Edit: Double checking it looks like they are affiliated with HF but it still is more of an open side project and anyone can contribute to the repository so quality will vary.
I think this is why its failing. The test and criteria that make it more realistic are too hard for the GAN to work out.
[0]: https://github.com/gradio-app/gradio [1]: https://huggingface.co/spaces [2]: http://www.cvlibs.net/publications/Sauer2021NEURIPS.pdf [3]: https://github.com/autonomousvision/projected_gan
That used a finetuned ruDALL-E which is not based on a GAN architecture and is much, much slower than a GAN, albeit the generated Pokemon are more coherent. You can play with it (with no queue) on your own Colab Notebook here: https://colab.research.google.com/drive/1A3t2gQofQGeXo5z1BAr...
Unbelievable how clean looking and artifact-free these neural net generated images have become (in a short short time!) compared to eg. this deconvolved monstrosity
https://www.christies.com/media-library/images/features/arti...
- 0 as Arceus + Shaymin S
- 1 as Lickilicky + Espurr
- 10 as Kirlia + Porygon 2, don't know where the colors are from
- 20 as Shellos + Froslass
- 30 as Roggenrolla/Oddish/Poliwag
- 42 as Garchomp + Trevenant
- I see the Kyurem in 60 but no idea where the tail is from
- 102 as Dragonite + Hitmonlee
Which is interesting because GANs tend not to overfit.
Some manual seeds:
4552 is a corrupted Talonflame
2518 is another Vivillion, and so is 3330, and so is 2216, and so is 3373, and so is 3151 (looks like all Vivillion forms were put in)
3129 is horrific, it's like Glaceon has been stretched into a Wurmple and put on top of a Dracovish head and an unknown body
1742 is a mutilated Slurpuff
2410 is a Tapu mixed with... Corsola-G?
3805 is obviously Magmortar with some dragon head
3546 is clearly Reshiram (with genie arms?), and 1878 is mega Tyranitar (both down to the colours)
2194 is Gible x Joltik
1576 is radioactive Alcremie
2000 is straight up Roselia
Well, that makes sense with the lore
