[HN Gopher] Each country as a Pokemon, using Stable Diffusion
___________________________________________________________________
Each country as a Pokemon, using Stable Diffusion
Author : montebicyclelo
Score : 45 points
Date : 2022-09-20 21:15 UTC (1 hours ago)
(HTM) web link (github.com)
(TXT) w3m dump (github.com)
| cookiengineer wrote:
| I was looking at Germany, expecting a bureaucrat pokemon. I was a
| little disappointed :D
| Shorel wrote:
| Chad looks more like Colombia than Colombia.
|
| I can't see any logic in Venezuela.
| TillE wrote:
| A bunch of these (eg, Cameroon) have a weird extra limb, which is
| basically consistent with my experience of Stable Diffusion: it
| frequently produces images that are physically impossible,
| architecturally nonsensical, etc.
|
| I'm not sure other models are better. I don't think they are.
| Seems like a big problem that won't be easy to solve.
| Magi604 wrote:
| Interesting premise, but unfortunately the results are not.
| There's nothing in the designs of the Pokemon that ties them to
| their connected country, so they all just end up looking generic.
| montebicyclelo wrote:
| Canada has a maple leaf for a tail :D [1]
|
| But yep, I do hope to improve this. (And if I don't, I'm sure
| someone else will.)
|
| [1] https://github.com/sradc/each-country-as-a-pokemon-stable-
| di...
| aaaaaaaaata wrote:
| Good attitude!
| jannyfer wrote:
| I spot checked a few and the generated pokemon colours matched
| their flags.
| Harlekuin wrote:
| Australia is a kangaroo with nipple tassels and a missing toe -
| pretty spot on
| bee_rider wrote:
| Ukraine got the colors right at least.
|
| Vatican City is pretty good.
|
| It is sort of interesting that United States and US Virgin
| Islands both have blue bodies and red paws.
| Xeoncross wrote:
| It's a been couple decades since I first saw pokemon, but is this
| what they look like now? Most of them kind of look like the same
| 2-legged, mammal thing in different primary colors.
| dragontamer wrote:
| https://bulbapedia.bulbagarden.net/wiki/Lechonk_(Pok%C3%A9mo...
|
| https://bulbapedia.bulbagarden.net/wiki/Mimikyu_(Pok%C3%A9mo...
|
| https://bulbapedia.bulbagarden.net/wiki/Greninja_(Pok%C3%A9m...
|
| https://bulbapedia.bulbagarden.net/wiki/Buzzwole_(Pok%C3%A9m...
|
| https://bulbapedia.bulbagarden.net/wiki/Corviknight_(Pok%C3%...
|
| ------
|
| Honestly, these monsters don't look much like Pokemon to me.
| But maybe cause I've played a good chunk of Pokemon.
|
| I think its impressive that Stable Diffusion can make such
| "artwork", but its not quite "Pokemon". There's something
| terrible going on with Stable Diffusion's generation of eyes
| here, I don't know quite what, but its like Stable Diffusion
| doesn't understand "anime perspective" at all.
|
| The eyes are often "bouncing" between 3/4ths perspective and
| straight-at-the-camera perspective, sometimes within the same
| generated monster. The algorithm is also trying to generate a
| 2nd face in the bottom-right of a lot of these pictures, for
| some reason.
| sbf501 wrote:
| It's about catching/buying them all. Best marketing strategy
| ever.
| Multicomp wrote:
| Some are two legged, others are 4, still others have 6 limbs
| like centaurs, and even so others have a 4 legged creature and
| a two legged TV stand thing following them around.
|
| But I suspect their similar texture is because stable diffusion
| was trained on the official artwork for Pokemon rather than
| their in-game sprites/models, though that is just a guess.
| oneoff786 wrote:
| Thankfully no, they're still good
| char_star_star wrote:
| Now just train a model to generate types and move sets from
| Pokemon images and you can do procedurally generated Pokemon
| games.
| Multicomp wrote:
| I am incredibly impressed with this post and with the novel
| results of Stable Diffusion already.
|
| The result for Ivory Coast looks like the latest+ dark n edgy
| brooding Pokemon for ash and company to love on and teach that
| life is not all grimdark after all, some 5 or so episodes after
| Ash gets to a new region and re learns type matchups for the Nth
| time.
|
| +next in line after Mewtwo and Lucario
| oneoff786 wrote:
| Vatican City is great. The rest... meh. These feel a bit overfit
| to me. I can tell with relative high confidence which pokemon is.
|
| Ukraine is kind of cool with a custom articuno vibe
___________________________________________________________________
(page generated 2022-09-20 23:02 UTC)