Loading
Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
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 26,956
CLEMENTINE VICIOUS Clementine is an Influencer from Canada 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...
Good for ink and wash, watercolor, etc. Use at .8 to 1 for watercolor with no trigger words, or at .35 for a more ink and wash look, with trigger words like "ink and wash", "watercolor", "rough ink sketch", etc.
Please put the model at the front of the front of the prompt. With TI order is very important. With Loras it doesn't matter.
Oh, hello there! I’m Smirnova, a highly intellectual blonde with an astonishing IQ of 69—nice, right? I’m a passionate advocate for world peace and an even bigger lover of animals (because, honestly, they’re smarter...
Lora trained in recreate Saeki Tatsuya's artstyle. This lora would not have been possible without the support of serp2022 , which provided the dataset necessary for its creation. (>°-°)>
Bunch of these preview images got marked R cause her outfit Hello ! 2nd LoRA is here. This one was not easy. hack//sign is 480p at best and the character shots are very lacking. Halfway decent full body were almost...
plum, 1girl, solo, green long hair, sidelocks, hair bobbles, low ponytail, ahoge, hair ornament, red eyes,
Sarah Silkie from the webcomic " Las Lindas " by Chalo. Works best around 1.0 weight . Training done on Pony Diffusion V6 XL . Request form
Trained for PonyXL with anime screencaps (thanks to ) and various other sources - using kohyass. I recommend a weight around 0.8 - 1.0 .
The heiress of one of the country's top conglomerates. On the surface, she appears impeccably virtuous, but in reality, she's lazy and prone to whining. Her favorite food is potato chips.
☁️ Cloud Dancer – Pantone Color of the Year 2026. LoRA for Z Image Turbo, Krea 2 and Flux 2. Ethereal White, Minimalist Realism
Made this one a long time ago just never got around to upload uploading it (i think it was around the time i was still learning anima training). I did make the other characters but ill likely be taking another stab...
This is a test of using entirely black-and-white dataset. For compatibility, you still need prompts like greyscale , monochrome , white background , and simple background to achieve the author's original style.
One of my favorite characters from the famous ero-game series called 'Inyouchuu'.She's a pretty girl (also a fox girl) with strong powers hidden within her covered eye.
Oxen King Uma from the manhwa The God of Highschool . A request from the form. Works best around 1.0 weight . Training done on NAI.
Glitch is a visual effect that mimics digital errors and malfunctions, often seen in corrupted or unstable video signals. It produces shifts, duplicated fragments, noise, and other artifacts that create a sense of...
Marian Kelly from River City Girls . Works best around 1.0 . Training done on Pony Diffusion V6 XL . Request form
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...
Controlling the exact orientation of the hand is extremely difficult when recreating scenes of characters covering their mouths using standard image generation models.
A beautiful, highly coherent digital painting style for Envy Starlight, with sharp details and nice character art.
