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 41,765
Gemma 4 E4B It GGUF
See Unsloth Dynamic 2.0 GGUFs for our quantization benchmarks.
Snac 24khz Hindi Ft
A SNAC 24 kHz multi-scale neural audio codec wh ose decoder has been fine-tuned on Hindi / Hinglish speech. It serves as the vocoder (SNAC-token → waveform detokenizer) for a Orpheus styled TTS stack.
Megalodon 2024 Yolov11
Trained by researchers at the Monterey Bay Aquarium Research Institute (MBARI). Ultralytics YOLO11x Object detection model Fine-tuned to detect 1 class, called 'object', using all FathomNet localizations Updated from...
Whisper Base Cv11
A plain openai/whisper-base (unmodified architecture) fine-tuned on the 11 languages of the CC0 Whispered corpus. This is the matched scientific control for burakaydinofficial/whisper-base-mla-cv11 — trained...
Marlin Vit Base Ytf
This repo is the official PyTorch implementation for the paper MARLIN: Masked Autoencoder for facial video Representation LearnINg (CVPR 2023) (arXiv).
Europe Reanalysis Downscaler Convbaseline
The aim of the project is to create a Machine learning (ML) model that can generate high-resolution regional reanalysis data (similar to the one produced by CERRA) by downscaling global reanalysis data from ERA5.
Ppe Detection
This model is a specialized version of YOLOv11, fine-tuned to detect Personal Protective Equipment (PPE) in industrial and construction environments. It is designed to enhance occupational safety by monitoring the...
Siglip2 Large Patch16 512 Dan 32768
This model is a 25.91% smaller version of google/siglip2-large-patch16-512 optimized for Danish language via vocabulary size reduction using the trimming method. This trimmed model should perform similarly to the...
Ccgdetector Fastweb Single
ONNX corner detector for CollectorVision-style card scanning. This release is fastweb-single 1.39 (corndog), an EfficientViT-B0 global-token SimCC model exported for 384x384 RGB input.
ControlNet Openpose SDXL 1.0
Developed by: xinsir Model type: ControlNetSDXL License: apache-2.0 Finetuned from model [optional]: stabilityai/stable-diffusion-xl-base-1.0
Llava Llama 3 8b Pretrain
llava-llama-3-8b-pretrain is a LLaVA projector pretrained from Meta-Llama-3-8B-Instruct and CLIP-ViT-Large-patch14-336 on LLaVA-Pretrain dataset by XTuner.
Huihui Gemma 4 E2B It Qat Q4 0 Unquantized Abliterated
This is an uncensored version of google/gemma-4-E2B-it-qat-q40-unquantized created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to...
Nakiri Ayame Wan 2.1 14b T2V
Base model: Wan Video 14B t2v Trained words: Nakiri Ayame, anime-style girl. The image features an anime-style character with long white hair adorned with horns.including a headpiece that resembles a demon mask with...
Ddpm Celebahq Finetuned Butterflies 2epochs
pipeline = DDPMPipeline.frompretrained('parsa98/ddpm-celebahq-finetuned-butterflies-2epochs') image = pipeline().images[0] image
Siglip2 So400m Patch16 512 Tam 32768
This model is a 22.63% smaller version of google/siglip2-so400m-patch16-512 optimized for Tamil language via vocabulary size reduction using the trimming method. This trimmed model should perform similarly to the...
Dinov3 Convnext Tiny Pretrain Lvd1689m
dinov3-license
PaddleOCR VL Aksara Jawa
LoRA fine-tune of PaddlePaddle/PaddleOCR-VL for Aksara Jawa (Javanese traditional script). Submitted to the PaddleOCR Global Derivative Model Challenge — Hackathon 10th.
Siglip2 Giant Opt Patch16 384 Nep 32768
This model is a 13.74% smaller version of google/siglip2-giant-opt-patch16-384 optimized for Nepali language via vocabulary size reduction using the trimming method. This trimmed model should perform similarly to the...
School Violence Detection Models
Bộ mô hình 3D CNN được fine-tune để phát hiện hành vi bạo lực trong video, phục vụ đồ án tốt nghiệp "Hệ thống phát hiện bạo lực học đường" tại UIT.
Matcha Clips 224 Fintuned 5
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set: Loss: 1.5168 Accuracy: 0.7326
