ChatGPT’s New Image Generator Creates Stunning Images for All Users (Including Free Ones)
OpenAI’s Latest Update
OpenAI has continuously expanded its ChatGPT offerings, adding an AI voice assistant, file and image understanding, advanced research capabilities, AI agents, and more. However, there was one glaring omission: A really capable image generator.
Introducing 4o Image Generation
Last week, OpenAI launched 4o image generation. This image model is significantly better, albeit slower, than the DALL-E models previously offered by OpenAI. It tackles very difficult prompts, such as realistic images and, most impressively, accurate text.
Capabilities
For example, in the 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.
Image Referencing
It also boasts many other capabilities that OpenAI’s previous image generator did not have, such as image referencing, which can be used to render a new version of the image (such as an anime version or a selfie) or as inspiration for creating a completely new work.
Looser Safeguards
Another new aspect of the image generator is that it can now create more risque content, something Elon Musk’s Grok model is known for. During the live stream, Altman shared that you will be able to use GPT-4o’s image generation to create offensive content "within reason." In an X post after the livestream, Altman added:
How to Access
The updated image generation features are rolling out now in ChatGPT and Sora. All users, including free ones, can access the model. However, if you’re unimpressed when you try it in the free version, it’s because the only method that activates the use of GPT-4o is typing in the shortcut "/create image." If you just type in a request such as "Create an image of XYZ," it will default to the DALL-E model, which will render significantly lower-quality photos.
Conclusion
OpenAI’s 4o image generation model is a significant step forward in the development of AI-powered image generation. With its ability to create accurate and realistic images, it has the potential to revolutionize various industries and applications. While there are some concerns about the potential misuse of this technology, OpenAI is taking steps to ensure that it is used responsibly.
FAQs
Q: What is the 4o image generation model?
A: The 4o image generation model is a new image generation model developed by OpenAI, which is capable of creating accurate and realistic images.
Q: What are the capabilities of the 4o image generation model?
A: The 4o image generation model has many capabilities, including image referencing, which can be used to render a new version of the image or as inspiration for creating a completely new work.
Q: Can I access the 4o image generation model?
A: Yes, all users, including free ones, can access the model. However, if you’re unimpressed when you try it in the free version, it’s because the only method that activates the use of GPT-4o is typing in the shortcut "/create image."
Q: What are the safeguards in place to prevent the misuse of the 4o image generation model?
A: OpenAI has implemented several safeguards, including blocking requests that violate content policies, limiting what can be created when real people are in the context, and robust safeguards around nudity and graphic violence.
Q: How do I use the 4o image generation model?
A: You can use the 4o image generation model by typing in the shortcut "/create image" in ChatGPT or Sora.
