Good Omens AI

I'm a traditional artist in a torrid love affair with AI. All original posts are AI.

[lemrent]

# AI Model: NovelAI 4.5 Full Quality tags enabled for prompt and negative prompt Base Prompt: decadent textures, painterly, colorful shadows and light, warm tones, incredible color depth, sensual feathers, close up, stripe of sunlight across face Character Prompt: boy, crowley (good omens), red hair, short hair, yellow eyes, hiding behind wing, black wing, peering

[lemrent]

#AI Art

Model: ChatGPT

Prompt:

Title: Devil of Convenience Setting: Crowley sitting at a desk in front of a glowing laptop. Aziraphale stands nearby. Panel 1 Aziraphale (mid-rant, hand in the air):

“AI is terrible, Crowley! It plagiarizes, fabricates…it creates without a soul! That’s not intelligence, that’s heresy!”

Crowley (same position, smug):

“Brilliant, isn't it?”

Panel 2 Crowley (gesturing grandly, still smug):

“Deepfakes, forged homework, bots sowing discord… Humans aren’t just doing my work for me— they’ve automated it! I’ve got it writing my letters to Head Office.”

Panel 3 Setting: Crowley sitting at a desk in front of a glowing laptop, smiling. Aziraphale stands nearby. Aziraphale (leaning in, wide-eyed):

“…It can do that?”

Panel 4 – Park scene Aziraphale and Crowley stand in a park. Aziraphale looks casual and nibbles a red popsicle. Crowley grins and holds vanilla icecream.

Aziraphale: “It’s just a bit of paperwork. No real harm in that.”

Crowley: “Sure, angel.”

[lemrent]

#AI #ChatGPT

Blakes 7 Servalan, by ChatGPT. Still haven't finished it, but I have not forgotten this haunting space beauty. I showed it some screenshots of her and said, "Make a delicate watercolor painting of this woman" and after the filter quit belly-achin, it did deliver.

[lemrent]

I noticed some rude comments on one of your recent posts and just wanted to say that I'm so sorry, I hope this does not discourage you from posting, a lot of people appreciate your work ❤️

That's very kind, thank you! The comments don't bother me any more. A lot of the negativity is well meant, just behind the times. Many artists are using AI now, so eventually people here are going to realize it isn't an Us vs Them issue. I probably won't be posting much because I don't like sharing sloppy generations and I'm waiting on updated inpainting, which could take a couple months. I'm putting aside promising generations to fix up for later, though. Like this sweet moment:

[lemrent]

The boots first session incidentally produced (although not unsurprisingly, since there's only so decent a snake can be in that position) a few slutty Crowley pictures that are neat, but have errors that can't be fixed yet because NAI V4 doesn't have inpainting fully implemented. So, have a cropped picture.

Model: NAI Diffusion V4 Curated Preview

[lemrent]

So genuine question here

If you're a traditional artist, why use AI to make the images you want to bring to fruition? Assuming that making art to be an activity you enjoy, why outsource it, when creating it yourself would be so much more satisfying and enjoyable?

If we're talking about drawing and painting, I don't find it enjoyable. I put in the work, 8 hours a day for years, did all the core classes for the major but had to drop out just shy of the degree, to learn the skills, because at the time I wanted pictures and there wasn't an alternative. I've been told that I'm good at it, but I never fell in love. It's a useful skill to fall back on if I need to do something like sketch an idea or texture a model, but now I only do it as a last resort.

People say pick up a pencil and anyone can draw, but that doesn't mean everyone will enjoy it. I still make other kinds of art things that aren't AI related because I'm a flow junkie and pick up anything within reach to see if I can figure it out. Beyond that, I don't view AI images as a replacement of drawing and painting. The end result can look the same, but as a medium they're different things. Different process, different skills. If anyone is reading this and wondering how AI is a skill, dig into the tools and find out. Or watch a video, maybe— I'm sure someone has recorded themselves doing it. Even if I did still enjoy drawing, I think I'd still like using AI because it's its own unique thing.

Is it disingenuous to call myself a traditional artist? Maybe? But it also feels wrong to say that I'm not when I trained for that and made a living with it and am still making stuff. There's something about calling myself an artist that feels pretentious and I rankle at the label, at the idea of defining and gatekeeping that term at all, but I put that in my description to combat the assumption that people that use AI do so because they are uncreative and unskilled, when many artists are picking up AI and playing with it and exploring it as a medium, because that is fundamentally what artists do.

[lemrent]

"Boots first" perspective

Model: NAI Diffusion V4 Curated Preview

[lemrent]

OH MY GOD! Your blog is so fucking awesome! I'm a new artist recently dipping my toes into AI art, I'm still too shy to share my work online, but your blog has been a huge inspiration to me. Thank you for sharing it <3

What's really cool about this is that you're starting your journey alongside the birth of a new medium, and your experience with these tools, and therefore your art, will be fundamentally different from everyone that's come before you. You're part of a new generation of artists (whatever your age!) that will develop an entirely new and unique style that will become the future. I hope that I'm around in ten or twenty years to see what that looks like.

[probably-enjoying-this]

Happy Holidays!

Kerr Avon and Roj Blake from Blake's 7, AI generated.

[lemrent]

NovelAI's new v4 image generator is blowing my mind. These pictures were done without Lora, controlnet, Photoshop, inpainting, or any human effort beyond simple text, done on remote servers in under five seconds each. We are truly that much closer to a one-click magic pretty picture generator.

NovelAI *does* have inpainting and a form of controlnet, so these could have been cleaned up, but what's really impressing me right now is how lazy they are. The new v4 supposedly allows for advanced interactions that define an object and actions that can be acted upon it, as well as specific placement of things, like Flux and the newer image generators can do. The model is a preview, so all features haven't been implemented yet.

Just a couple of years ago, AI could not handle the things we're seeing here, like different body types, wrinkles, slit pupils, or the chainmail tie, the concept of which destroyed Stable Diffusion.

(Note: If you like text generation, NovelAI is among the best and image gen and text gen come bundled in the same paid service.)

Example Prompt:

Two men in a greenhouse, cartoon style, quirky style, looking at each other, gazing adoringly

Character 1:

man, Aziraphale, Good Omens, tan suit, brown vest, white collared shirt, tartan bowtie, hands clasped, smiling

Character 2:

Man, Crowley, Good Omens, yellow eyes, slit pupils, sunglasses, red hair, short hair, black jacket, quilted jacket, silver chain necktie, holding a potted plant, smiling

[oxideblack]

[acitymadeofsong]

Blake’s 7 + Onion Headlines

[bunn1cula-deactivated20240409]

[acitymadeofsong]

New additions

[incorrect-blakes7]

THESE HURT ME

[lemrent]

found this while rifling through folders for another project. cute

[probably-enjoying-this]

Happy Halloween 🎃

[lemrent]

This is how I imagined the drop pods looking when I read Nightborn, with the core behind them.

[lemrent]

Please return to traditional art. Please.

I never left. I've got a lot of projects going on at any given time. I'm working on Good Omens jewelry for metal 3D printing since I like modeling and have been meaning to learn how to convert that to print. Textgen AI is definitely taking the lion's share of my time at the moment, though.

[lemrent]

#AI Art #Stable Diffusion