OpenAI Unveils 4o Image Generation: A Game-Changer for Creatives
Introduction
OpenAI has been expanding its ChatGPT offerings, adding AI voice assistants, file and image understanding, advanced research capabilities, and more. However, there was one glaring omission – a really capable image generator. That changed with the launch of 4o image generation, a model that tackles very difficult prompts, including realistic images and accurate text.
Key Features
4o image generation boasts many capabilities that OpenAI’s previous image generator didn’t have, such as image referencing, which can be used to render a new version of the image or as inspiration for creating a completely new work. It can also generate images on transparent backgrounds, use specific colors from HEX codes, or implement the chatbot’s advanced conversational capabilities in the generations.
Prompt Example
During a live stream demo, OpenAI CEO Sam Altman, joined by researchers Gabriel Goh and Prafulla Dhariwal, prompted 4o to create a photo from a specific POV with a flyer that included lots of text. After loading for a few seconds, it got the cinematic direction right and accurately printed all the text.
What’s New
The image generator is now accessible in ChatGPT, allowing users to refine images through a multi-turn conversation. This makes tweaking images easier and allows the model to use the context of previous generations to create new ones. Since GPT-4o has access to the web, that context is also added to creating the images.
Looser Safeguards
The new image generator also allows for more risqué content, similar to Elon Musk’s Grok model. However, OpenAI has implemented safeguards to block requests that violate content policies, including child sexual abuse materials and sexual deepfakes.
How to Access
The updated image generation features are rolling out now in ChatGPT and Sora. However, due to high demand, the rollout to the free tier has been delayed. To access the image generation, you need to be a subscriber, with options including ChatGPT Plus, which costs $20 per user per month, and enterprise and education users will be given access soon.
Conclusion
OpenAI’s 4o image generation is a game-changer for creatives, offering a range of features and capabilities that set it apart from other image generation models. With its ability to tackle difficult prompts, generate realistic images, and reference previous generations, it’s an exciting development for the world of AI.
FAQs
Q: What is 4o image generation?
A: 4o image generation is a new model from OpenAI that can generate realistic images based on text prompts.
Q: What are the key features of 4o image generation?
A: 4o image generation has many capabilities, including image referencing, transparent backgrounds, and specific colors from HEX codes.
Q: Is 4o image generation available for free?
A: Not yet, but it will be available for free for all users in the future. For now, it’s available for subscribers, including ChatGPT Plus and enterprise and education users.
Q: Can I still access DALL-E?
A: Yes, you can still access DALL-E through a dedicated DALL-E GPT.
