Find what you need for your workflow.

Dinodepth Model

Trained Simple Depth Transformer (SDT) decoder heads for zero-shot affine-invariant (relative) monocular depth, reproducing AnyDepth (arXiv:2601.02760) on a frozen DINOv3 backbone. Only the small SDT decoder is...

Craftconnect Vit

A fine-tuned Vision Transformer (ViT-B/16) that classifies photographs of Indian folk-art paintings into one of seven traditional art styles. It's the vision component of CraftConnect, a multimodal platform that...

Kokoro 82M CoreAI

> Mirror of mlboydaisuke/Kokoro-82M-CoreAI — the canonical repo (CoreAI Model Zoo). Updates land there first.

Wav2vec2 Large Xlsr Deepfake Audio Classification

This is the ONNX format of Gustking/wav2vec2-large-xlsr-deepfake-audio-classification, a Wav2Vec2 model fine-tuned for binary classification of audio as real (bonafide) or fake (spoof/deepfake).

Galaxeye Eo Sar Change Detection

Lightweight multimodal EO--SAR change detection framework based on EfficientNet-B0 UNet architecture.

MUNIN

Lightweight few-shot learning for acoustic individual identification in birds. A ResNet18 encoder trained from scratch on mel spectrograms using episodic prototypical learning.

CleanMel

The CleanMel model was presented in the paper CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR.

ControlNet Fill Circle

These are controlnet weights trained on runwayml/stable-diffusion-v1-5 with new type of conditioning. You can find some example images in the following.

Gemma 4 12B It FP8

Hugging Face | GitHub | Launch Blog | Documentation

DFF InstructBLIP Detection

This is the core DFF (DeepFake Detection and Forensic Explanation Framework) model as described in the ACL 2026 paper: "Generating Attribution Reports for Manipulated Facial Images: A Dataset and Baseline".

Microsam Vit B Lm Onnx

Promptable micro-sam vitblm exported to ONNX for client-side inference with onnxruntime-web + WebGPU, used by the JAX Image Tools viewer (jit-ui#90) SAM segment tool.

Wav2vec2 Xlsr 53 Russian Aligner Coreml

This repository contains a fixed-contract Core ML conversion intended for offline Russian speech alignment.

Spinopelvic Seg Checkpoints

5-fold nnU-Net v2 ResEnc-L ensemble for spine + pelvis CT segmentation, trained with an LSTV-aware merged-label scheme that collapses L5/L6 into a single lastlumbar class to handle lumbosacral transitional vertebrae.

Stt En Fastconformer Ctc Xxlarge GGUF

GGUF quantisations of nvidia/sttenfastconformerctcxxlarge for CrispASR.

comfyui-auth

Comfy Backup

Sar Flood Extent Unet Resnet34

A U-Net with a ResNet34 encoder that segments flood water from Sentinel-1 Synthetic Aperture Radar (SAR) imagery. Input is the two SAR polarizations (VV, VH); output is a binary water mask. Trained on the...

CLEAR

This repository hosts the pretrained vision-language backbone for CLEAR (Concept-Level Embeddings for Auditable Radiology). The checkpoint contains a contrastive image–text encoder that maps chest X-rays and...

ControlNet Shadows 20230430 224850

These are controlnet weights trained on runwayml/stable-diffusion-v1-5 with new type of conditioning. You can find some example images in the following.

Diffusion DDIM

An extension of the DDPM-CIFAR10 model that adds a Denoising Diffusion Implicit Models (DDIM) sampler for fast, deterministic inference. The underlying U-Net is trained identically to the DDPM variant; only the...