Resource directory
Search Sweet Tea Pipes, external workflows, models, node packs, and guides in one evidence-linked catalog.
Start with a workflow instead ↗Search results
20 shown of 27,543
SDXL LoRA/LyCORIS works best on the model that it was trained on. I will release multiple versions for a few popular models. Feel free to request for artist or model.
Wonhan the barbarian from Nisego's Forgotten lands and Our Silent Vow comics. Works best between 0.8-1.0 weight . Training done on Pony Diffusion V6 XL . Request form
if you want something please send me a DM on twitter, or support me on my patreon(there is exclusive models there)
Trained with the 2100 Steps in A1111 deterministic default style. I know the trigger word "test64a7f32" is a little bit strange, it was just a try to create a SDTI out of some outputs of the biomechanicals...
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...
KOKORO VICIOUS Kokoro is Japanese and of course part of the gigantic 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...
Originally posted to HuggingFace by sd-concepts-library summie-style on Stable Diffusion This is the concept taught to Stable Diffusion via Textual Inversion. You can load this concept into the Stable Conceptualizer...
ANGELICA VICIOUS Angelica is from Hawaii and of course part of the gigantic Vicious family. They are nice people and gave birth to a lot of pretty daughters, the best about them is... they are entirely fictional....
Nix Toon is a personal flavour I have built up. I love the western comic style, but things can get too chiselled and hard, so this aims to soften the character shapes and enrich the colour palettes. Things are not...
Another AI character. The TI focuses on the face/upper body. I'm not quite happy how he adapts to clothing. I might do another run with different input images to improve the model.
Originally posted to HuggingFace by sd-concepts-library Malika Favre Art Style on Stable Diffusion This is the concept taught to Stable Diffusion via Textual Inversion. You can load this concept into the Stable...
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...
Datasets created from colorful and clean styles and made available for Illustrious, Anima or Z-Image.
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...
This is something I meant to make months ago but the dataset got kind of lost between millions of other things so I had to start over from scratch. I feel like there was something I was meant to mention but my brain...
Train with photo of woman with different type of hair colors, eyes colors and skin colors but the majority of them are with redheads and blue eyes.
A slider for line weight. No trigger word needed. Apply it with a positive weight for thicker lines, negative for thinner. It is trained so that the rest of the picture stays as close as possible to what you get...
Originally posted to HuggingFace by sd-concepts-library green-blue shanshui on Stable Diffusion This is the concept taught to Stable Diffusion via Textual Inversion. You can load this concept into the Stable...
Hey guys! Hope you love using this new LoRA as much as I loved making it. Just a quick word of advice: try not to go overboard stacking a ton of LoRAs together, or they will just fight each other and ruin the whole...
SAKURA VICIOUS Sakura from 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 TRUALITY ENGINE All Vicious...