How Good Is DALL-E Mini at Origami?
origami.kosmulski.org
How Good Is DALL-E Mini at Origami?
1–10 of 31 posts
Re: How Good Is DALL-E Mini at Origami?
#2Slightly OT, although there might be some sort of connection with origami: does anyone know if DALL-E can produce vector images?
Re: How Good Is DALL-E Mini at Origami?
#3Slightly OT, although there might be some sort of connection with origami: does anyone know if DALL-E can produce vector images?
No, it's trained on pixels and it generates pixels. You could make a vector AI if you had millions of labeled vector inputs.
Re: How Good Is DALL-E Mini at Origami?
#4Slightly OT, although there might be some sort of connection with origami: does anyone know if DALL-E can produce vector images?
No, it's trained on pixels and it generates pixels. You could make a vector AI if you had millions of labeled vector inputs.
GPT-3 already seems capable of generating SVG. I prompted it with:
Re: How Good Is DALL-E Mini at Origami?
#5Earlier quoted context omitted.
No, it's trained on pixels and it generates pixels. You could make a vector AI if you had millions of labeled vector inputs.
GPT-3 already seems capable of generating SVG. I prompted it with: and it completed it to the following: which looks like this: https://i.imgur.com/sHpv4Ii.png
Do androids dream of disemboweled cubist ducks?
Re: How Good Is DALL-E Mini at Origami?
#6Earlier quoted context omitted.
No, it's trained on pixels and it generates pixels. You could make a vector AI if you had millions of labeled vector inputs.
GPT-3 already seems capable of generating SVG. I prompted it with: and it completed it to the following: which looks like this: https://i.imgur.com/sHpv4Ii.png
Guinea pig wearing a hat?
Re: How Good Is DALL-E Mini at Origami?
#7Earlier quoted context omitted.
GPT-3 already seems capable of generating SVG. I prompted it with: and it completed it to the following: which looks like this: https://i.imgur.com/sHpv4Ii.png
Guinea pig wearing a hat? https://i.imgur.com/Q8KWdAO.png
Do some of them have no eye? Are they proper pirates?
Re: How Good Is DALL-E Mini at Origami?
#8Earlier quoted context omitted.
No, it's trained on pixels and it generates pixels. You could make a vector AI if you had millions of labeled vector inputs.
GPT-3 already seems capable of generating SVG. I prompted it with: and it completed it to the following: which looks like this: https://i.imgur.com/sHpv4Ii.png
Yes, but that's just random SVG (xml); it would be amazing to be able to ask for specific shapes or silhouettes.
Re: How Good Is DALL-E Mini at Origami?
#9Some of the issues seemingly stem from the model's either poor or mis-understanding of the input language... I wonder what a fusion of DALL-E + GPT3 or LaMBDA, where the text-based models perform prompt interpretations, would look like.
This may be a naïve thought as my understanding of all models mentioned is superficial at best.
Re: How Good Is DALL-E Mini at Origami?
#10I know this is a little bit banal, but I feel like:
(1) the author is thinking about "origami"
(2) the model is only able to create "pictures of origami"
The model can only ever be trained on pictures of origami. Thus, the model can generate images that are getting close to "pictures of origami", but (as pictures necessarily are abstracted 2d projections) this might still be way way way off from "origami". Not knowing about actual origami, only ever having seen pictures, I thought most of the generated images were quite good. The actual experienced origami-folding person doesn't see it that way.
I hope my thought is phrased clearly enough, I am having trouble finding the right words here.