DALL-E 2 AI Image Generation

OpenAPI and their GPT-3 models are doing incredible things. Thanks for sharing!


Yeah, both text and images are great for dummy content.

1 Like

Guess what. DALL-E 2 is available!

If you haven’t yet checked out OpenAI’s’s DALL-E 2, prepare to have your mind blown!:exploding_head:

No more endless Google searching for the perfect game art. Have AI create it for you in SECONDS!

Check out my demo here:


Did you see this? https://twitter.com/nptacek/status/1548402120075800577


Midjourney is nice too!

I really wish I could have used this. I applied and got through but then found out OpenAI does not support my country, and there’s no way I can work around it (VPN doesn’t work)

Hi, I don’t know how to use API, but is this OpenAI API a way to integrate Dall-E with Glide?

Oh…just wait. There will soon be a way I’m sure :wink:


All the more than Dall-E has an API …OpenAI API

This is cool! Let me put that in Glide, LOL… give me 10 minutes

1 Like

WOW! What column did you use to do that?

google script

Soon you won’t even need Google Script… just wait!


Hahaha, I have so much fun with this… the script is working well!

You can try it here:

go to the Dream Catcher tab

Well done, but 2 questions :

  • Google script, hum, not easy to address for a non-coder (“10 mn”, I am jealous !)
  • Did you use the API DallE that I mentionned above? If yes, won’t you be quickly limited in terms of nb of images, cf. credits?
1 Like

yes, they give the curl…

curl https://api.openai.com/v1/images/generations \
  -H 'Content-Type: application/json' \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
    "prompt": "a white siamese cat",
    "n": 1,
    "size": "1024x1024"

all you need to do is adjust the payload, fetch the result, fish out the URL, and place it into the image component.
I did not find any limitations other than 10 images per call.


I fixed the Glide entry component. When you hit enter instead of the Go button, DALL-E will return an error, so all of you who did that have never seen the image… now it will work no matter what you enter :wink:

I love the “all you need” for a non coder :slight_smile:

1 Like

@Uzo, since I have 0 knowledge about this, sorry for the very basic questions.

To do what you did, is the following approach the right one?


  • User Specific field: “prompt”
  • “Javascript” field: copy your code → but what should we do with the p1, p2, p3… ?
  • User Specific field: “image”

Front end

  • component “entry text”: writing to the USC field “prompt”
  • button action activating the javascript: → how to activate it?
  • component “image”: display the USC field “image”

Many thanks in advance

oh no, I don’t think you can prepare a payload in Glide (I might be wrong, and maybe someone here has done it). I used Google WebApp and fetched the result to Glide.