site banner

Friday Fun Thread for May 19, 2023

Be advised: this thread is not for serious in-depth discussion of weighty topics (we have a link for that), this thread is not for anything Culture War related. This thread is for Fun. You got jokes? Share 'em. You got silly questions? Ask 'em.

3
Jump in the discussion.

No email address required.

I designed a proper cover for my ongoing web serial, Ex Nihilo, Nihil Supernum using a combination of AI image generation on-and-offline, Photoshop and Canva!

Certainly looks a lot better than I could have ever hoped to make in the past without hiring someone, especially since I peaked at drawing stick figures and isometric houses, Graphic Design Is My Passion, and I know just enough Photoshop to hang myself with haha.

What do you guys think? All I'm hoping for is to standout compared to the frankly amateurish art that most Royal Road writers commission, which isn't that high a bar to meet.

Cool story, I'll start reading it.

I've been struggling getting together some art for my still unborn webnovel. Turns out my stablediffusion loves giving robots huge pauldrons, even when that's specifically what I don't want, even when I prompt against it.

AI proofreading however, that's a godsend.

Are you running it locally? Are you familiar with in painting or more advanced techniques like controlnet?

Alternatively you can try Bing Image Creator that runs on the latest version of DALLE, it's quite good, and understands context much better than SD.

Well, you've given me the impulse to make it happen. I bought an expensive GPU for AI and I suppose I should get my money's worth.

I like how sometimes SD just throws up a real gem of its own accord without any manipulation but spontaneity isn't cutting it.

If you want very specific and controllable results, by all means use controlnet. You can inherit silhouettes and poses from reference images, such as a humanoid silhouette that you can make into a robot without the issue of pauldrons.

That, or deleting the offending section and inpainting over and over again till it's fixed.

While SD isn't the most advanced model by itself, it's the extensions that let it put up a fight against Midjourney and the like!

Got it working now. It's fascinating how much the open source community can do, yet the heavyweights can just overwhelm it with computational firepower. Google's high-parameter models could produce readable text on demand in photorealistic images before Stable Diffusion even existed.

https://twitter.com/JeffDean/status/1539743557476663300