arfa

🐺

[arfa @arfafax]

My current guess is that it's somehow related to this (Rank promotion warning), which throws an exception if I set the error level to 'raise'.

https://t.co/vdOhh7SR0z

But what tensors are being reshaped incorrectly, and where? 🤔

[arfa @arfafax]

I stumbled across an interesting bug while porting my StyleGAN2 stuff to flax/TPU VMs.

When parallelizing using pmap, if I set my batch size wrong, parts of the output images just *vanish*.

I love when neural networks fail in such visually interesting ways.

[arfa @arfafax]

Here's a notebook for reproducing the effect.
https://t.co/oHsTqUqAM8

I'm still at a bit of a loss as to what's actually going on here. It's almost like the network weights are being corrupted by pmap somehow, but it's strange that it modifies the image in such a striking way.

[arfa @arfafax]

@FranklinLynam @sadlyoddisfying @NoraDotCodes There was an article about the copyright issues related to it in Gizmodo, but there isn't really a definite conclusion since nothing like this has ever been tried in court as far as I know.
https://t.co/uCRGMNsAfz

[arfa @arfafax]

Cursed samples (selfie to furry and furry to selfie).

[arfa @arfafax]

Transfer learning the pretrained GNR checkpoint on my furry dataset, before the heat wave forced me to stop training because my GPU was heating up my apartment too much.

[AK @_akhaliq]

GANs N’ Roses: Stable, Controllable, Diverse Image to Image Translation (works for videos too!)
pdf: https://t.co/deIE02NarD
abs: https://t.co/iN9KZnV9jW
github: https://t.co/F4sdgUm68g

[arfa @arfafax]

Finally, @Kettukaa has launched a store for his foxy AI-generated art!

I'm amazed at how quickly he's managed to learn and apply all the different ML skills involved in creating these.

Check it out and consider supporting him.

🦊

[ket 🏳️‍🌈 @kettukaa]

I opened up an art store! To support a college student and get your hands on some beautiful fox art, please check out my store at https://t.co/uhh0XIIIEt !

[Astralite Heart @AstraliteHeart]

Teaching ponies to speak (client-side playback for https://t.co/J0WqDaKSnX, depth estimation via https://t.co/4VsHJE1G5j, Three.js rendering)

[arfa @arfafax]

@dmvaldman Eventually™

Right now the frontend is built on webdev knowledge from the 90s, and the backend is held together using duct tape and superglue and a Colab notebook that shuts down intermittently.

[arfa @arfafax]

I've been building tools for exploring datasets and models.
Here's Danbooru + ThisAnimeDoesNotExist.
The top is a UMAP clustering of the CLIP embeddings of the images. The hexagons indicate common tags for images in that region. Clicking an image lets you edit it on the bottom.

[hauket.bsky.social @HawkeSouthworth]

AI Generated Furries?? I had a blast making this video and @arfafax I absolutely love the AI you've made!!
https://t.co/qmnBSjibKU

[arfa @arfafax]

TADNE -> e621s after 2.1 million steps of transfer learning.

[Sharon Zhou @realSharonZhou]

GAN training shows an "aha!" moment, when fakes *suddenly* look like reals during training!

Embeddings: 🔴 Reals. 🔵 Fakes, with image samples on the right.

▫️ Generator creates a fake that looks a bit real
▫️ Discriminator has learned enough to start providing useful feedback

[arfa @arfafax]

@harskish @DabhiLevin @AydaoAI Yep, that's what I did for my other ganspace-based editors. But it's a lot of work testing out the different combinations of layers to find which ones do the thing you want.

[arfa @arfafax]

Here's the notebook for playing around with this. I believe @SkyLi0n is planning on releasing a more feature-complete version with some optimizations eventually.
https://t.co/tXuClviHv3

[arfa @arfafax]

I'm still amazed at how powerful @AydaoAI's ThisAnimeDoesNotExist model is. So much potential behind this technology.🤯