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
18 shown of 35,706
Styltok / splash of colors
This style combines various paints like acrylic, gouache and most likely watercolor. There is a splash of colors, some expression. With this model, you can combine various hints, descriptions and everything that you...
Lopmon - ロップモン IL (Digimon)
If you'd like to continue supporting my creations, models, images, sequences, videos, etc, please feel free to make a donation on my Yellow Buzz profile; you're always welcome.
Pre-Timeskips Perona (One Piece) LyCORIS | Cheems AI
Making models can be time consuming and expensive. If you like what I do consider commissioning a LoRA or buying me a borgar 🍔 !
overprettified
Originally posted to HuggingFace by sd-concepts-library overprettified on Stable Diffusion This is the concept taught to Stable Diffusion via Textual Inversion. You can load this concept into the Stable...
Teri Hypernetwork
This is a hypernetwork that makes it possible to generate Teri, the paper bear from The Amazing World of Gumball series.
Instagram_Influencer_46_By_Stable_Yogi
Loving this model? Get the Pro version of my models here for exclusive perks and early access to unique resources.
[+]XL 合欢垣吹雪 / Nemugaki Fubuki / 合歓垣フブキ | Blue Archive
The model data source is derived from Waifuc, a highly robust tool for crawling, filtering, and processing training sets. With the aid of the Waifuc tool and a single 5600g machine, it is possible to efficiently...
Piper Vicious
PIPER VICIOUS Piper is from the European side of the Vicious family. They are nice people and gave birth to a lot of pretty daughters, the best about them is... they are entirely fictional. WORKS BEST WITH THE...
Noise Style (Pony v6)
Lora trained in re-create Noise's art style. This one is a really detailed style, is more appreciable in monocrome / grayscale.
Vanillaware style TI
Style embedding trained on Vanillaware's art (also some art from "The Vagrant" videogame was used, because they have a very close style). Good for generating girls and fantasy stuff. Tested on UnstableInkDream model
has_kuma artstyle
Look at the example images to understand what to do with tag weights. Reduce the weight of your characters tag find the boundary where the style is applied optimally and your characters features are preserved. Dont...
XL | touhou|东方 projcet 斯塔萨菲雅/スターサファイア/Star Sapphire
The model data source is derived from Waifuc, a highly robust tool for crawling, filtering, and processing training sets. With the aid of the Waifuc tool and a single 5600g machine, it is possible to efficiently...
sam-yang
Originally posted to HuggingFace by sd-concepts-library Sam Yang on Stable Diffusion This is the concept taught to Stable Diffusion via Textual Inversion. You can load this concept into the Stable Conceptualizer...
Ben Templesmith style [XL]
Ben Templesmith (born 7 March 1984) is an Australian comic book artist best known for his work in the American comic book industry, most notably the Image Comics series Fell , with writer Warren Ellis, and IDW's 30...
XL | touhou|东方 projcet 十六夜咲夜/十六夜 咲夜/Izayoi Sakuya
The model data source is derived from Waifuc, a highly robust tool for crawling, filtering, and processing training sets. With the aid of the Waifuc tool and a single 5600g machine, it is possible to efficiently...
XenoBABE - Jessie McSloot - The Influencer
With over 600k InstaTok followers, Jessie McSloot is an up and coming social media influencer. Much to her mother Jenny 's dismay, the 22 year old has also started a more adult oriented channel on FanFace. Will...
eyeball Style | あい・ぼうる
Style LoCon for eyeball . I don't know it was the case for everyone but it was a classic artist from early/pre-booru days with of course a very 1990s style.
Multi-waifu-mix
An experimental hypernetwork trained on 100+ different anime characters. Do we actually need to create specific networks for each and every character or could we work on improving our base models instead?
