Compete in HackAPrompt 2.0, the world's largest AI Red-Teaming competition!

Check it out →
Bienvenue
😃 Bases
💼 Applications de base
🧙‍♂️ Intermédiaire
🤖 Agents
⚖️ Fiabilité
🖼️ Prompting d'images
🔓 Hacking de prompts
🔨 Outillage
💪 Calibrage de prompts
🎲 Divers
📚 Bibliographie
📦 Prompted Products
🛸 Ressources supplémentaires
🔥 Sujets Brûlants
✨ Générique
🖼️ Prompting d'images🟢 Style Modifiers

Style Modifiers

🟢 This article is rated easy
Reading Time: 1 minute
Last updated on August 7, 2024

Sander Schulhoff

Style modifiers are simply descriptors which consistently produce certain styles (e.g. 'tinted red', 'made of glass', 'rendered in Unity'). They can be combined together to produce even more specific styles. They can "include information about art periods, schools, and styles, but also art materials and media, techniques, and artists".

Example

Here are a few pyramids generated by DALLE, with the prompt pyramid.

Here are a few pyramids generated by DALLE, with the prompt A pyramid made of glass, rendered in Unity and tinted red, which uses 3 style modifiers.

Here is a list of some useful style modifiers:

photorealistic, by greg rutkowski, by christopher nolan, painting, digital painting, concept art, octane render, wide lens, 3D render, cinematic lighting, trending on ArtStation, trending on CGSociety, hyper realist, photo, natural light, film grain

Notes

Oppenlaender et al. describe the rendered in ... descriptor as a quality booster, but our working definition differs, since that modifier does consistently generate the specific Unity (or other render engine) style. As such, we will call that descriptor a style modifier.

Sander Schulhoff

Sander Schulhoff is the CEO of HackAPrompt and Learn Prompting. He created the first Prompt Engineering guide on the internet, two months before ChatGPT was released, which has taught 3 million people how to prompt ChatGPT. He also partnered with OpenAI to run the first AI Red Teaming competition, HackAPrompt, which was 2x larger than the White House's subsequent AI Red Teaming competition. Today, HackAPrompt partners with the Frontier AI labs to produce research that makes their models more secure. Sander's background is in Natural Language Processing and deep reinforcement learning. He recently led the team behind The Prompt Report, the most comprehensive study of prompt engineering ever done. This 76-page survey, co-authored with OpenAI, Microsoft, Google, Princeton, Stanford, and other leading institutions, analyzed 1,500+ academic papers and covered 200+ prompting techniques.

Footnotes

  1. Oppenlaender, J. (2022). A Taxonomy of Prompt Modifiers for Text-To-Image Generation. 2 3