ChatGPT

9200 readers

59 users here now

Unofficial ChatGPT community to discuss anything ChatGPT

founded 2 years ago

MODERATORS

marcar

Why Can’t ChatGPT Draw a Full Glass of Wine? - Alex O'Conner (youtu.be)

submitted 2 days ago by HoneyMustardGas to c/chatgpt

10 comments fedilink hide all child comments

Been liking Alex O'Connor's ChatGPT explanation videos and ChatGPT related experiments.

Alex O'Conner makes content related to philosophy and religion but I particularly enjoyed, in addition to this video, one where he gaslights ChatGPT using moral dilemmas.

In this video he tells you the reason why it is so hard to get ChatGPT to do this. Short Answer: most images you find of wine are either empty glasses or partially full because who fills their wine to the top?

you are viewing a single comment's thread
view the rest of the comments

[–] [email protected] 2 points 1 day ago (1 children)

If I ask you to imagine a street with no lanterns, are you imagining lanterns or no lanterns?

[–] [email protected] 2 points 1 day ago* (last edited 1 day ago) (1 children)

Lanterns of course.

Would take an image generation model at least 3 steps which it doesn’t have right now.

A review step to see if the output matches the prompt.

A identification step to detect elements that don't match

A redo step to mix that area in the background image (remove) or regenerates an improvement.

Right now you cant iterate on images. Every minor tweak is a completely new image. At least not with dalle because you cant control the seed.

[–] HoneyMustardGas 1 points 1 day ago

It might be more accurate to use something like Leonardo.AI rather than ChatGPT because you can edit existing images as needed and set the seed. You can even keep a consistent 'character' and reuse it in many pictures. Its dreamshaper model is based on SD. I have had the most accurate results with Leonardo. I don't use ChatGPT/Dall-E for images, it uses too much on a free plan.