ChatGPT Images 2.0

ChatGPT Images 2.0 on Morphic lets you generate images from text and edit existing images using OpenAI's latest model. Describe a product label, a multilingual poster, or an app interface and the model renders the text correctly, with photorealistic detail.

How to access ChatGPT Images 2.0 on Morphic

1. Open a new or existing project on Morphic

2. Switch the mode to 'Image' in the prompt bar at the bottom

1. Click the model selector and select 'GPT Image 2'

1. Write your prompt describing what you want to generate

2. (Optional) Upload a reference image if you want to edit an existing image rather than generate it from scratch

3. Click 'Generate'

Tips for better results

Do	Don't
Put the exact text you want in quotation marks, like "OPEN LATE" or "Summit Roast"	Leave text unquoted and hope the model spells it right
Add a spatial direction for text placement ("centered at the top," "bottom-left corner")	Skip placement instructions and assume the model will guess
Start your prompt with the visual style before the subject ("a photorealistic 35mm photograph of...")	Describe everything first and add the style as an afterthought
Name a real lighting setup ("soft window light from the left," "natural fluorescent lighting")	Say "good lighting" or leave it out entirely
Upload a reference image for edits and describe what changes vs. what stays the same	Try to describe an existing image from memory instead of uploading it

That's how you use ChatGPT Images 2.0 on Morphic. Use it when your visuals need accurate text, realistic detail, or edits to an existing image without starting over.

If you have any trouble or have any questions, feel free to reach out. We're happy to help. Write to us at [e-mail].