Find what you need for your workflow.

Noob SDXL ControlNet Canny

fair-ai-public-license-1.0-sd

Pocket Tts Es Onnx

Flat mirror of the spanish int8 ONNX bundle for Pocket TTS (Kyutai CALM zero-shot voice-cloning TTS), repackaged for the Sokuji Local Native provider's standard model-repo download path. Source bundle: the...

ACDC Heart Segmentation

A 5-fold cross-validated Attention U-Net ensemble trained on the ACDC cardiac MRI dataset for multi-class segmentation of cardiac structures.

Kastela Dof5 Building Segmentation

Binary building-footprint segmentation model for Croatian official digital orthophotos (DOF5) published by the State Geodetic Administration (Državna geodetska uprava, DGU). Given a 3-band RGB orthophoto chip at 0.5...

Noob SDXL ControlNet Depth Midas v1 1

fair-ai-public-license-1.0-sd

Biomedclip Gpt2 Captioner

A dermatology image captioning model combining BiomedCLIP vision encoder with gpt2-medium language model. Trained on dermatological images for generating clinical descriptions of skin lesions.

Rl Pos Test10 Rgpe A15

libraryname: transformers tags: trl grpo

ImageSuperResolution Replication

This repository contains the DiT4SR transformer weights exported from the local dit4sr-replication experiment at checkpoint-150000.

Dinov3 Vit7b16 Pretrain Sat493m

dinov3-license

Nethack Ppo Ablation Baseline Curiosity Skill Only

This repository contains a complete Sequential Skill RL model trained on NetHack/MiniHack environments.

InternVL3 2B

This version of InternVL3-2B has been converted to run on the Axera NPU using w8a16 quantization.

Dis Seg Former Deprecated

This model is finetuned on the top of RF-DETR-seg-Preview model, utilizing leaf-disease-segmentation dataset in the coco-segmentation format from roboflow.

ComfyUI Models

This repository contains only artifacts classified as public in the pinned recovery manifest. It does not apply one blanket license: each artifact retains its upstream license and usage conditions.

Trellis OA

TRELLIS-OA, a large 3D genetive model produces orientation-aligned 3D objects. It was introduced in the paper Orientation Matters: Making 3D Generative Models Orientation-Aligned.

Miril Drone 2B 1 MLX 4bit

Drones can talk, including on Apple Silicon.

Diabetic Retinopathy Analysis

A complete end-to-end deep learning pipeline for Diabetic Retinopathy (DR) analysis using retinal fundus images. This project performs three tasks:

Agrovision Plantcount

Modelo de segmentación de instancias para conteo de plantas de arándano (blueberry) en imágenes aéreas de alta resolución.

Megaman NT Warrior Dr Wily RVC

This is Dr. Wily's voice from Megaman NT Warrior This was created with RVC V2, by Rejekts, trained on 500 epochs. If you would like to use the model, go here:

ComfyUI-NVIDIA-CMD

Homochi XL | Male Focused Anime SDXL Model

Homochi XL v2 – Quick FAQ