“Kyubey from Madoka Magica, white creature with four ears, 4k high quality anime, screenshot from Puella Magi Madoka Magica” (I fiddled with the prompt because I don’t think it knows Madoka quiiiiite well enough, and was giving me vaguely Kyubey-themed anime girls.)
Since OpenAI optimized it’s output for things as you suggested in your article (dresses, animals) I believe hidden in the depths of the AI, it can pull pictures such as Kyubey but requires an un-optimized input (as in broken English or maybe in Japanese for this specific one)
So basically telling an alien what to generate in their own language… And the problem is that we don’t know what this is with the information currently available (with tests from DALL-E 1)
So it knows the color-scheme and then tries to make some sort of Pokémon off of it. I think maybe the AI believes it is creating a fictional screenshot concept art type thing. Even when you give it a show to go off of, it doesn’t understand what to pull off of. I think whenever I get access to dall-e 2, I will try figuring out key buzz words to give it.
I also think since I added “pixiv” since most of the pictures there are anthropomorphic, it kinda just tagged it in. I believe the prompting is much more complicated than we think and requires further evaluation. There has to be certain phrases in specific orders the AI can use better that the community doesn’t know yet.
“Kyubey from Madoka Magica swimming in a pool of soul-gems, 4K anime, digital art, pixiv, hyperrealistic beautiful”. It’s definitely confused on some of these about whether they’re anime girls, but it gets the vibe!
Ohhhh so maybe next prompt we can specify that they are not “anime girls” Also, these are very cute lol. The first one is the most accurate and the fact that the AI understands what Kyubey looks like means that it is probably looking for very specific wording to get it accurate
It looks like all the other modifiers override the “in the style of chis sweet home” I think the AI needs: “A Cute Cat Creature Character: Kyubey, Anime Show: Puella Magi Madoka Magica, Style: Screenshot From Anime Show. Exact screenshot, no variations from original artwork”
Suggestion: Can it do Kyubey from Madoka Magica?
Kyubey from Madoka Magica, photorealistic, high quality anime, 4K, pixiv, digital picture
Kyubey from Madoka Magica swimming in a pool of soul-gems, 4K anime, digital art, pixiv, hyperrealistic beautiful
Kyubey from Puella Magi Madoka Magica in the style of Chi’s Sweet Home Anime, 4K digital art anime, pixiv
(Feel free to change these around)
“Kyubey from Madoka Magica, white creature with four ears, 4k high quality anime, screenshot from Puella Magi Madoka Magica” (I fiddled with the prompt because I don’t think it knows Madoka quiiiiite well enough, and was giving me vaguely Kyubey-themed anime girls.)
Since OpenAI optimized it’s output for things as you suggested in your article (dresses, animals) I believe hidden in the depths of the AI, it can pull pictures such as Kyubey but requires an un-optimized input (as in broken English or maybe in Japanese for this specific one)
So basically telling an alien what to generate in their own language… And the problem is that we don’t know what this is with the information currently available (with tests from DALL-E 1)
So it knows the color-scheme and then tries to make some sort of Pokémon off of it. I think maybe the AI believes it is creating a fictional screenshot concept art type thing. Even when you give it a show to go off of, it doesn’t understand what to pull off of. I think whenever I get access to dall-e 2, I will try figuring out key buzz words to give it.
I also think since I added “pixiv” since most of the pictures there are anthropomorphic, it kinda just tagged it in. I believe the prompting is much more complicated than we think and requires further evaluation. There has to be certain phrases in specific orders the AI can use better that the community doesn’t know yet.
“Kyubey from Madoka Magica swimming in a pool of soul-gems, 4K anime, digital art, pixiv, hyperrealistic beautiful”. It’s definitely confused on some of these about whether they’re anime girls, but it gets the vibe!
Ohhhh so maybe next prompt we can specify that they are not “anime girls” Also, these are very cute lol. The first one is the most accurate and the fact that the AI understands what Kyubey looks like means that it is probably looking for very specific wording to get it accurate
“Kyubey from Puella Magi Madoka Magica in the style of Chi’s Sweet Home Anime, 4K digital art anime, pixiv”
It looks like all the other modifiers override the “in the style of chis sweet home” I think the AI needs: “A Cute Cat Creature Character: Kyubey, Anime Show: Puella Magi Madoka Magica, Style: Screenshot From Anime Show. Exact screenshot, no variations from original artwork”