Find what you need for your workflow.

ControlNet

These are controlnet weights trained on stabilityai/stable-diffusion-2-1-base with new type of conditioning. You can find some example images below.

Runrazor Detectors

Downloadable subject-detector weights for runrazor. These are stock YOLOX object detectors, exported to ONNX and used at runtime restricted to the COCO person class (skiers are detected as people; runrazor's tracking...

Umbra-Nodes

ComfyUI custom nodes for Umbra Studio

ComfyUI-SAM2-Realtime

OvisOCR2 OQ4e

> Apple Silicon Optimized oQe4 MLX Quantized Release

Lucida Web

This repository contains an experimental ONNX/WebGPU conversion of Lucida for personal validation in a web browser. It is not an official release of the original project and is not affiliated with or endorsed by the...

Openworld Sam

OpenWorldSAM extends SAM2 with language understanding to enable open-vocabulary instance, panoptic, semantic, and referring segmentation from arbitrary text prompts — without any task-specific fine-tuning.

Resnet50 Inference Optimization

This is a standard torchvision ResNet-50 (IMAGENET1KV2 weights) exported to ONNX, published as the portable artifact from an inference-optimization study. The point of the repo is not the weights — they're the stock...

Samid Drone Detector

Audio Spectrogram Transformer fine-tuned for binary acoustic drone detection.

LibreSigLIP2b16 Cls

SigLIP 2 base patch-16 (256 px) dual-tower zero-shot image classifier, repackaged for LibreYOLO. Open vocabulary: define your own class set at runtime with setclasses, no training needed. Multilingual (SentencePiece,...

BattyBirdNET Onnx

ONNX-converted regional bat species classifiers from BattyBirdNET-Analyzer, optimized for inference with ONNX Runtime.

Medocr Asr Bn

INT8 (MatMul-only dynamic quantization) ONNX export of the encoder of ai4bharat/indicconformersttbnhybridctcrnntlarge (MIT license, AI4Bharat), plus its CTC head, vocabulary, and mel filterbank. MatMul-only...

2xHFA2k LUDVAE Compact

Name: 2xHFA2kLUDVAEcompact Author: Philip Hofmann Release Date: 26.12.2023 License: CC BY 4.0 Network: SRVGGNetCompact Scale: 2 Purpose: A lightweight anime 2x upscaling model with realistic degradations, based on...

Output Dir ControlNet

These are controlnet weights trained on stabilityai/stable-diffusion-2-1-base with new type of conditioning. You can find some example images below.

ClearVAE

Diffusers format of ClearVAEV2.3.safetensors from

Dashcam Collision Rockchip Mnv3s

Causal sliding-window crash detector for the RK3588 NPU. Because the NPU has no 3D convolutions, this is a per-frame 2D-CNN + a small temporal head, deployed as two ONNX graphs (convert the backbone to INT8 RKNN; run...

Wan 2.2 ComfyUI Repackaged

Examples: https://comfyanonymous.github.io/ComfyUI examples/wan22/

Linear A Linear B Bothros

Weights for the BOTHROS pipeline: photograph an ancient Aegean tablet, get the signs on it by catalogue code and reading.

STRLite

STR-Lite is an ultra-lightweight scene text recognition model that combines Masked Autoencoder (MAE) pretraining with an autoregressive decoder for text generation. With only 6M parameters, it achieves competitive...

Audiosronnx Gtcrn

ONNX weights for the gtcrn denoise engine in audiosronnx — a mirror of the streaming GTCRN graph from Xiaobin-Rong/gtcrn (MIT).