Find what you need for your workflow.

model.safetensors

Kasumi Tendou (LOCON version) - Ranma 1/2

Here we have the best Tendo sister, she is arguably one of the best 3 Ranma girls competing only with Shampoo and Ranma-chan herself. This LOCON is based on my Kasumi V2 LORA , it uses the same dataset, so download...

model.safetensors

ConvTasNet Bassoon Causal

A Causal Bassoon/Others separation model for the CAD2-Task2 baseline system.

Seri Kikyou (桔梗 セリ) - Call of the Night (よふかしのうた)

Support my work by subscribing to patreon!

Nemotron 3 Nano Omni 30B A3B Reasoning BF16

nvidia-open-model-agreement

Lightning Lora, massive speed up for Wan2.1 / Wan2.2 made by Lightx2v / Kijai

Xtts Moore Femme

coqui-public-model-license

Fire Emblem GBA Portrait Style [Anima]

Fire Emblem GBA Portrait Style. Trained on Anima.

spo-sdxl_lora_fp16.safetensors

model.safetensors

Can you draw like a five-year-old? Children's Crayon Drawing Style (Krea 2)

This is a Krea 2 version of

Maiky Odel Style

Works best at 0.75 weight.

Videomt Dinov2 Large Ytvis2022

This repository contains the Hugging Face Transformers conversion of the official VidEoMT checkpoint yt2022vitlarge42.6.pth from tue-mps/VidEoMT.

model.safetensors

model.safetensors

[noobvpred] artist style:kensight328 and hotahotatenshi and xiaoyezi 3合1

三个画师风格在一个lycoris模型里实现 可以分别使用各自的启动词,也可以合在一起 启动词在模型noobaiXLNAIXL_vPred10Version下效果如下 hotahotatenshi kensight328 xiaoyezi

Videomae Base Finetuned Kinetics 0403 Final Bbox

This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.5415 Accuracy: 0.8825

Audio Cls Hhd

This model is a fine-tuned version of Kkonjeong/wav2vec2-base-korean on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.6877 Accuracy: 0.8487

model.safetensors