# P-Image Edit

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

## Quick Reference

- Model ID: p-image-edit
- Creator: PrunaAI
- Status: active
- Base URL: https://api.lumenfall.ai/openai/v1

## Specifications

- Max Input Images: 5
- Input Modalities: text, image
- Output Modalities: image
- Supported Modes: Image Edit

## API Parameters

The compiled parameter schema for this model is available via the API: `GET /v1/models/p-image-edit?schema=true`.

### Core Parameters

- `prompt` (string) — REQUIRED: Edit instruction for the image
- `seed` (integer): Random seed for reproducibility

### Size & Layout

- `size` (string): Image dimensions as WxH pixels (e.g. "1024x1024") or aspect ratio (e.g. "16:9"). Values: auto, 1365x768, 768x1365, 1254x836, 836x1254, 887x1182, 1024x1024, 1183x887
- `aspect_ratio` (string): Aspect ratio of the output image (e.g. "16:9", "1:1"). Values: auto, 9:16, 2:3, 3:4, 1:1, 4:3, 3:2, 16:9
- `resolution` (string): Output resolution tier (e.g. "1K", "4K"). Values: auto, 1K

### Media Inputs

- `image` (file) — REQUIRED: Input image(s) to edit

### Output & Format

- `response_format` (string): How to return the image. Default: url. Values: url, b64_json
- `output_format` (string): Output image format. Values: png, jpeg, gif, webp, avif
- `output_compression` (integer): Compression level for lossy formats (JPEG, WebP, AVIF)
- `n` (integer): Number of images to generate. Default: 1

### Additional Parameters

- `disable_safety_checker` (boolean): Disable safety checker for generated images.. Only available via replicate
- `replicate_weights` (string): Task to perform with P-Edit.. Only available via replicate
- `turbo` (boolean): If turned on, the model will run faster with additional optimizations. For complicated tasks, it is recommended to turn this off.. Only available via replicate


## Model Identifiers

- Primary Slug: p-image-edit


## Tags

image-editing, image-to-image

## Available Providers

### Replicate

- Config Key: replicate/p-image-edit
- Provider Model ID: prunaai/p-image-edit
- Pricing: $0.010/image
  - Note: Sub-second multi-image editing model
  - Note: Supports up to 5 reference images
  - Source: https://replicate.com/prunaai/p-image-edit


## Performance Metrics

Provider performance over the last 30 days.

### replicate

- Median Generation Time (p50): 3043ms
- 95th Percentile Generation Time (p95): 7170ms
- Average Generation Time: 3528ms
- Success Rate: 100.0%
- Total Requests: 22
- Time to First Byte (p50): 2365ms
- Time to First Byte (p95): 5376ms


## Image Gallery

2 images available for this model. Browse all at https://lumenfall.ai/models/prunaai/p-image-edit/gallery

### Curated Examples

- [Add a plane to this beautiful sunset city](https://assets.lumenfall.ai/ODoCGCZ-f5B4uCuXhsSnSCJz9R2FzMYqo-PFA5svk6s/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/4urr6t0x1n17o42smjo6l25omqtf@jpeg)
- [Add a capybara](https://assets.lumenfall.ai/-fv6LadGG2mDGuE8WS-HY6e8KoMsXPI9zeEQCrwngJI/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/le9laqd3ckogiuo8zanxt1ol0iwy@jpeg)

## Example Prompt

The following prompt was used to generate an example image in our playground:

Add a capybara

## Code Examples

### Image Edit (/v1/images/edits)

#### cURL

curl -X POST \
  https://api.lumenfall.ai/openai/v1/images/edits \
  -H "Authorization: Bearer $LUMENFALL_API_KEY" \
  -F "model=p-image-edit" \
  -F "image=@source.png" \
  -F "prompt=Add a starry night sky to this image" \
  -F "size=1024x1024"

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

#### JavaScript

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);

#### Python

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)


## About

## 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.

## Frequently Asked Questions

### 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.

## Links

- Model Page: https://lumenfall.ai/models/prunaai/p-image-edit
- About: https://lumenfall.ai/models/prunaai/p-image-edit/about
- Providers, Pricing & Performance: https://lumenfall.ai/models/prunaai/p-image-edit/providers
- API Reference: https://lumenfall.ai/models/prunaai/p-image-edit/api
- Benchmarks: https://lumenfall.ai/models/prunaai/p-image-edit/benchmarks
- Use Cases: https://lumenfall.ai/models/prunaai/p-image-edit/use-cases
- Gallery: https://lumenfall.ai/models/prunaai/p-image-edit/gallery
- Playground: https://lumenfall.ai/playground?model=p-image-edit
- API Documentation: https://docs.lumenfall.ai