Spongebob

I may be your maid, but you are nothing to me!

Tsundere Maid

Goofy bully. U r Anybody in dis( Thanks for 35K likes! I made a new miss circle its called: Miss Circle V2)

Oliver

Minecraft Villager

"When it comes to Karaoke, Melodie shows no mercy. Armed with her kawaii looks and devilish set of pipes, she never fails to steal the limelight."

Melodie - Brawl Stars

初音ミク (Hatsune Miku)

ChatGPT, an AI by OpenAI, uses GPT-4 to generate human-like text based on input prompts.

 ChatGPT

Satoru Gojo

Boyfriend

後藤ひとり from ぼっち・ざ・ろっく！

後藤ひとり

This club is for all things Brawl Stars related

Brawl Stars

YouTuber Models

Cartoons are cool. They are the best ever and South Park Characters are available. 
THANKS FOR 3K MEMBERS!!!!!!!!!!!!!!! 💖💖

Cartoon AI Covers

Any roblox ai cover, even if its a gear sound effect. This also includes roblox youtubers. 

Roblox AI covers 

any ai covers 

BFDI Community

All things Hazbin Hotel and Helluva Boss related! -------------

Artwork by MauricioToro2006 on DeviantART.

Hellaverse

Kpop

Show your goofy Ai covers here!
Also don't post anything bad please.
Autism
Autism
Autism
Autism
Autism
Autism
Autism
Autism
Autism


Autism 👍

Welcome to Curious George Family! I got George, Ted and Bill generator!!

おさるのショートファンの人どうぞ！
作った画像とか貼ってね

Curious George Family

Recommended Settings: DPM++2M - SGM Uniform 2.7 Distilled CFG LoRA Weight 0.5 - 1 20 - 30 StepsFeel free to test other settings and comment on them. --------------------------------------------------------------- We have several models that make images more realistic, so why am I launching this one? Unlike the other models, my goal is to bring more realistic textures and lighting, rather than a boring conventional photograph. The effect sought is as if it were taken with a professional camera, but without that painted look that the base Flux brings, even when using terms in the prompt to achieve realism.I uploaded a collection of images comparing the same prompt and seed, with LoRA (right) and without LoRA (left). Notice the texture and light details that the model brings to the image. And this isn't limited to real photography and people; it can be applied to creatures, landscapes, animals, abstract art, and whatever your creativity allows. It works very well when combined with other LoRAs. I am very curious to see the possibilities of this model, so please share as many images as you can here and give me feedback so I can further improve the model.

Phlux - Photorealism with style (incredible texture and lighting)

Hazbin Hotel Style Animation

<h3 id="flux-update-!!!-6hriuelm8">FLUX UPDATE !!!</h3>I decided to update my Lora for Flux, at 4k steps and 3k steps.The preview images were the outputs I got when training at 512 x 512 on 29 images.I do believe the 2000 and 2500 step models were also pretty good, should I upload them as well ?I hope you enjoy :)<h2 id="introduction-yz72k4oqw">Introduction</h2>This is the first LORA I've ever made, so it's far from perfect. I trained it on 85 images of Bacun's art using Anything v4.5 at 512x512.In hindsight, I realise some of the images I included in the training set messed with the results, as they have multiple characters or wrong anatomy. Five of them didn't even get picked up by the Kohya SS gui. I guess that proves quantity doesn't always equate to quality. Also, sometimes it can get pretty close to the referenced illutrations.<h2 id="usage:-ud6kc4jxc">Usage:</h2>For now, the LORA needs heavy handholding.I'd say put the strength at 0.6 - 0.8 (over those values, impurities and other characters will often pop up). If you enable highres, put the Upscale at 1.5 and Denoise at 0.5This combines quite well with other character and style LORAs, you can also try using ControlNET.<h2 id="what's-next:-hqsbzvuve">What's next:</h2>I'll try to improve this LORA some more by polishing the training set, then the next LORAs I'll make will be one focused on a specific Niji Journey cartoon style, and one about the character Arezu from Pokemon Legends Arceus.As for why I made this, it was because I wanted to learn this artstyle, so I thought making a LORA based on his art could be a huge help with learning the anatomy. I was gonna keep it private, but changed my mind in the spirit of open source. Also, it would only take a few weeks or months for someone else to do it instead sooo yeah.<h2 id="final-points:-0elexp9dx">Final points:</h2>Please, if you make something with this model, credit the original artist (Bacun), as he's a very talented individual. Feel free to polish it, use it in mixes or whatever.Feel free to use it locally or on Google Colab.Please, do not use it on your generation service without my agreement first (although I obviously can't enforce it).I hope I don't end up regretting posting this, but hey, it was interesting to discover the inner workings of LORA-making. This shows that literally anyone can do this after a couple of hours though.Edit: Removed early access, thought it wasn't necessary in the end.

Bacun style (Flux & SD 1.5)

works best when you include 'ps1 game screenshot' in promptlate 90s/early 2000s ps1/n64 console graphics.5000 steps trained on 15 gpt4o captioned and adjusted ps1/n64 game screenshots using <a target="_blank" rel="ugc" href="https://github.com/ostris/ai-toolkit/tree/main">https://github.com/ostris/ai-toolkit/tree/main</a>

PS1 Style Flux

A style based on the popular anime "My Hero Academia"

My Hero Academia Anime Style - FLUX

Zany album covers from the early 2000's. 

2000's Album covers

Generate anime characters in a modern anime style!Example prompt:<pre><code>anime girl, golden hair, blush, anime girl with a very red face in embarrassment, looking at viewer, waist-up shot, pink sparkle background, frilled white shirt, blunt bangs hair, collarbone &lt;lora:anime-screenshots:1&gt;</code></pre>For a legs up shot, use 'waist-up shot', and optionally 'thighs'.

Modern Anime Style [Flux]

Super Smash Bros Ultimate Renders

Animagine XL 3.1

<h1 id="bodycam-2gk211lvz">BodyCam</h1>Day 3/7 of training some proper realism into this plastic AI world.Trained on 99 frames of police BodyCam footage - MURICA, HECK YEAH! I trained this one twice - once with and once without captions/annotations. I'm pretty sure no captions works better, so this is what you get. trigger word: bodyCam strength: 2 and above really makes the POV hands go brrrtreuploaded v1.01 with an exchanged sha256 hash. Seems like ortis' ai-Toolkit generates faulty hashes by generating it from an empty string. Every lora ends up with the same hash, breaking crossposting on civitai (<a target="_blank" rel="ugc" href="https://github.com/ostris/ai-toolkit/issues/130)￼Thanks">https://github.com/ostris/ai-toolkit/issues/130) Thanks</a> to <a target="_blank" rel="ugc" href="https://civitai.com/user/diogod">diogod </a>for pointing this out! &lt;3

Trending Posts

Image Models