P-Image-Edit

P-Image-Edit is Pruna’s performance image editing model, delivering state-of-the-art AI image editing in less than one second.

Designed for professional results, it offers a rare combination of speed, affordability, visual quality, exact prompt adherence, exceptional text rendering, and multi-image editing capabilities, making it the go-to choice when you need fast, precise, and reliable image editing with high control.

Tip

Test it now in the P-Image-Edit Playground.

[Modification] [Change Target] [Preservation]

Add a teddy bear, next to the character reading a book, matching textures while preserving the overall style and keeping all other elements unchanged

Before

After

Modification Instruction - What change to make? - Add: “add a bird”, “insert clouds”, “place flowers” - Remove: “remove the person”, “eliminate power lines” - Modify: “change color to blue”, “convert to oil painting” - Transform: “transform to Viking”, “change outfit to modern”
Change Target - What to modify? - Be specific: “the woman with red hair”, “the car in the foreground”, “the text on the sign” - Avoid pronouns: Use “the purple prune character” not “it”
Preservation Requirements - What must stay the same? - Identity: “preserve facial features”, “keep same person” - Composition: “maintain exact position”, “keep same pose” - Lighting: “keep same lighting”, “preserve shadows” - Style: “maintain visual consistency”, “keep art style”

Tip

For full prompting guidelines, see the Image Editing guide.

Key Features

P-Image-Edit delivers exceptional performance for image editing with the following key capabilities:

Performance: State-of-the-art AI image editing in 1s for $0.010. P-Image-Edit provides exceptional value with ultra-fast editing times while maintaining high-quality output.
Adherence: Faithful image generation from controllable prompt instructions. The model provides exact prompt adherence for precise results, faithfully following your editing prompts to deliver accurate and consistent image editing.
Text Rendering: Precise, styled text rendering without misspelling. P-Image-Edit excels at rendering and editing text within images with precision and control, delivering highly controlled text generation.
Multi-Image Editing: High control with multiple reference images. The model can seamlessly combine and edit multiple images with precise control over the final output, enabling advanced multi-image editing workflows.

"Change background / object / camera angle"

"Change background / object / setting"

"Change text / person"

"Take the mountain from image 1. Take the sky from image 2. Take the man on the rocks from image 3."

Tip

For full prompting guidelines, see the Image Editing guide.

Domain Use Cases

"Change the red Ferrari to a matte black finish with gold racing stripes. And add a racing number '23' and sponsorship decals to the car's doors and hood."

"Place the red Ferrari speeding on a sun-drenched coastal highway instead of the city."

"Add a blue motorbike and driver next to the red car. And add a helicopter flying low above the street, with its spotlight on the car."

Tip

For full prompting guidelines, see the Image Generation guide.

Integration

P-Image-Edit integrates seamlessly with Pruna’s API infrastructure. Here’s how to get started:

Tip

For more information on how to use the API, see the API Reference.

API Endpoint: Base URL: https://api.pruna.ai/v1/predictions

Authentication

Include your API key in the request header:

-H 'apikey: YOUR_API_KEY'

File Upload

Before editing images, you’ll need to upload your reference images. P-Image-Edit supports 1-5 images for multi-image editing.

Upload an image:

curl -X POST https://api.pruna.ai/v1/files \
-H 'apikey: YOUR_API_KEY' \
-F 'content=@my-photo.jpg'

Response:

{
    "id": "file-abc123",
    "urls": {
        "get": "https://api.pruna.ai/v1/files/file-abc123"
    }
}

Use the file URL from the response in your editing requests.

Asynchronous (Default)

Submit requests asynchronously for longer-running edits:

curl -X POST 'https://api.pruna.ai/v1/predictions' \
-H 'Content-Type: application/json' \
-H 'apikey: YOUR_API_KEY' \
-H 'Model: p-image-edit' \
-d '{
    "input": {
        "images": ["https://api.pruna.ai/v1/files/file-abc123"],
        "prompt": "Change the background to a sunset beach scene",
        "aspect_ratio": "16:9"
    }
}'

Response includes a status URL to check progress:

{
    "id": "1zww7deyssrme0csqwr90phzzr",
    "model": "p-image-edit",
    "input": { },
    "get_url": "https://api.pruna.ai/v1/predictions/status/1zww7deyssrme0csqwr90phzzr"
}

Check status by polling the status endpoint:

curl -H 'apikey: YOUR_API_KEY' \
https://api.pruna.ai/v1/predictions/status/1zww7deyssrme0csqwr90phzzr

When completed, download the result:

curl -H 'apikey: YOUR_API_KEY' \
https://api.pruna.ai/v1/predictions/delivery/xezq/abc123.../output.jpg \
-o result.jpg

Synchronous (Try-Sync)

For faster results, use synchronous mode with the Try-Sync: true header:

curl -X POST 'https://api.pruna.ai/v1/predictions' \
-H 'Content-Type: application/json' \
-H 'apikey: YOUR_API_KEY' \
-H 'Model: p-image-edit' \
-H 'Try-Sync: true' \
-d '{
    "input": {
        "images": ["https://api.pruna.ai/v1/files/file-abc123"],
        "prompt": "Change the background to a sunset beach scene",
        "aspect_ratio": "16:9"
    }
}'

If the editing completes within 60 seconds, you’ll receive the result directly:

{
    "status": "succeeded",
    "generation_url": "https://api.pruna.ai/v1/predictions/delivery/xezq/abc123.../output.jpg"
}

Download your image:

curl -H 'apikey: YOUR_API_KEY' \
https://api.pruna.ai/v1/predictions/delivery/xezq/abc123.../output.jpg \
-o my-image.jpg

Configuration

P-Image-Edit offers flexible configuration options to customize image editing:

Tip

For more information on how to use the API, see the API Reference.

Required Parameters

Parameter	Type	Description
images	array	Array of 1-5 image URLs or base64 encoded images to edit. The source images that will be modified.
prompt	string	Text description of the editing instructions. The model provides exact prompt adherence for precise results, faithfully following your editing prompts to deliver accurate and consistent image editing.

Optional Parameters

Parameter	Type	Default	Description
reference_image	string	“1”	Which image in the images array to use as the primary reference (e.g., “1”, “2”, “3”). Used for multi-image editing to specify the main image.
aspect_ratio	string	“16:9”	Aspect ratio for the edited image. Options: “1:1”, “16:9”, “9:16”, “4:3”, “3:4”, “3:2”, “2:3”, “custom”
width	integer	None	Custom width in pixels (256-1440). Only used when aspect_ratio=”custom”. Must be multiple of 16.
height	integer	None	Custom height in pixels (256-1440). Only used when aspect_ratio=”custom”. Must be multiple of 16.
seed	integer	random	Random seed for reproducible editing
disable_safety_checker	boolean	false	Disable safety checker for edited images

Example Configuration

Single image editing:

{
    "input": {
        "images": ["https://api.pruna.ai/v1/files/file-abc123"],
        "prompt": "Replace the sky with a dramatic stormy sky with lightning",
        "aspect_ratio": "16:9",
        "seed": 42
    }
}

Multi-image editing:

{
    "input": {
        "images": [
            "https://api.pruna.ai/v1/files/file-abc123",
            "https://api.pruna.ai/v1/files/file-def456"
        ],
        "prompt": "Combine the subject from the main image with the background from reference image 2",
        "reference_image": "1",
        "aspect_ratio": "custom",
        "width": 1024,
        "height": 768
    }
}