Got a new graphics card that generates everything faster (RTX 3060 12GB).

Here's the prompt I used for these pictures. Insert the correct pony, though in some cases I put in generic terms like unicorn or filly. Also keep in mind I filtered out a lot of the ones that had messups (a surprising number of double horned unicorns), or were verging on nsfw. You might notice it ignoring parts of the prompt, too (and I kinda forgot blushing was in there...).

Read More

I posted this to a group about ai, but thought I'd post it on my blog, too...

Just thought it'd be fun to create some ai art in stable diffusion by drawing badly, and document it.

So, step 1 was that I drew this bad 512x512 picture.

I put that into img2img using ponyv4 (purplesmart), with this prompt:
Prompt: A cute happy pony standing on a hill with one leg in the air, one ear down, line art

Read More

sweetie belle giraffe
Steps: 20, Sampler: DPM++ SDE, CFG scale: 7, Seed: 4275345952, Size: 512x768, Model hash: 6d22788a2c, Model: poneart075-075ponyv3-pruned

sweetie belle giraffe
Steps: 20, Sampler: DPM++ SDE, CFG scale: 7, Seed: 4275345954, Size: 512x768, Model hash: 6d22788a2c, Model: poneart075-075ponyv3-pruned

I said in my last blog post that I downloaded and installed Stable Diffusion, an AI image generator thingy. I'm obviously still playing with it.

Read More

Welcome to Neko Magic Academy, where catgirls learn to control their magical powers! (And get their magical tails under control, and keep them from detaching themselves...)

Read More

I've been interested in trying out ai image generation for a while, ethical questions aside. While there are plenty of ai image generators online, they usually have limitations or want to charge you money eventually, and I thought it'd be more fun to set it up on my own computer, if it'd run.

Read More