sTypical run time
36.3MTotal runs

About

A sub 1 second 0.01$ multi-image editing model built for production use cases. For image generation, check out p-image here: https://replicate.com/prunaai/p-image

Example Output

Prompt:

"

Change the color of her dress to golden and white with a different elegant pattern.
Add delicate traces of gold to her crown.

Place the text "P-Image-Edit" in the middle in romantic white paint-brushed letters, like hand-painted lettering on an old fairytale canvas. The letters should have graceful swashes, soft curves, and thin-to-medium strokes . The text should be ornate but still readable, not bold, chunky, or digital-looking. The text is located on the level of her shoulder

"

Output

Example output

Performance Metrics

1.10s Prediction Time
2.19s Total Time
All Input Parameters 
{
  "seed": 42,
  "no_op": false,
  "turbo": true,
  "images": [
    "https://replicate.delivery/pbxt/PJrnETmC9Jz37ILO9fyovK1Zt9LpztRGRBvkwbkdRe8jtrii/4b325407-eb03-4fad-b14f-ff4985775f8b.png"
  ],
  "prompt": "Change the color of her dress to golden and white with a different elegant pattern.\nAdd delicate traces of gold to her crown.\n\nPlace the text \"P-Image-Edit\" in the middle in romantic white paint-brushed letters, like hand-painted lettering on an old fairytale canvas. The letters should have graceful swashes, soft curves, and thin-to-medium strokes . The text should be ornate but still readable, not bold, chunky, or digital-looking. The text is located on the level of her shoulder ",
  "aspect_ratio": "match_input_image"
}
Input Parameters
seed Type: integer
Random seed. Set for reproducible generation.
no_op Type: booleanDefault: false
Health check mode - returns status without inference.
turbo Type: booleanDefault: true
If turned on, the model will run faster with additional optimizations. For complicated tasks, it is recommended to turn this off.
images Type: arrayDefault:
Images to use as a reference. For editing task, provide the main image as the first image.
prompt (required) Type: string
Text prompt for image generation. Make sure to describe your edit task clearly. You can refer to the images as 'image 1' and 'image 2' and so on.
aspect_ratio Default: match_input_image
Aspect ratio for the generated image. `match_input_image` will match the aspect ratio of the first image.
replicate_weights Default: default
Task to perform with P-Edit.
disable_safety_checker Type: booleanDefault: false
Disable safety checker for generated images.
Output Schema

Output

Type: string • Format: uri

Example Execution Logs 
Using seed: 42
Generation took 0.87 seconds
Version Details
Version ID
3239a09914920a6bf519253ab0308a1fb6c363f8ec57e7a4163c8cc16b17f967
Version Created
June 22, 2026
Run on Replicate →