AI Generated Images
Community for AI image generation. Any models are allowed. Creativity is valuable! It is recommended to post the model used for reference, but not a rule.
No explicit violence, gore, or nudity.
This is not a NSFW community although exceptions are sometimes made. Any NSFW posts must be marked as NSFW and may be removed at any moderator's discretion. Any suggestive imagery may be removed at any time.
Refer to https://lemmynsfw.com/ for any NSFW imagery.
No misconduct: Harassment, Abuse or assault, Bullying, Illegal activity, Discrimination, Racism, Trolling, Bigotry.
AI Generated Videos are allowed under the same rules. Photosensitivity warning required for any flashing videos.
To embed images type:
“![](put image url in here)”
Follow all sh.itjust.works rules.
Community Challenge Past Entries
Related communities:
- [email protected]
Useful general AI discussion - [email protected]
Photo-realistic AI images - [email protected] Stable Diffusion Art
- [email protected] Stable Diffusion Anime Art
- [email protected] AI art generated through bots
- [email protected]
NSFW weird and surreal images - [email protected]
NSFW AI generated porn
Ooh, these are really nicely done, I especially like Nightmare Code. I can totally picture the story. And the tagline has that classic campy wordplay.
Those are great!
I love how you made them look almost like worn paperback covers. Absolutely nails my memory of every Goosebumps book I took out of the library; those things were beat up 😅
This is nice!!
Thanks!! 😃
Wow, that looks very good!
With some janky photoshop I was able to make "DREAM SEEKER", the one who seeks to steal the dreams of others and feeds them harsh reality in return.
Futura Condensed Medium is the font. Both for the title and tagline.
This is really not my strong suit, but it was fun nonetheless. Even the titles and blurbs are AI generated, original idea is still mine :)
Blurb: When the new disco club opened in town, Jake and his friends couldn't wait to check it out. They loved dancing and having fun, and the club promised to be the coolest place ever. But they soon discovered that the club had a dark secret: it was run by zombies who wanted to turn everyone into undead dancers! Now Jake and his friends have to escape from the disco zombies before they become their next victims. Will they make it out alive or will they join the groovy graveyard? Find out in Goosebumps: Disco of the Dead!
Prompt: style of goosebumps, full - body, low - angle, a disco zombie, wearing a leisure suit, on the dance floor
Blurb: You've been working hard on your project for months, but when you come to the office one morning, you find that all your files are gone. No backups, no traces, no clues. Who could have done this? And why? You have to find out before your boss fires you, or worse. But as you start to investigate, you realize that something sinister is going on in your workplace. There are strange noises, creepy shadows, and mysterious messages. And you're not the only one who's missing something. Your co-workers are acting weird, and some of them have disappeared altogether. What is happening in this office of horrors? And can you survive long enough to finish your project? Find out in... The Missing Project!
Prompt: style of goosebumps, scared man with computer, computer is smoking, brown, red, dark
For those still busy with their entry, I found this template for a Goosebumps book cover. The Photoshop and Affinity Photo files are very handy.
I love the AI story addition!
Some of my favorite generated story titles that didn't make it into the submission:
- Night of the Living Groove: Can You Survive the Funk?
- The GANs of Doom: Beware of the Generative Adversarial Networks
- The Deadline Demon: He'll Make You Work Till You Drop
- Night of the Living Deadlines: How to Survive When Everything is Due Tomorrow
- Monster Blood IV: It's Gluten-Free, But It Still Makes You Grow
- The Abominable Snowman of Pasadena: He's Not Here for a Vacation
- Beware, the Boss!: He Knows When You're Slacking Off
That last one hit a little bit too close to home :)
So if anyone is still trying to think of a title, they're all free for the taking.
I had fun trying to do this "in camera" without any editing after generation. I ended up using segmentation but after playing around with a lot of different options for what colors to use (trying stone, book, window, painting), I gave up and just made it black and white and still used segmentation.
Hang on, so you're saying all the text is "in camera" too? How?
Segmentation controlnet with an image of the cover template with different parts being different colors as the input. The segmentation controlnet makes Stablediffusion treats different colors as different things, so it keeps each part distinct. If you use colors that aren't in the actual color reference chart, it just sorta improvises, so I used black and white. On one I used the color that corresponds to painting,picture for the area inside the "frame" where the actual art is. Since I was doing it all in one generation with one prompt I just sorta had to accept what it gave me for the colors and textures of the text and borders.
That is absolutely wild. Thanks for sharing.
Quick question, is editing allowed (Photoshop, etc) or do we stick strictly to prompting and other AI tools only? Or maybe it doesn't matter all that much and I'm thinking too hard about it?
There was nothing in the rules about it, and all the contestants so far have done it, so I'd say use it. That's a good question for next time though.
For me personally, I like using all the tools at our disposal to create the best image possible. But I can also see how that might raise the bar for people who aren't skilled with Photoshop and create a barrier to entry. So I'd be okay with either decision.
Yeah, I also would like to keep the process as "pure" as possible but, for something like this, editing the AI results into a Goosebumps frame makes sense (since AI is so terrible with text).
I'm probably thinking too hard about it lol.
Goosebumps frame isn't required, just simply wanted to do it because I thought it would be fun to practice basic image editing/layering with Krita. There's definitely no way to stop anyone from editing their AI generated images, so it's better to just allow that freedom. The whole point of these challenges is inclusivity, anyone can use AI to generate high quality images without years of artistic knowledge.
I don't mind if people use Photoshop, or another tool, as long as an AI generated image forms the base.
Personally, I love it when people share their workflow. Everyone benefits when we share our knowledge and experience.
Shout out to Pixlr E. It's a free, web-based Photoshop alternative, and it's surprisingly full-featured and easy to use.