PrunaAI

llms.txt

P-Image Edit

Name: P-Image Edit
Brand: PrunaAI
Price: 0.01 USD
Availability: InStock

AI Image Editing Model

Image

PrunaAI's sub-1-second multi-image editing model supporting up to 5 reference images with state-of-the-art quality

Try Model

Supported Modes

Image Edit

Active

Details

Model ID

p-image-edit

Creator

PrunaAI

Max Input Images

Ready to integrate?

Access p-image-edit via our unified API.

Create Account

Available at 1 provider

Starting from

$0.010 /image via Replicate

Prices shown are in USD

Full pricing details

Provider Performance

Fastest generation through replicate at 3,043ms median latency with 100.0% success rate.

Aggregated from real API requests over the last 30 days.

Generation Time

replicate

p95: 7,170ms

Success Rate

replicate

100.0%

22 / 22 requests

Time to First Byte

replicate

2,365ms

p95: 5,376ms

Provider Rankings

#	Provider	p50 Gen Time	p95 Gen Time	Success Rate	TTFB (p50)
1	replicate	3,043ms	7,170ms	100.0%	2,365ms

Data updated every 15 minutes. Based on all API requests through Lumenfall over the last 30 days.

Providers & Pricing (1)

P-Image Edit is available exclusively through Replicate, starting at $0.01/image.

Replicate

replicate/p-image-edit

Provider Model ID: prunaai/p-image-edit

Output

Image

$0.010 per image

Pricing Notes (2)

• Sub-second multi-image editing model
• Supports up to 5 reference images

View official pricing • As of Dec 30, 2025

P-Image Edit API OpenAI-compatible

Integrate PrunaAI's sub-one-second multi-image editing model into your application using Lumenfall's OpenAI-compatible API to perform text-to-image generation and high-speed image modifications.

Base URL

https://api.lumenfall.ai/openai/v1

Model

p-image-edit

Code Examples

Image Edit

/v1/images/edits

curl -X POST \

  https://api.lumenfall.ai/openai/v1/images/edits \

  -H "Authorization: Bearer $LUMENFALL_API_KEY" \

  -F "model=p-image-edit" \

  -F "[email protected]" \

  -F "prompt=Add a starry night sky to this image" \

  -F "size=1024x1024"

# Response:

# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }

import OpenAI from 'openai';

import fs from 'fs';

const client = new OpenAI({

  apiKey: 'YOUR_API_KEY',

  baseURL: 'https://api.lumenfall.ai/openai/v1'

});

const response = await client.images.edit({

  model: 'p-image-edit',

  image: fs.createReadStream('source.png'),

  prompt: 'Add a starry night sky to this image',

  size: '1024x1024'

});

// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }

console.log(response.data[0].url);

from openai import OpenAI

client = OpenAI(

    api_key="YOUR_API_KEY",

    base_url="https://api.lumenfall.ai/openai/v1"

response = client.images.edit(

    model="p-image-edit",

    image=open("source.png", "rb"),

    prompt="Add a starry night sky to this image",

    size="1024x1024"

# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }

print(response.data[0].url)

Parameter Reference

Required Supported Not available

Size & Layout

Parameter	Type	Description	Modes
`size`	string	Image dimensions as WxH pixels (e.g. "1024x1024") or aspect ratio (e.g. "16:9") WxH determines both shape and scale (aspect_ratio and resolution are ignored when size is provided). W:H format is equivalent to aspect_ratio.	Edit
`aspect_ratio`	string	Aspect ratio of the output image (e.g. "16:9", "1:1") Controls shape independently of scale. Use with resolution to control both. If size is also provided, size takes precedence. Any ratio is accepted and mapped to the nearest supported value.	Edit
`resolution`	string	Output resolution tier (e.g. "1K", "4K") Controls scale independently of shape. Higher tiers produce larger images and cost more. If size is also provided, size takes precedence for scale. Any tier is accepted and mapped to the nearest supported value.	Edit

size

Exact pixel dimensions

"1920x1080"

aspect_ratio

Shape only, default scale

"16:9"

resolution

Scale tier, preserves shape

"1K"

Priority when combined

size › aspect_ratio + resolution › aspect_ratio › resolution

size is most specific and always wins. aspect_ratio and resolution control shape and scale independently.

How matching works

Shape matching – we pick the closest supported ratio. Ask for 7:1 on a model with 4:1 and 8:1, you get 8:1.

