Tech Desk 
Jul 30, 2024
Getty Images has teamed up with NVIDIA to produce a commercially safe image generation AI model trained exclusively on Getty’s ‘best in class’ creative content, ensuring the highest quality output. Getty states that it fairly compensates its creators for their content to encourage continued production.
The service is exclusive to Getty Images subscribers and partners.
Generating prompts for Getty Images AI
Positive prompts
Prompts are essential for generating a desirable image. They must be based on keywords to specify the subject matter so that the most accurate result can be achieved. As of now, Getty's AI image generator is compatible with English only. Here are a few components to consider when writing prompts:
- Main subject: The 'who' of the prompt, e.g. "Small puppy with a fluffy white tail wearing a red collar."
- Action: The 'what/how' of the prompt, e.g. "Joyfully carrying a long wooden stick."
- Surroundings: The 'when/where' of the prompt, e.g. "On a busy street corner at dusk. A small basketball court in the background."
- Visual aesthetics: How you want the images to look, e.g. "Shot from above, soft yellow light, blurred background."
Read more: Meta’s AI Studio now allows you to create your own custom AI chatbot
Negative prompts
Negative prompts create a stricter definition of the image by specifying what elements to exclude, such as blurriness, high contrast, weird hands, unsettling expressions, etc. Commonly used negative prompt terms include:
- ugly
- blurry
- childish
- flat
- malformed
Examples from Getty
Prompt: "A building in the woods made of pink cotton candy, bountiful, all pink, surreal, unusual, misty light, foggy, dusk or dawn, magic hour, pink sky, magical, wispy, strange, fantasy."
Negative prompt: "illustration, vectors, close-up, flash, bright, people, daytime"
This ensures the generated image aligns more closely with the desired outcome, providing both creativity and precision.
