P-Image

P-Image is Pruna’s performance text-to-image generation model, delivering state-of-the-art AI images in less than one second.

Designed for professional results, it offers a rare combination of speed, affordability, visual quality, diversity, exact prompt adherence, and exceptional text rendering, making it the go-to choice when you need fast, beautiful, and reliable image generation.

Tip

Test it now in the P-Image Playground.

Prompt formula

[Subject] [Behavior] [Style] [Environment]

A purple prune character, reading a book, animation style, in a living room

[Subject] [Behavior] [Style] [Environment]

Low angle shot of a happy knitted purple prune character with expressive eyes, cute limbs and a roundish body, reading a book, animated style, award-winning design, in a cosy, dimly lit living room with a window

Basic

Advanced

Primary Subject - What/who is the focus? - Be specific: “young woman with short black hair” not “person” - Include details: age, appearance, clothing, expression
Subject Behavior - What are they doing? - Use descriptive actions: “reading”, “walking”, “smiling”
Visual Style - Artistic medium/aesthetic - Examples: “photorealistic”, “oil painting”, “anime style”, “watercolor”
Environmental Context - Setting & atmosphere - Location: “living room”, “mountain peak”, “urban street” - Lighting: “golden hour”, “soft studio lighting”, “dramatic shadows” - Mood: “peaceful”, “energetic”, “mysterious”

Tip

For full prompting guidelines, see the Image Generation guide.

Key Features

P-Image delivers exceptional performance for text-to-image generation with the following key capabilities:

Cost, Speed and Quality: Just $0.005 and 1 second per image. P-Image provides exceptional value with ultra-fast generation times while maintaining high-quality output.
Adherence: Exact prompt adherence for precise results. The model faithfully follows your prompts to deliver accurate and consistent image generation.
Text Rendering: Highly controlled text generation. P-Image excels at rendering text within images with precision and control.
Diversity: The model can generate images with a high degree of diversity.

"Full-body fashion shot of a model wearing an oversized beige hoodie and cargo pants, leaning against a graffiti-covered concrete wall in Tokyo at night. Neon street signs reflect off the wet pavement. Flash photography style, high grain, hypebeast aesthetic, sharp focus on the clothing texture and fabric drape, 35mm film look."

"A landscape image created entirely out of layered colored paper cutouts. A mountain range at sunset with a paper moon and paper clouds suspended by strings. The lighting casts realistic shadows between the paper layers, giving it physical depth. Orange, purple, and deep blue color palette. Arts and crafts style, playful but intricate."

"Intense, high-contrast action shot of a female athlete boxing in a dark, gritty gym. She is mid-punch, with sweat droplets flying off her glove. Rim lighting outlines her silhouette against the dark background. Smoke machine atmosphere. Motivational, gritty, Nike ad style, desaturated colours with high contrast. Add text "Now only $45 per month" and in small letters "Free trial class"

"A man" / "A woman"

Tip

Test it now in the P-Image Playground.

Domain Use Cases

"Full-body fashion shot of a model wearing an oversized beige hoodie and cargo pants, leaning against a graffiti-covered concrete wall in Tokyo at night. Neon street signs reflect off the wet pavement. Flash photography style, high grain, hypebeast aesthetic, sharp focus on the clothing texture and fabric drape, 35mm film look."

"Michelin-star style food photography of a deconstructed scallop dish on a dark ceramic plate. Garnished with delicate edible flowers, foam, and small dots of vibrant green herb oil. The lighting is dramatic and moody (chiaroscuro), coming from the side to emphasize texture. Macro lens, extremely shallow depth of field, focus sharp on the seared scallop texture."

"A pair of muddy, worn leather hiking boots resting on a mossy rock next to a rushing mountain stream. In the background, out of focus, are a backpack and a camping stove with steam rising. Sunrise light filtering through pine trees (golden hour). The focus is sharp on the brand logo embossed on the boot tongue. Authentic, adventurous lifestyle branding."

Tip

Test it now in the P-Image Playground.

Integration

P-Image 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'

Asynchronous (Default)

Submit requests asynchronously for longer-running generations:

curl -X POST 'https://api.pruna.ai/v1/predictions' \
-H 'Content-Type: application/json' \
-H 'apikey: YOUR_API_KEY' \
-H 'Model: p-image' \
-d '{
    "input": {
    "prompt": "A majestic lion standing on a rocky cliff at sunset, photorealistic, 4k",
    "aspect_ratio": "16:9"
    }
}'

Response includes a status URL to check progress:

{
    "id": "1zww7deyssrme0csqwr90phzzr",
    "model": "p-image",
    "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' \
-H 'Try-Sync: true' \
-d '{
    "input": {
        "prompt": "A majestic lion standing on a rocky cliff at sunset, photorealistic, 4k",
        "aspect_ratio": "16:9"
    }
}'

If the generation 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 offers flexible configuration options to customize image generation:

Tip

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

Required Parameters

Parameter	Type	Description
prompt	string	Text description of the image to generate. The model provides exact prompt adherence for precise results.

Optional Parameters

Parameter	Type	Default	Description
aspect_ratio	string	“16:9”	Aspect ratio for the 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 generation
disable_safety_checker	boolean	false	Disable safety checker for generated images

Example Configuration

Standard aspect ratio:

{
    "input": {
        "prompt": "A serene mountain landscape at dawn",
        "aspect_ratio": "16:9",
        "seed": 42
    }
}

Custom dimensions:

{
    "input": {
        "prompt": "A futuristic cityscape",
        "aspect_ratio": "custom",
        "width": 1024,
        "height": 768
    }
}