It's out for everyone already! I think you get like 100 seconds free when you start, too

SO much phenomenal art. Thanks for abducting me :D

Thanks man! Trying to get back into the posting swing but I am SO bad a platform juggling xD

If you keep your VRAM usage under 10 gigs (I think that's the free cutoff), you might be able to run this in a free account--I enabled a VRAM-conserving training flag

Let me know if you need any help!! I've made the official quickstart videos for DreamStudio and I've written a bunch of tutorials about various aspects of AI art :)

This is just awesome!!! I work at stability.ai and have been beating the "AI art is gonna be a big effing deal" drum here on hive for two years now. Amazing to see you integrating Hive and stable

Heya! I've been summoned!! I am always, always down for a good ole chat about ai art, art philosophy, and related topics. Lately I've been more active over on Twitter(@kaliyuga_ai), but Hive (specifically

It's just a mind-blowing tool. Truly game-changing. I can't believe I get to help :)

THANK YOU :D

Welcome to AI art land :D

Awesome batch this week!! Thank you for the mention <3 :)

I'm still on the Dalle waiting list, so no tips there, but I would recommend joining the Disco Diffusion discord server, as well as checking out the AI art scene on Twitter :)

I'd also recommend looking into Clip-guided diffusion, which is sort of the gold standard for text-to-image generation these days. My pinned post has some resources :) Also, there was recently a Vox video

DALLE-E mini isn't the same thing as DALL-E 2, it's an attempt at recreating DALL-E 2 (which is invite only right now), but open-source. It's a lot of fun, but it's definitely not the same level of insane

Excellent work with Disco! It's cool to see other folks on Hive starting to get into AI art! Have you played around with any of the other text-to-image google colabs around?

This is awesome!!! Did you use VQGAN+Clip for the art?

I'm just butting in to say that more images are probably better! I'd recommend 1000 or more so that you don't overtrain :)

Of course :)

Awesome models!!! I'm so happy to see other people starting to do this :)

Great stuff this week!! Thanks so much for including me :D