Resource directory
Find what you need for your workflow.
Guides: techniques, setup, and troubleshootingSearch Sweet Tea Pipes, external workflows, models, node packs, and guides in one evidence-linked catalog.
Start with a workflow instead ↗Search results
All resources
20 shown of 42,152
Unstable Babies
I'm trying to recreate some of the art from board game "Unstable Unicorns", starting with the babies, but it seems kinda hard to get some variations that fit with the game artstyle.
[IllustriousXL v0.1 LoCon] Juniper Actias | VTuber
Trigger + Appearance: juniperactias, monster girl, arthropod girl, moth girl, white skin, insect wings, extra arms, fewer digits, carapace, long hair, multicolored hair, white hair, green hair, hair over one eye,...
moeb-style
Originally posted to HuggingFace by sd-concepts-library Moeb Style on Stable Diffusion This is the concept taught to Stable Diffusion via Textual Inversion. You can load this concept into the Stable Conceptualizer...
XenoBABE - Vickie Zane - The Popular Girl
Vickie Zane was that super popular girl through high school and college. Nice to everyone, even the freaks and geeks, she seemingly has no idea just how beautiful she really is. The bad news? She's out of your...
Ningguang (凝光) - Genshin Impact (原神)
ningguang, grey hair, hair ornament, hairpin, long hair, parted bangs, (red eyes:1.5), sidelocks, streaked hair, red hair,
MiniMax-H3 GGUF (fl2va + ref2va) Q5_1 / Q4_0
CIVITAI IS RENAMING EVERY DOWNLOADED FILE THE SAME THING. MAKE SURE YOU SAVE-AS AND NAME THE FILE SO YOU KNOW WHAT IT IS.
Hitori Gotou (後藤 ひとり) - Bocchi the Rock (ぼっち・ざ・ろっく!)
hitori gotou, blue eyes, cube hair ornament, hair between eyes, hair ornament, pink hair, one side up, long hair,
Virtual Goddess: Noor
This is an embedding of a woman that I've generated consistent faces of thru SD and decided to make into an embedding for easier access in the future. It uses a mere 5 tokens.
Soyuzmultfilm Style [Krea 2, Qwen 2.1]
This LoRA is trained on a dataset of images from "Ну Погоди!" (Just you wait!) soviet era animated cartoon series. This is my first (published) LoRA attempt and I welcome your feedback.
Instagram_Influencer_64_By_Stable_Yogi
Loving this model? Get the Pro version of my models here for exclusive perks and early access to unique resources.
smurf-style
Originally posted to HuggingFace by sd-concepts-library Smurf Style on Stable Diffusion This is the concept taught to Stable Diffusion via Textual Inversion. You can load this concept into the Stable Conceptualizer...
Alicia Florence (LOCON version) - Aria/Aqua
This is the LOCON version of my Alicia Florence LORA , a pretty oneesan of one of my favorite slice of Life shows(the other being Yokohama kaidashi kikou). Let's be honest here... who else thinks Akatsuki got Alicia...
Midnight Fairytale
Dark whimsy, gothic beauty, haunted storybook characters, and strange little monsters from the fairytale that starts after midnight
Derpixon Style LyCORIS | Cheems AI
Making models can be time consuming and expensive. If you like what I do consider giving this a rating and commissioning a model or buying me a borgar 🍔 !
Instagram_Influencer_72_By_Stable_Yogi
Loving this model? Get the Pro version of my models here for exclusive perks and early access to unique resources.
Mickey Vicious
MICKEY VICIOUS Meet Mickey Vicious, the 21-year-old Italian fire-breather turned candle enthusiast, who aspires to turn a childhood talent into a booming career that's less circus tent, more Yankee Candle. With a...
Concept_CrimePreventionBuzzer
This is a DoRA for PonyXL. If you're still on an ancient commit that doesn't support DoRA , you must update to use it. If you're on forge, use catboxanon's PR.
Envy Starlight Fae Automaton 01
As dangerous as they are exquisite, these living automata are built with impossible, magic-infused fae technology.
cthulhuTECH - spiderbots
Honestly who knows, it makes gross robot spiders. Im working on a better version but it's kinda fun now so i'm putting it out there.
Jake Sully - James Cameron's Avatar franchise
KREA VERSION: use 8 steps for the first image, 1 CFG scale, then 4 steps for upscaling, and 0.4 of denoising strength to obtain TERRIFIC results like the one shown in these images.
