Nano GPT logo
NanoGPT

P-Image

pruna-ai/p-image/text-to-image
BackTry Model

P-Image

pruna-ai/p-image/text-to-image
BackTry Model

Fast text-to-image generation for low-cost drafts, social visuals, and rapid creative iteration.

Added May 12, 2026

Approx. Price

Varies per image

Model Type

text-to-image

Settings

Generation controls available for this model.

Images Per Run

Up to 4

Output images

Input Images

N/A

No reference/edit image input

Output Sizes

Square
Portrait
Landscape
up to 1,376px

Number of Images

Default

1

Output Format

Default

png

Options (3)

PNG, JPEG, WebP

Output image format.

Resolution

Default

1024x1024

Options (7)

1024x1024 (Square (1:1)), 1376x768 (Wide Landscape (~16:9)), 1184x896 (Landscape (~4:3)), 1248x832 (Landscape (~3:2)) +3 more

Seed

Number

Default

-1

Control reproducibility (-1 for random).

Benchmarks

Human preference benchmarks sourced from Artificial Analysis.

Text to Image

#87 / 147

ELO

1093.0

Appearances

4,277

95% CI

-8/8

Release Date 2025-12 · Matched as P-Image

Artificial Analysis API

Examples

Loading examples…

Compare P-Image with similar models from the same provider or model family.

P-Image Edit

pruna-ai/p-image/edit

Prompt-guided image editing for one to five reference images, with controls for output format and aspect ratio.

P-Image Edit LoRA

pruna-ai/p-image/edit-lora

P-Image prompt-guided editing with optional external LoRA weights and one to five reference images.

P-Image LoRA

pruna-ai/p-image/text-to-image-lora

P-Image text-to-image generation with optional external LoRA weights.

P-Image Upscale

pruna-ai/p-image/upscale

Fast image upscaling with target output size controls from 1 to 8 megapixels.

P-Image

prunaai:1@1

Fast image generation and editing. Supports both text-to-image and image-to-image workflows.

Krea 2 Turbo

wavespeed-ai/krea-v2/turbo

Krea 2 Turbo is a fast 12.9B open-weights image model with native 1K and 2K generation plus optional image-to-image guidance.