Find what you need for your workflow.

Cunnilingus - Concept - booru v1 - Illustrious - cunnilingus.safetensors

model.safetensors

Oryx ViT

The Oryx-ViT model is trained on 200M data and can seamlessly and efficiently process visual inputs with arbitrary spatial sizes and temporal lengths. It is described in the paper Oryx MLLM: On-Demand...

t2i-adapter_diffusers_xl_canny.safetensors

Videomae Base Finetuned Ucf101 Subset

This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.4043 Accuracy: 0.8571

model.safetensors

Photo Background 2d Compositing

Base model: Wan Video 14B t2v Trained words: photo background, real world location

model.safetensors

model.safetensors

model.safetensors

Qwen3 Tts Hindi LoRA Grpo

A Hindi LoRA adapter for Qwen3-TTS-0.6B, post-trained with GRPO (reinforcement learning) on top of the supervised akashicmarga/qwen3-tts-hindi-lora (SFT) adapter.

Floverale Style

Works best at 0.75 weight.

ResEncL OpenMind SwinUNETR

> Model from the paper: An OpenMind for 3D medical vision self-supervised learning > Pre-training codebase used to create checkpoint: MIC-DKFZ/nnssl > Dataset: AnonRes/OpenMind > Downstream (segmentation)...

KD OCT ConvNeXtV2

This model is part of the KD-OCT project, which provides a framework for efficient, clinical-grade retinal Optical Coherence Tomography (OCT) image classification. It was introduced in the paper KD-OCT: Efficient...

Hug & Suck - Illustrious - hug and suck , hugging, implied fellatio.safetensors

林雨霞 Lin Yuhsia Arknights.safetensors

SDXL Nuclear - General Purpose v3 - Semi-Realism - BASED - SFW / NSFW / Anime

VesselFM

TL;DR: VesselFM is a foundation model for universal 3D blood vessel segmentation in arbitrary imaging domains. For details, please refer to our manuscript and our GitHub repo.

Spindle - Style Anima LORA

Trained on Anima with 88 pictures. Best result with weight between : 0.8.

model.safetensors