Imagen V3

imagen-3.0-generate-002

Imagen V3

imagen-3.0-generate-002

Google's highest quality text-to-image model with fine detail, rich lighting, and excellent text rendering capabilities.

Approx. Price

$0.051 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 1,408px

Number of Images

Default

1

Person Generation

Default

allow_adult

Options (2)

Allow Adults, Don't Allow People

Allow generation of images with people

Resolution

Default

1024x1024

Options (5)

1024x1024 (Square (1:1)), 768x1408 (Portrait (9:16)), 1408x768 (Landscape (16:9)), 896x1280 (Portrait (3:4)) +1 more

Safety Filter

Default

BLOCK_ONLY_HIGH

Options (3)

Block High Risk Only, Block Medium & High Risk, Block All Risk Levels

Level of safety filtering to apply

Benchmarks

Human preference benchmarks sourced from LMArena.

Text to Image

#58 / 75

Arena Score

1058.1

Votes

360,739

Confidence Interval

1054.9 - 1061.3

Published 2026-08-07 · Matched as imagen-3.0-generate-002

LMArena Dataset

Examples

Loading examples…

Compare Imagen V3 with similar models from the same provider or model family.