Text to image AI - made simple

I read this post elsewhere. Is there a chance Glide could consider harnessing it when it becomes available? Looks incredible.


Breaking News: Now everyone can use AI Image Generation

(without technical skills or technical knowledge) ! Watch this:

Open AI are about to release DALL-E 3, the new text-to-image generation model in ChatGPT and it’s accessible to everyone.

The new tool makes it easy for anyone to use AI image generation without being technical and without knowing how to write complex prompts. The model can translate nuanced requests into very detailed and accurate images.

Here are 3 key takeaways you need to know:

  1. The DALL-E 3 is now just part of ChatGPT

With the DALL-E 3 Image Model, you can simply type prompts directly into ChatGPT and it will create the images.

There is no separate application or process. Previously if you wanted to use AI image generation, you most likely have been using MidJourney which you had to access a different application and do it through Discord. It was a bit long winded and technical.

  1. DALLE-E 3 requires much more simple command prompts than previously.

Example of how to prompt MidJourney:

a Shakespeare stage play, 16mm film, yellow mist, atmospheric, set design by Michel Crête, Aerial acrobatics design by André Simard, hyperrealistic, 4K, Octane render, unreal engine, –ar 9:16 –uplight

Example of how to prompt DALLE-E 3:

To generate the images in the video you are watching, they have simply typed

“My 5 year-old keeps talking about a super-duper sunflower hedgehog - - what does it look like?”


“Can you show me Larry’s House”

This allows almost everyone the opportunity to use AI to generate wild and wonderful images, with a couple of words and a click of a button.

  1. Sam Altman, CEO of OpenAI said BAAA will be released to ChatGPT + Users and Enterprise over the next couple of weeks.

I don’t know about you but the idea of having an AI image generator, that is native to ChatGPT and has the capabilities of MidJourney V5 is quite remarkable and will be one hell of a moment for AI.

If you liked this post and you want to be kept up to date with breaking news in AI, follow me Chris Donnelly and repost :recycle: this with your network.


Hope they push this to the web version and the API at the same time, would be nice for some conversational AI that can edit the images as it go on.