How to edit, create AI images using ChatGPT

ChatGPT’s built-in image generator makes the process simple. Here’s a clear guide on how to use it effectively.

ChatGPT is no longer just a text-based assistant, it can now generate, edit, and transform images with surprising flexibility. You don’t need a paid subscription, and you don’t need to master complex image-editing tools. Whether you want to create art from scratch or make changes to your own photos, ChatGPT’s built-in image generator makes the process simple. Here’s a clear guide on how to use it effectively.

Chat GPT is the one of the most used AI app (Photo: Adobe Illustrator)

By Ayushmann Chawla

Ayushmann Chawla is the Deputy Chief Content Producer at Hindustan Times. A seasoned tech journalist with years of experience working for some of the industry’s leading media organizations, his articles can also be read on Live Mint. His passion extends beyond journalism—he’s a dedicated automobile enthusiast, always ready to explore the latest in car technology and design. A self-confessed gadget lover, Ayushmann finds joy in testing new devices and sharing his findings with his audience. Instagram: ayushmannchawla

Read moreRead less

Create AI images using text prompts

The simplest way to generate an image in ChatGPT is through a prompt. Just type what you want in the message bar. There’s no specific format required, phrases like “Create an image of…”, “Generate a photo showing…”, or even “Draw…” work instantly.

ChatGPT will begin processing your request, which usually takes under two minutes. On days with heavy server load, results might appear slightly slower.

For best results, be as descriptive as possible. Specify the setting, style, mood, colour palette, or any visual elements you want included. The clearer the description, the better the output.

Create or modify images using your own photos

You can also upload an image and ask ChatGPT to edit, enhance, or recreate it. This is often easier because you don’t need to describe the base composition.

How to upload and edit:

-Tap the “+” icon next to the prompt bar.
-Select Add photos & files.
-Choose the image you want to upload.
-Write what you want changed- remove an object, fix lighting, change the background, add something new, and more.
-If you're uploading from a phone, grant the app permission to access your photo library.

Important: Uploaded images may be used by OpenAI to train future models. To opt out:

Go to Settings > Data Controls > Improve the model for everyone and switch it off.

Edit AI-generated images

If the image ChatGPT generates isn’t exactly what you want, you can revise it without starting from scratch.

To regenerate the entire image:

-Tap the two arrows icon under the image.
-Pick Try again, Add details, or More concise.
-Or simply type a new prompt.

To edit only part of the image:

-Tap the image.
-Select Edit or Select (desktop: use the paintbrush icon).
-Mask the area you want changed.
-Describe the modification you want.

ChatGPT will adjust only the selected section while preserving the rest of the image.

Tips for better image results

Be specific: Describe objects, lighting, mood, framing, and colours.

Use references: Mention styles like anime, photorealistic, cyberpunk, oil painting, etc.

Iterate: AI images improve with feedback. Small refinements go a long way.

Expect variations: ChatGPT is non-deterministic, repeating a prompt rarely gives identical results.

ChatGPT’s image tools can produce illustrations, concept art, product mock-ups, social media visuals, photo edits, and more, without needing Photoshop-level skills. With text prompts, selective editing, and the ability to upload your own photos, the platform gives users a full AI-powered creative studio directly inside the chat window.