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
19 shown of 27,898
Loving this model? Get the Pro version of my models here for exclusive perks and early access to unique resources.
Ivan Aivazovsky (1817–1900) was the preeminent Russian-Armenian Romantic marine painter, renowned for his masterful depiction of water, atmospheric light, and epic seascapes. This LoRA captures his signature...
Trained on 162 images by Zefrableu. I've only tested it on the AnyLoRA checkpoint and i would recommend using it. Use a weight around 0.6 and a CFG Scale of 7 for best results.
This Loha is just a small fun exercise. It basically provides and enhances a "smoke style" to pics. It is easily triggered with a handful of keywords, but it also acts as a kind of enhancer when used without keywords.
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.
This LoRA gives almost everything in the scene a soft plush texture. The exceptions are typically liquids like water, smooth surfaces like glass or screens, and sometimes grass or tiles. I didn't want it to default...
➼Like what I do? Consider throwing me a few dollars at so I can keep making cool crap for you all to enjoy for free! If you'd like to support me and also get some spicier pics, check out !
A full finetune of Anima Base v1.0 by CircleStone Labs, trained in two stages on a hand-curated set of pixiv illustrations selected for ornate costume detail, jewelry, embroidery, and rendered (semi-realistic)...
Trigger: rentbstyle, muscular, muscular female, I ended up weighting (muscular, muscular female) up to 1.5 to get it looking nice. Depends on the checkpoint a bit too I guess.
My first attempt on creating an AI character. The TI focuses on the face, so don't expect full body character. ;)
Loving this model? Get the Pro version of my models here for exclusive perks and early access to unique resources.
Trained on Anylora model.Use anime screenshots , some game materials and some fanarts as training materials.
This concept shares some similarities with Blending and Fixed-Point Camera , but it focuses on using empty space as a deliberate and essential part of the composition—as if the image would not work without it.
It was originally planned that Lora was made for one avatar - a Lady of Blades and a bit of vintage asian architecture. However, as the practice of using, this Lora in various neural networks has shown - everything...
Originally posted to HuggingFace by sd-concepts-library Kuvshinov on Stable Diffusion This is the concept taught to Stable Diffusion via Textual Inversion. You can load this concept into the Stable Conceptualizer...
prompts: labrajp, no humans, furry, chibi, blue eyes, white fur, jewelry, necklace, bear, multicolored hair, pink tail, white chest fur, tufted fur, one pink leg,
Lynae from Wuthering Waves. Trained on Illustrious-XL v0.1 . Tested at 0.8-1.0 strength. Contains two outfits: Default, Peppermint Outfit 2026
If the original artist requests a takedown, I will immediately remove this model off of CivitAI. Thank you. Please support their work here. Meanwhile, please do not monetize your generations.
prompt : abe takakazu, black hair, naked overalls, black eyes, eyebrows, bangs, yaranaika, full-length zipper
