Find what you need for your workflow.

Qwen3 5 0.8b Base

The official release of Qwen3.5, introducing the open-weight of the first model in the Qwen3.5 series, As a native vision-language model, demonstrates outstanding results across a full range of benchmark evaluations,...

[Anima & SDXL] Artist Style: potg/ぴおてぐ

Artist style of potg/ぴおてぐ

ZodaPlus 🍾 – Detailer

【 Early Access Policy - Free Access】

Alice from Disney [IllustriousXL]

Reviews, Hearts, Likes etc. are very appreciated!

Fiz-Rot - LyCORIS LoCon - Illustrious

LoCon trained on Fiz-Rot's artstyle for Illustrious models

暗黑幻想/Dark fantasy style

大家好,我是chosen鲷,这次带来的是 Dark fantasy style lora 模型anima版本,主要就是为了获得那种低饱和度,高对比度的厚涂画风,整体色调偏黑暗,适合出那种大场景酷酷的图。

Manyakis Style LyCORIS | Cheems AI

Making models can be time consuming and expensive. If you like what I do consider giving this a rating and commissioning a model or buying me a borgar 🍔 !

mage_flow_vae_bf16.safetensors

Shadowverse,Rage of Bahamut Yuzuki / ユヅキ

Train based on AnyLora model. Training materials are basically official arts,fanarts and game resources from Cygames products.

XL_透明人_Invisible person

不小心删掉了重新传一遍淦( 对应版本用对应的模型

Samantha : The Curvy Heartbreaker

Samantha’s got the kind of curves you can’t ignore and a fun, flirty vibe that makes her impossible to forget. She’s playful, confident, and always knows how to keep things exciting.

Liliana Vess | Magic the Gathering

Feel free to share your images in the galley.

ltx-2.3-22b-distilled_transformer_only_mxfp8_block32.safetensors

Shizuno Urushibara - [Seiken Tsukai no World Break]

Shizuno Urushibara - [Seiken Tsukai no World Break]

Mare Style

Trained on 129 images (flip aug is turned on for this training, so technically trained on 258 unique images) . I take my time decensoring, cropping, cleaning up my dataset to make my Loras.

diffusion_pytorch_model.safetensors

Pittman/彼亚塔曼/ピアタマン---Alchemy Stars/白夜極光

Circuit Aware Rushd 8B

رُشْد — "guidance" or "right path" in Arabic

Realism Engine Ideogram 4 + Krea 2

Realism Engine Krea 2 v3

INT4 Convrot Comfy Models

A collection of INT4 ConvRot-quantized diffusion, video, and upscaling models for ComfyUI, built to run comfortably on 8GB-class GPUs (developed and tested on an RTX 3070 Ti) without gutting output quality.