Find what you need for your workflow.

[SDXL] Artist Style: shiun/siun 5513

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.

Painterly Cyber

reduced Dataset to 50 Images, captioning with joycaptioner and medium length output. Training wit ai-toolkit standard settings for Krea 2.

[IllustriousXL v0.1 LoCon] Valerie | Orc Massage

Trigger + Appearance: va1erie, tiger tail, animal hands, claws, animal feet, short hair, streaked hair, orange hair, white hair, black hair, tiger ears, blue eyes

[IllustriousXl v0.1 LoCon] Saki | The Atko's OC

Trigger + Appearance: s4ki, long hair, blue hair, hair between eyes, ponytail, hairclip, black horns, blue eyes

[+]XL 药子沙耶 / Yakushi Saya / 薬子サヤ | 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...

Tunnel Vision Animation -- Adiff V3 Motion lora

This motion model simulates the experience speeding through a tunnel, creating dynamic, tunnel-like animations. The motion is fluid yet structured, as parallel lines stretch and converge, mimicking the forward rush...

Akira E. Ferrari (LOCON version) - Aria/Aqua

Here we have Akira, Alicia's counter part from Himeya Company and the Crimson Rose of Neo Venezia. this is the LOCON version of my Akira LORA , it is trained almost exclusively on the manga with a bit of the anime...

RD_RN00 Style | Pony

Style inspired by RDRN00. I hope i credit the right artist. The Style left a strong impression. Works well with other loras. Without other loras involved it tends to give the Characters a scar on the nose.

Quartermaster Green (Call of Duty : Wold War II)

Here is a model of Corporal Green from COD:WWII, couldnt get a lot of pics to train her so it might be a bit unstable, anyways let me know what you think :D

Magritte Graffiti Strappy Chunky Sandal

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...

Luna Everly, a bohemian rock star

Luna Everly is a fictional character made by merging some of my embeddings. The bohemian rock star is a fiction too so you can get her as a stewardess or anything else. It's a very light embedding.

Big Hands

Not quite steam shovel sized, but still big, hands. This model is relatively inflexible and requires cherry picking due to a low amount of training data. Best results seem to be a weight of around 0.7-1, along with...

Instagram_Influencer_135_By_Stable_Yogi

Discover the magic of Babes V5 by Stable Yogi ❤ , a part of our Instagram Influencer series by StableYogi. This tool is designed to bring your digital creations to life with stunning clarity and artistic flair.

Taiki Style

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.

Evelissa Mix

So I wanted to do something different and take all these different images I’ve collected in different trainings and create something. This became the Mix person series.

Slithe (Thundercats 1985) - ILXL/Anima

LoRA of the mutant Slithe from the 1985 Thundercats cartoon series. Trained with Illustrious XL and Anima base model.

MiniMax-H3 comfy-native ref2va - w4a8 / nvfp4 / int8 / mxfp8, ComfyUI 0.32+

Everything here is free and stays free — the format spec, the nodes, the workflows, the cartridges, the LoRAs. If it saved you a night of debugging (it contains several hundred of mine), tips keep the 5090 warm:

Spanish Mix (Experimental)

The Spanish mix is an embeding trained on 98 images of Spanish models, one image for each, so it looks like none of them but captures their commonalities.