Mint

joined 1 year ago
[–] Mint@lemmy.one 3 points 1 year ago

Huh, interesting. Mind you it was accidental pun then.

[–] Mint@lemmy.one 1 points 1 year ago

Lmao I didn't even notice until you pointed out, I forget how much the brain just skips over when reading text

[–] Mint@lemmy.one 1 points 1 year ago* (last edited 1 year ago)

That wasn't the prompt I used I just put what is happening in the image description the funny thing is the prompt I had the chicken was just standing there, but Dall'e made it get blasted by the explosion the prompt I used is:

"a blurry, low quality, overexposed, dark-visiblity compression grain of a cctv footage of a chicken standing outside of a KFC that is mid-explosion, the KFC logo is clearly visible and the chicken is in frame, the KFC is being exploded from the inside out"

[–] Mint@lemmy.one 11 points 1 year ago

My assumption is that because the McDonalds frie's packet is slightly covered by a wrapper so it struggles with that situation, I say this because from what I seen image generators have been struggling with that the whole time they existed (if I'm not mistaken) like an object looking weird around the edges

[–] Mint@lemmy.one 10 points 1 year ago

Yes for the most part it can correctly do text. Mind you it isn't the first one to be released that is able to do text DeepFloydIf , if I'm not mistaken is the first generator to be released that can do text - but not many use it.

[–] Mint@lemmy.one 20 points 1 year ago* (last edited 1 year ago) (2 children)

None for the text, Dall'e 3 for the most part tends to nail text, and I would say most of the time, it get text right that you specifically ask for.

So say if you ask for Pepsi most of the time the text will eligible with maybe some oddities at worst, but if you ask for something general like "Magazine cover" and not specify the text that should be on there, it will likely be unlegible.

Though in the case of Pepsi because it is a brand with ton of photos I assume its easier for it to nail, where as say if I asked for a sign with "x" text it out of the four images one or two will be legible, and the more text you will put the more likely for it to be nonsensical.

[–] Mint@lemmy.one 17 points 1 year ago (2 children)

[Created using Bing Create which is currently using Dall'e 3]

[–] Mint@lemmy.one 3 points 1 year ago

[Created using Bing Create which is currently using Dall'e 3]

[–] Mint@lemmy.one 1 points 1 year ago (2 children)

What's the prompt for it? And what are you using Stable Diffusion?

[–] Mint@lemmy.one 11 points 1 year ago

"Taoism or Daoism (/ˈtaʊɪzəm/ ⓘ or /ˈdaʊɪzəm/ ⓘ) is a diverse tradition indigenous to China, variously characterized as both a philosophy and a religion. Taoism emphasizes living in harmony with what is known as the Tao—generally understood as being the impersonal, enigmatic process of transformation ultimately underlying reality." - Wikipedia

view more: ‹ prev next ›