We've improved image generation in the API. Editing with faces, logos, and fine-grained details is now much higher fidelity with features preserved. 🔍 Edit specific objects, create marketing assets with your logo, or adjust facial expressions, poses, and outfits on people.

Here’s a guide to get started: And we’re taking edit requests today! Drop a photo below and what you’d like changed. We’ll use image generation to make it happen. ⬇️

Awesome!!! Is it available in ChatGPT? Also, are you working on reducing the yellow tint in the outputs of the model?

Do these improvements also apply to the ChatGPT web app’s image generation (like with Plus), or is this update strictly limited to the API for now?

Oh this is gonna be a hit

did the overall quality get better or just editing?

but every time i try to edit a photo of a person I get a denial. Nothing bad in my prompt. "Your request was rejected as a result of our safety system. Your request may contain images that is not allowed by our safety system."

pleasee make this available in chatgpt?

This is good upgrade as it maintain structure of inour image but why you guys are not doing something for the yellow tint layer🙄

@sahir2k

Just tried !!! It is absolutely awesome. Now I just need to check how consistent the style is!