Text-to-image AI

Create images from text without writing a single line of code

Generate images from text descriptions in seconds using Google Cloud AI-powered image generation with available APIs in Python, Java, and Go programming languages. 

New customers get up to $300 in free credits to generate images and more using Imagen on Vertex AI. 

Overview

What is text-to-image AI?

Text-to-image AI is a type of artificial intelligence that can generate images from text descriptions. This technology has the potential to transform how we interact with and create visual content. Google Cloud text-to-AI tools and resources, including pre-trained AI models like Imagen, Parti, and Muse, available in Vertex AI, are designed to help developers easily implement text-to-image generation in their applications. And, with AutoML, you can customize AI models for domain-specific applications.

How is text-to-image used in application development?

Text-to-image AI can be used in application development to generate mockups, prototypes, illustrations, test data, educational content, and visualizations for debugging. Google Cloud's Vertex AI and Cloud Vision API giving developers access to a suite of image processing capabilities, including text detection, object detection, and image classification. Document AI can be used to extract text from scanned documents to generate text description images.

What models are used for text-to-image generation?

Imagen, Parti, and Muse are key text-to-image models. Imagen is a diffusion model with a high degree of photorealism. The Pathways Autoregressive Text-to-Image model (Parti) supports content-rich synthesis involving complex compositions and world knowledge. Muse is a Transformer model for strong image generation performance. And Gemini extends what's possible with a model that can understand virtually any input and generate almost any output—including text, images, audio, video, and code.

How are these models different from each other?

Imagen, a diffusion model, is great for photorealism with a deep level of language understanding. Parti, an autoregressive model, is great for consistent style and theme and for generating images in a particular style. Muse, a Transformer model, can generate images with multiple objects and complex composition. Each offers unique strengths: Imagen excels in photorealism, Parti in rich content, and Muse in speed and editing tools. All are easy to use and require no programing knowledge.

What is Imagen 3?

Imagen 3 is Google’s latest image generation model. It delivers outstanding image quality alongside several improvements over Imagen 2 — including over 40% faster generation for rapid prototyping and iteration; better prompt understanding and instruction-following; photo-realistic generations, including groups of people; and greater control over text rendering within an image. 

Launching in preview for Vertex AI customers with early access, Imagen 3 also includes multi-language support, built-in safety features like Google DeepMind’s SynthID digital watermarking, and support for multiple aspect ratios.

How can I use these Google models?

You can access these text-to-image AI models through Vertex AI on Google Cloud or through a third party API provider. To use the models, just provide a text prompt, select parameters (some models allow you to select parameters that control the style, creativity, and accuracy of the generated image) and finally generate the image. 

How It Works

Text-to-image AI uses natural language processing (NLP) to convert the text description into a machine-readable format. Once converted into a machine-readable format, the machine learning model is trained on a massive dataset of text and images, learns to identify patterns, and to uses them to generate new images. Google Cloud's text-to-image AI uses a deep learning model called Imagen, a state-of-the-art model that can generate photorealistic images from text descriptions.

Generative AI product UI
Generate and edit images with Vertex AI Studio

Common Uses

Generate images using AI

Generate images using text prompts

Learn how to use the text-to-image generation feature of Imagen on Vertex AI and export an upscaled version of a generated image. This quickstart shows you how to use Imagen image generation in the Google Cloud console.

Get started
Generated image of dog reading a newspaper in the Vertex AI product

Generate images using text prompts

Learn how to use the text-to-image generation feature of Imagen on Vertex AI and export an upscaled version of a generated image. This quickstart shows you how to use Imagen image generation in the Google Cloud console.

Get started
Generated image of dog reading a newspaper in the Vertex AI product

Edit images with AI

Edit images using text prompts

Use Imagen to edit generated or existing images. You can use a text prompt to update the entire image (mask-free editing), or you can specify part of the image to modify in addition to the text description of the updates (mask-base editing).

Start editing images with text prompts
Image editing in Vertex AI

Edit images using text prompts

Use Imagen to edit generated or existing images. You can use a text prompt to update the entire image (mask-free editing), or you can specify part of the image to modify in addition to the text description of the updates (mask-base editing).

Start editing images with text prompts
Image editing in Vertex AI

Visual captioning with AI

Get image descriptions using visual captioning

Generate relevant descriptions for images, including detailed metadata, automated captioning, and quick descriptions of products and visual assets.

Start generating captions for your images
Image caption product UI

Get image descriptions using visual captioning

Generate relevant descriptions for images, including detailed metadata, automated captioning, and quick descriptions of products and visual assets.

Start generating captions for your images
Image caption product UI

Start your proof of concept

New customers get up to $300 in free credits to generate images and more in Vertex AI

Have a large project?

Learn what types of images you can create

Learn how to generate images using text prompts

Learn how to generate and verify image watermarks

Google Cloud
  • ‪English‬
  • ‪Deutsch‬
  • ‪Español‬
  • ‪Español (Latinoamérica)‬
  • ‪Français‬
  • ‪Indonesia‬
  • ‪Italiano‬
  • ‪Português (Brasil)‬
  • ‪简体中文‬
  • ‪繁體中文‬
  • ‪日本語‬
  • ‪한국어‬
Console
Google Cloud