Scale matching – providers use different tier formats: K tiers (0.5K 1K 2K 4K) or megapixel tiers (0.25 1). If the exact tier isn't available, you get the nearest one.

Dimension clamping – if a model has pixel limits, we clamp dimensions to fit and keep the aspect ratio intact.

Media Inputs

Parameter	Type	Description	Modes
`image`	file	Required. Input image(s) to edit Supports PNG, JPEG, WebP.	Edit

Output & Format

Parameter	Type	Description	Modes
`response_format`	string	How to return the image `url` `b64_json` Default: `"url"`	Edit
`output_format`	string	Output image format `png` `jpeg` `gif` `webp` `avif` Gateway converts to requested format if provider doesn't support it natively.	Edit
`output_compression`	integer	Compression level for lossy formats (JPEG, WebP, AVIF)	Edit
`n`	integer	Number of images to generate Default: `1` Gateway generates multiple images in parallel even if provider only supports 1.	Edit

Parameter Normalization

How we handle parameters across different providers

Not every provider speaks the same language. When you send a parameter, we handle it in one of four ways depending on what the model supports:

Behavior	What happens	Example
`passthrough`	Sent as-is to the provider	style, quality
`renamed`	Same value, mapped to the field name the provider expects	prompt
`converted`	Transformed to the provider's native format	size
`emulated`	Works even if the provider has no concept of it	n, response_format

Parameters we don't recognize pass straight through to the upstream API, so provider-specific options still work.

Full API Reference Authentication, endpoints, and more

Gallery

View all 2 images

P-Image Edit FAQ

How much does P-Image Edit cost?

P-Image Edit starts at $0.01 per image through Lumenfall. Pricing varies by provider. Lumenfall does not add any markup to provider pricing.

How do I use P-Image Edit via API?

You can use P-Image Edit through Lumenfall's OpenAI-compatible API. Send requests to the unified endpoint with model ID "p-image-edit". Code examples are available in Python, JavaScript, and cURL.

Which providers offer P-Image Edit?

P-Image Edit is available through Replicate on Lumenfall. Lumenfall automatically routes requests to the best available provider.

Overview

P-Image Edit is a high-speed image-to-image editing model developed by PrunaAI designed for near-instantaneous visual transformations. It stands out in the generative AI landscape by offering sub-second inference times while supporting up to five separate reference images for a single edit. This multi-reference capability allows the model to synthesize stylistic and structural elements from several sources simultaneously, maintaining high visual quality without typical performance bottlenecks.

Strengths

Latency Performance: Achieves sub-one-second processing times, making it suitable for real-time interactive applications and high-throughput production pipelines.
Multi-Reference Composition: Supports inputting up to five reference images, allowing the model to bridge visual information across multiple context sources more effectively than single-image editing models.
Temporal and Structural Consistency: Maintains state-of-the-art visual quality during the editing process, ensuring that the output respects the core attributes of the primary input while integrating text-prompted changes.
Flexibility in Modality: Operates on a text-and-image input structure, providing granular control over how specific visual elements are modified or preserved.

Limitations

Inference Constraints: While optimized for speed, the sub-second performance may vary depending on the resolution of the input images or the complexity of the specified edits.
Context Management: Balancing five different reference images requires precise prompting; the model may prioritize certain references over others depending on the visual weights of the input data.
Limited Customization: Being a specialized editing model, it may not perform as well in “text-to-image” only scenarios compared to general-purpose diffusion models like Stable Diffusion XL.

Technical Background

P-Image Edit is built by PrunaAI with a focus on optimization and efficient inference. While the specific architecture builds upon modern diffusion techniques, the primary technical innovation lies in its multi-reference processing layer and the underlying acceleration that enables sub-second execution. This allows the model to bypass the heavy computational overhead usually associated with high-fidelity image-to-image tasks.

Best For

Real-time Creative Tools: Applications where users need immediate feedback while adjusting image styles or elements.
Batch Media Processing: Workflows that require applying consistent edits or branding across large sets of images quickly.
Concept Blending: Scenarios where a final image needs to combine the aesthetic of several different source inspirations into a cohesive new output.

P-Image Edit is available for integration and testing through Lumenfall’s unified API and playground, providing a streamlined way to incorporate high-speed image editing into your stack.

Try P-Image Edit in Playground

Generate images with custom prompts — no API key needed.

Open Playground