Resource directory
Find what you need for your workflow.
Guides: techniques, setup, and troubleshootingSearch Sweet Tea Pipes, external workflows, models, node packs, and guides in one evidence-linked catalog.
Start with a workflow instead ↗Search results
All resources
20 shown of 38,740
MOSS Audio 8B Instruct MLX
An Apple MLX conversion of MOSS-Audio-8B-Instruct — the ASR-strongest MOSS-Audio checkpoint — for fast, low-memory inference on Apple Silicon. LLM quantized to uniform INT4 (groupsize 64); audio encoder + adapter +...
ControlNet SDXL 512
These are controlnet weights trained on stabilityai/stable-diffusion-xl-base-1.0 with new type of conditioning.
Resnet18 Crnn Ocr
This repository hosts a lightweight, high-performance Convolutional Recurrent Neural Network (CRNN) using a ResNet18 backbone for sequence-based handwritten text recognition (OCR). The model is optimized for...
Llava v1.6 Mistral 7b 4bit RoVQA LoRA v1
This is a parameter-efficient Low-Rank Adaptation (LoRA) adapter for LLaVA-v1.6-Mistral-7B fine-tuned on Romanian Visual Question Answering (VQA).
LibreEfficientNetV2b2 Cls
EfficientNetV2-base-b2 image classifier (1000-class ImageNet-1k), repackaged for LibreYOLO. Eval resolution 260px; timm-reported top-1 accuracy 80.5%.
Dpt Large Onnx
ONNX export of Intel/dpt-large — the Dense Prediction Transformer for monocular depth. 330M params, originally published as part of the MiDaS project at Intel Intelligent Systems Lab.
2xHFA2kSwinIR S
Name: 2xHFA2kSwinIR-S Author: Philip Hofmann Release Date: 26.12.2023 License: CC BY 4.0 Network: SwinIR Small Scale: 2 Purpose: 2x anime upscaler Iterations: 22'000 epoch: 10 batchsize: 6 - 12 HRsize: 128 - 256...
PathFLIP
Model weights for the paper PathFLIP: Fine-Grained Language-Image Pretraining for Versatile Pathology Image Understanding.
Phoonnx Vits
Per-architecture mono-repo of VITS voices for phoonnx. One model per subfolder. Part of the phoonnx community mirror.
v56 Public091 Rslora R128 A16 Lr6e5 Ep2
This model is a fine-tuned version of OpenOneRec/OneReason-0.8B-pretrain-competition on the expv49public091exact dataset.
Vggt Omega 1B 256 Oxe Mimicgen Rc365 Step23000
Single checkpoint snapshot from the 3DAunified VGGT-Omega 1B-256 multi-source pretraining run, taken at training step 23,000.
Eo VAE
EO-VAE is a multi-sensor variational autoencoder designed to serve as a foundational tokenizer for the Earth Observation (EO) domain. Unlike traditional approaches that require separate models for different sensors,...
Legal Qwen3.6 27B Abliterated GGUF
GGUF build of Legal-Qwen3.6-27B-Abliterated for Ollama / llama.cpp.
Oct Fluid Segmentation
Author: Animesh Kumar | Newcastle University MSc Advanced Computer Science 2025–26 Target Venue: OMIA 2026 Workshop at MICCAI + medRxiv preprint Framework: PyTorch | Compute: Google Colab H100 Live Demo: HuggingFace...
Meow Machine Mert
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
2xEvangelion Omnisr
Name: 2xEvangelionomnisr License: CC BY 4.0 Release Date: 08.02.2024 (dd/mm/yy) Author: Philip Hofmann Network: OmniSR Scale: 2 Purpose: 2x upscaler for evangelion episodes Iterations: 218'000 epoch: 198 batchsize:...
Nnunet Breast Mri
Pretrained nnU-Net v2 weights for tissue segmentation on breast dynamic contrast-enhanced MRI (DCE-MRI). The accompanying inference/evaluation code is in code/; the online demo is the Space zhang0319/breast-mri-seg.
ControlNet Celeb v2 1
These are controlnet weights trained on runwayml/stable-diffusion-v1-5 with new type of conditioning.
Q777
Steps: from 12 - more is better For quality you can use dpm++ 2s ancestral . Something else if you want better speed. Default euler ancestral should work well.
BiliSakura/VAEs · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
