OpenAI has rolled out a brand new picture technology system instantly built-in with GPT-4o. This method permits the AI to entry its data base and dialog context when creating photos.
This integration is alleged to allow extra contextually related and correct visible outputs.
OpenAI’s announcement reads:
“GPT‑4o picture technology excels at precisely rendering textual content, exactly following prompts, and leveraging 4o’s inherent data base and chat context—together with reworking uploaded photos or utilizing them as visible inspiration. These capabilities make it simpler to create precisely the picture you envision, serving to you talk extra successfully via visuals and advancing picture technology right into a sensible software with precision and energy.”
Right here’s every thing else you’ll want to know.
Technical Capabilities
OpenAI highlights the next capabilities of its new picture technology system:
- It precisely renders textual content inside photos.
- It permits customers to refine photos via dialog whereas holding a constant fashion.
- It helps advanced prompts with as much as 20 totally different objects.
- It will probably generate photos primarily based on uploaded references.
- It creates visuals utilizing info from GPT-4o’s coaching information.
OpenAI states in its announcement:
“As a result of picture technology is now native to GPT‑4o, you may refine photos via pure dialog. GPT‑4o can construct upon photos and textual content in chat context, making certain consistency all through. For instance, if you happen to’re designing a online game character, the character’s look stays coherent throughout a number of iterations as you refine and experiment.”
Examples
To reveal character consistency, right here’s an instance exhibiting a cat after which that very same cat with a hat and monocle.
Right here’s a extra sensible instance for entrepreneurs, demonstrating textual content technology: a full restaurant menu generated with an in depth immediate.
Screenshot from: openai.com/index/introducing-4o-image-generation/, March 2025.There are dozens extra examples in OpenAI’s announcement publish, a lot of which include a number of prompts and follow-ups.
Limitations
OpenAI admits:
“Our mannequin isn’t good. We’re conscious of a number of limitations for the time being which we are going to work to deal with via mannequin enhancements after the preliminary launch.”
The corporate notes the next limitations of its new picture technology system:
- Cropping: GPT-4o generally crops lengthy photos, like posters, too intently on the backside.
- Hallucinations: This mannequin can create false info, particularly with obscure prompts.
- Excessive Mixing Issues: It struggles to precisely depict greater than 10 to twenty ideas without delay, like an entire periodic desk.
- Multilingual Textual content: The mannequin can have points exhibiting non-Latin characters, resulting in errors.
- Modifying: Requests to edit particular picture components might change different areas or create new errors. It additionally struggles to maintain faces constant in uploaded photos.
- Info Density: The mannequin has issue exhibiting detailed info at small sizes.
Search Implications
This replace adjustments AI picture technology from primarily ornamental makes use of to extra sensible features in enterprise and communication.
Web sites can use AI-generated photos however with essential concerns.
Google’s pointers don’t prohibit AI-generated visuals, focusing as an alternative on whether or not content material supplies worth no matter the way it’s produced.
Following these finest practices is really useful:
- Utilizing C2PA metadata (which GPT-4o provides routinely) to take care of transparency
- Including correct alt textual content for accessibility and indexing
- Guaranteeing photos serve consumer intent reasonably than simply filling house
- Creating distinctive visuals reasonably than generic AI templates
Google Search Advocate John Mueller has expressed a destructive opinion relating to AI-generated photos. Whereas his private preferences don’t affect Google’s algorithms, they might point out how others really feel about AI photos.
Screenshot from: bsky.app/profile/johnmu.com, March 2025.Be aware that Google is implementing measures to label AI-generated photos in search outcomes.
Availability
The function is now accessible to ChatGPT customers with Plus, Professional, Group, or Free plans. Entry for Enterprise and Edu customers will likely be accessible quickly.
Builders can anticipate API entry within the coming weeks. Due to increased processing wants, picture technology takes about one minute on common.
Featured Picture: PatrickAssale/Shutterstock
