Home Artists Posts Import Register

Content

If you been following the AI projects for Image Generation, you must had at least head of Stable Diffusion. It let create images like this homer thanos from a test of mine:


Well, they just got a Github:

https://github.com/CompVis/stable-diffusion

The trained model is still not available, but this allow me to already start working with the code:

I do plan to start with this simple GUI, so is easy to enjoy SD and then to expand it to create a pretty cool tool.
From their post:
Stable diffusion runs on under 10 GB of VRAM on consumer GPUs, generating images at 512x512 pixels in a few seconds.

So I will upgrade my computer to get a 12vram card, that way will be a lot easier to develop this tool.


Side node: Rife-App model seen to be training correctly, today I will learn if my new modifications really helped the model or not.

Comments

Brew MeUp

Niiceeee... I managed to get into the closed beta,.. it is a seriously impressive AI,.. and they are saying a lot of things that indicate they are working on an animation AI as well.. exciting times ahead!

DAINAPP

Cogvideo already show a glimpse on what to come, but yeah, I can't even begin to imagine what tools we will have until a year from now.