Stable Diffusion, NovelAI, Machine Learning Art - AI art generation discussion and image dump

[Smug Chuckler]

Anyone knows a site that generates free DALL-E 3 images without bullshit censorship? The one I was using got lobotomized recently.

 

[XL xQgg?QcQCaTYDMjqoDnYpG]

not mine

 

[AmpleApricots]

I've been out of the loop regarding image generation to about maybe a month or two before Dall-e 3 was released. Somebody mind spoon-feeding me if anythinig big happened since then? Besides the various video stuff.

 

[AnOminous]

Looks like Google has a proprietary AI ( Archive ) ready to roll out to the public.

We need Skynet right now.

 

[Balr0g]

Did some Bing ai with Dragons. But rather boring ones:

 

[Levitica]

Image dump of some of my latest shenanigans

 

[Baraadmirer]

Not sure if it was ever posted in the relevant lolcow thread, but there is an SD 1.5 LoRA of Rainer "Drachenlord" Winkler.

 

[Anti Snigger]

I've been fucking around with that nightshade tool, both from the user end and trying to deompile it. If I get the source I'll zip it and post it, but it's extremely low on my priority list rn.

 

[PandaChai]

eggs

serious eggs


casual eggs

 

[AmpleApricots]

Stability released Stable Cascade: https://huggingface.co/stabilityai/stable-cascade

Demo is here: https://huggingface.co/spaces/multimodalart/stable-cascade

 

[PandaChai]

Apologies for posting again so soon, but when I get a prompt set up just right I run it into the mud.

Spoiler: Mughal Ivory Watercolour Miniatures

 

[Sinner's Sandwich]

I wanted a mix between different Pokemon...but I wasn't prepared for...THAT



John Carpenter presents: The Pokething

 

[Catgirl Tyranid]

I wanted a mix between different Pokemon...but I wasn't prepared for...THAT
View attachment 5720740


John Carpenter presents: The Pokething

That is fucking nightmare fuel. Anywho, have some spooky red forests...

Spoiler: Spoooks

Edit: Forgot to mention. Credit to @eDove for the source image all of these are drawn from: https://kiwifarms.net/threads/cursed-images.38757/post-17718018

Spoiler: Source Image

 

[Susanna]

That is fucking nightmare fuel. Anywho, have some spooky red forests...

I quite like these! Maybe I'll try to figure out a prompt for some Simon Stålenhag type scenes...

 

[TerrifyingPterodactyl]

Figured I'd throw my bing ai made pics in here, debating on which one to use for my Easter profile pic.

Spoiler: The eastering

[

Spoiler: Bonus

 

[notorietus]

OpenAI introduced SORA (Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions.) today on their Twitter thread - archive. You can visit it here.

Here is an example. The prompt is: "Beautiful, snowy Tokyo city is bustling. The camera moves through the bustling city street, following several people enjoying the beautiful snowy weather and shopping at nearby stalls. Gorgeous sakura petals are flying through the wind along with snowflakes."

 

[AmpleApricots]

Yeah, can't believe anything you haven't seen with your own eyes anymore.

 

[Susanna]

I wouldn't go that far. For faking content, deepfaking over a video game render produces much more plausible results, and that's been doable for years now. Pay attention to the scale of the people. The woman walking before the pair the camera follows is like half their height, and at one point they pass a grown woman smaller than the left person (who for a few seconds seems to become a child himself).

 

[Slav Power]

Stability released Stable Cascade: https://huggingface.co/stabilityai/stable-cascade

Demo is here: https://huggingface.co/spaces/multimodalart/stable-cascade

1) Can I run this locally
2) How much VRAM and processing power is needed to run it compared to SDXL and SD1.5
3) Is it the same level of open to training to generate anything as SDXL and SD1.5

 

[Breadbassket]

Yeah, can't believe anything you haven't seen with your own eyes anymore.

Just focus on the subtle issues with videos to identity if they are AI made or not (height issues, distortions, strange angling, clipping), the bad part is this stuff will most likely be ironed out as time goes on which will make everything even harder to recognize.