Skip to main content
ModelRunner
google avatar

google / imagen4/fast

Generate high-quality, photorealistic images from a text prompt fast and at the best price, with strong prompt adherence and improved in-image text rendering.

0.02
OpenAPI

Model Input

Input

Text description of the image to generate.

The aspect ratio of the generated image.

Additional Settings

Customize your input with more control.

The file format of the generated image.

Content moderation strictness from 1 (strictest) to 6 (most permissive).

Seed for reproducible generation. Leave unset for a random result.

You need to be logged in to run this model and view results.
Log in

Model Output

Output

Generated image output
Generated in 7.289 seconds
Logs (1 lines)

Model Example Requests

Examples

Example output 1Example output 2

Model Details

Model Details

Imagen 4 Fast is the speed- and cost-optimized member of the Imagen 4 family. It turns a text prompt into a high-quality, photorealistic image with strong prompt adherence and improved in-image text rendering (legible words, signage, and short labels) at the best price in the family, ideal for rapid iteration and high-volume generation.

The only required input is prompt. Use aspect_ratio to set the frame (1:1, 16:9, 9:16, 4:3, 3:4). Output is one generated image returned as a URL. This is the Fast tier the best value; for a balanced default use Imagen 4 (Standard), and for the highest quality use Imagen 4 Ultra.

## Best for - Rapid iteration and high-volume image generation on a budget - Web-sized product, lifestyle, and marketing images from a written brief - Scenes that need legible in-image text such as short signage, labels, posters - Quick concept exploration before committing to a higher-quality tier

## Choose another model when - You want maximum detail or 2K output use Imagen 4 Ultra (or Imagen 4 Standard for 2K) - You want the balanced quality/cost default use Imagen 4 (Standard) - You want to edit, restyle, or extend an existing image use an image-to-image or image-editing model - You need motion or animation use a text-to-video or image-to-video model

## Tips - Describe the subject, setting, lighting, lens/feel, and any short text you want rendered explicitly in the prompt - Set framing with aspect_ratio (e.g. 16:9 for banners, 9:16 for mobile/social, 1:1 for thumbnails)

## Safety and Content Moderation - safety_tolerance (advanced) controls how strict content filtering is, as a string from 1 (strictest) to 6 (most permissive); the default is 4. Lower it for tighter moderation, raise it only when stricter filtering is rejecting acceptable prompts.

To run via the ModelRunner JavaScript client:

```js import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("google/imagen4/fast", { input: { prompt: "a glass coffee mug on a marble counter, soft morning light", aspect_ratio: "1:1", }, }); ```