Find what you need for your workflow.

Esp32 Markov Mixer 973k

We wanted to see whether a language model made mostly from low-rank Markov lookups, two tiny recurrent heads, and a little nonlinear context mixing could fit on an ESP32 and still say recognizably different things....

ComfyUI_SaveImageCustom

IDM VTON

This is an official implementation of paper 'Improving Diffusion Models for Authentic Virtual Try-on in the Wild' paper project page

LibreEfficientNetV2b3 Cls

EfficientNetV2-base-b3 image classifier (1000-class ImageNet-1k), repackaged for LibreYOLO. Eval resolution 300px; timm-reported top-1 accuracy 82.1%.

ForwardRenderer

This repository contains the base and LoRA weights for the Weather-conditioned Forward Renderer, as presented in IntrinsicWeather: Controllable Weather Editing in Intrinsic Space.

Breeze ASR 26 GGML

The smallest-footprint build: peak RSS 1.85 GB (Q40), fits a 4 GB host, and loads directly in whisper.cpp desktop apps (MacWhisper Pro, superwhisper) — drag the .bin in, no code. Slower than CT2 (RTF 0.40) but the...

Mero ControlNet Lr1

These are controlnet weights trained on runwayml/stable-diffusion-v1-5 with new type of conditioning.

Mae

A PyTorch implementation of Masked Autoencoder (MAE) for self-supervised learning on chest X-ray images, specifically designed for the CheXpert dataset.

Gemma 4 E2b Nla L23 Av Grpo Dense500

LoRA adapter for an Activation Verbalizer (AV) over google/gemma-4-E2B layer-0/embedding injection (marker token U+3297, injection scale sqrt(1536)). Starting point was the prior-deviation SFT checkpoint (step 5000);...

ComfyUI-Qwen2_5-Omni

Qwen2.5-Omni in ComfyUI

ComfyUI Momo

A copy of momo full from

ControlNet VIDIT FAID

We propose a ControlNet using depth maps conditioning that is capable of controlling the light direction in a scene while trying to maintain the scene integrity. The model was trained on VIDIT dataset and [ A Dataset...

PonyMan [Hyper]

Thanks to TomoKozaki for his support on this model !

Intern Qformer Epoch4 1207

Developed by: [More Information Needed] Funded by [optional]: [More Information Needed] Shared by [optional]: [More Information Needed] Model type: [More Information Needed] Language(s) (NLP): [More Information...

Siftformer 1.5

| Index | Class | | 0 | 정상 (normal) | | 1 | 졸음 (drowsy) | | 2 | 주의분산 (distracted) | | 3 | 폭행 (violence) |

XMR Demo Industrial Foreign Object Detection Lentils

Three pre-trained Cuvis.AI pipelines for hyperspectral foreign-object detection on a sliding lentil conveyor. All three use the same architecture (a frozen DINOv2 backbone with a Dinomaly anomaly head and a two-stage...

Pictory ControlNet Crayon R8 Edge Lr1e 4 Ep5

This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated.

Full Cot Epoch 3 Llama

Developed by: [More Information Needed] Funded by [optional]: [More Information Needed] Shared by [optional]: [More Information Needed] Model type: [More Information Needed] Language(s) (NLP): [More Information...

Tibetan Modern Book Layout Detection RFDETR

Permissive (Apache-2.0) alternative in TiBLA (Tibetan Book Layout Analysis) — a lighter, PyTorch-native RF-DETR-L detector for the page layout of modern Tibetan books (headers, text area, footers, footnotes).

Hangul Font Classification

A PyTorch model that recognizes which font a printed Hangul (Korean) syllable glyph was rendered in, and jointly recognizes which syllable the glyph represents.