<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Generative AI by Getty Images on Getty Images API</title><link>/ai-generation/</link><description>Recent content in Generative AI by Getty Images on Getty Images API</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><lastBuildDate>Fri, 22 Sep 2023 06:00:00 -0700</lastBuildDate><atom:link href="/ai-generation/index.xml" rel="self" type="application/rss+xml"/><item><title>Generative AI Download Images</title><link>/ai-generation/downloads/</link><pubDate>Thu, 31 Oct 2024 11:20:49 -0700</pubDate><guid>/ai-generation/downloads/</guid><description>Downloading Generated Images Preview size URLs are returned on the GET /v3/ai/image-generations/{generationRequestId} endpoint and the POST /ai/image-generations/* endpoints. If larger sizes are needed, the PUT /v3/ai/image-generations/{generationRequestId}/images/{index}/download and GET /v3/ai/image-generations/{generationRequestId}/images/{index}/download can be used to retrieve different sizes.
Get Access Token In order to generate images you will need to use Client Credentials or Authorization Code to obtain an access token, and then include that token in all calls.
Get Available Download Sizes for Generated Image To determine what sizes are available for a generated image, use the GET /v3/ai/image-generations/{generationRequestId}/images/{index}/download-sizes endpoint.</description></item><item><title>Generative AI Parameters</title><link>/ai-generation/parameters/</link><pubDate>Thu, 31 Oct 2024 11:20:49 -0700</pubDate><guid>/ai-generation/parameters/</guid><description>Refer to Swagger for full AI Generation API technical documentation.
Prompt Guide Prompt Text Knowing how to engineer prompts is instrumental to producing high quality images in generative AI. Prompts are composed of keywords and phrases that describe a subject and its styles. An effective text prompt may have several components, including:
Main subject: the who of the prompt, e.g. Small puppy with a fluffy white tail wearing a red collar.</description></item><item><title>Generative AI Reference Images</title><link>/ai-generation/reference-images/</link><pubDate>Thu, 31 Oct 2024 11:20:49 -0700</pubDate><guid>/ai-generation/reference-images/</guid><description>Generate Images Using Reference Image Many of the Getty Images Generative AI endpoints use a reference image to influence the generated results. Below are examples of using reference images from a variety of sources. Further documentation for each endpoint can be found on Swagger.
Required Polling For all reference image flows, clients will be required to poll the GET /v3/ai/image-generations/{generationRequestId} endpoint after the initial reference image request to ultimately get the successful generation result.</description></item><item><title>Generative AI Extend</title><link>/ai-generation/extend/</link><pubDate>Thu, 22 Jun 2023 16:20:49 -0700</pubDate><guid>/ai-generation/extend/</guid><description>Extend Extend is currently in beta. Quality may vary when extended images are downloaded at the 4K resolution.
Extend, often called “outpainting” on other platforms, enables users to generate content beyond the borders of a previously generated image or an image from the Getty Images creative library (excluding illustrations, fine art and vectors) using text prompts and numerical values, filling in new areas based on the context of the original image.</description></item><item><title>Generative AI Refine</title><link>/ai-generation/refine/</link><pubDate>Thu, 22 Jun 2023 16:20:49 -0700</pubDate><guid>/ai-generation/refine/</guid><description>Refine Refine is currently in beta. Image quality may vary when refining.
The process of refining, often called “inpainting” on other platforms, allows users to mask a region of a previously generated image, or an image from the Getty Images creative library (excluding illustrations, fine art and vectors), and then fill in the region with content described via a text prompt. The mask needs to be made of black and white areas, where white defines the area to be refined and black defines the area to remain untouched.</description></item><item><title>Getty Images Summary of Training Content</title><link>/ai-generation/summary-of-training-content/</link><pubDate>Thu, 30 Jul 2026 00:00:00 +0000</pubDate><guid>/ai-generation/summary-of-training-content/</guid><description>Last updated: July, 2026
Public Summary of Training Content for General-Purpose AI models required by Article 53 (1)(d) of Regulation (EU) 2024/1689 (AI Act) Provider name and contact details: Getty Images International, Unlimited Company
10 Earlsfort Terrace, Dublin 2, Dublin, D02 T380, Ireland
Authorised representative name and contact details: Getty Images France, SAS
RCS Paris 433 960 895
162 boulevard Haussmann, 75008 Paris
legalnotice@gettyimages.com
Versioned model name(s): Generative AI by Getty Images (See model card here)</description></item><item><title>Getty Images Model Card</title><link>/ai-generation/model-card/</link><pubDate>Wed, 08 Apr 2026 00:00:00 +0000</pubDate><guid>/ai-generation/model-card/</guid><description>Last updated: April, 2026
Model Details Model name: Generative AI by Getty Images Model release date: November, 2025 Model version: Bria Fibo Lite Model summary: Generative AI by Getty Images is a commercially safe service built on a responsibly trained and clean foundational model. Key elements of this commercial safety are: The model was trained on high resolution photography, illustrations, and still images from Getty Images and Bria’s other creative partners, paired with detailed descriptions for each asset.</description></item></channel></rss>