Stable Diffusion - AI image generation gallery

[struppigel]

If you consider using Stable Diffusion yourself, I recommend to watch this video for Windows installation:



For Linux just follow the readme in the Github page. Since most people don't have super computers, I recommend this fork:

GitHub - basujindal/stable-diffusion: Optimized Stable Diffusion modified to run on lower GPU VRAM

Optimized Stable Diffusion modified to run on lower GPU VRAM - basujindal/stable-diffusion

github.com

You need an NVIDIA graphics card.

---

I would like to use this thread to share some pictures, seeds and prompts for AI image generation.
When using this yourself, you will notice that it is not magic, the AI will create a lot of disturbing things, especially if you include people or animals. So I let it run for quite some time and just pick out the best images. I think 90% of them you can throw away.

Here some good ones.

Prompt: "cyberpunk hedgehog dressed as batman" seeds 168872, 168881



Prompt: "cyberpunk hedgehog dressed as batman" and using the second image from above as init-img, seeds 371883, 371884



Prompt: "hedgehog with cyberclothing in a fancy car" seed 886743



Prompt: "cyberpunk hedgehog is a superhero" seed 367578

 

[upnorth]

You need an NVIDIA graphics card.

Spoiler: AMD users! :P

 

[eonline]

I was testing this a bit, and it gave this as a result. I'm not very impressed by artificial intelligence, at least not when it comes to generating images.