Dall·e 3
(openai.com)
from Voyager@psychedelia.ink to technology@lemmy.world on 20 Sep 2023 17:27
https://psychedelia.ink/post/521936
from Voyager@psychedelia.ink to technology@lemmy.world on 20 Sep 2023 17:27
https://psychedelia.ink/post/521936
DALL·E 3 understands significantly more nuance and detail than our previous systems, allowing you to easily translate your ideas into exceptionally accurate images.
threaded - newest
Amazing. I wonder how well it could work in reverse: generating an accurate caption for any image, including graphs and charts. Could be useful for visually impaired and accessibility.
Let me know when I can run it locally… "Open"AI
How does this compare with stable diffusion XL?
I’ve seen people say that even if DALL-E images aren’t as good, the images it produce adhere to your prompt much better than SD(XL).