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
19 shown of 41,753
VAE Lyra SDXL T5xl
I cooked an incorrect cross-attention mechanism based version where the clipl was learning from the clipg. This next version will have correctly decoupled behaviors and the correct cantor cross-attention formula. The...
Videomae Base Finetuned Kinetics Finetuned Accident Dataset
This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.0077 Accuracy: 1.0
Navila Satnav Continue 1ep 8f Sample Hk7 Fs7 Stopx4
This checkpoint is designed for use with SatNav, the continuous-state vision-and-language navigation platform for satellite maps. The SatNav NaVILA integration uses it to predict compact actions from a language...
Mistral Vitaly LoRA
This model is a fine-tuned version of mistralai/Mistral-Small-3.1-24B-Instruct-2503. It has been trained using TRL.
Gemma Medical Qa LoRA
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...
RegNet Y 1 6GF.tv2 In1k
This repository provides a model compiled and optimized for Mobilint NPU hardware. The model is packaged for deployment on Mobilint’s acceleration stack and is intended to be used within that environment.
Scribegene Llm v0.4
Vision-native handwritten insurance form understanding, fine-tuned from unsloth/Qwen2-VL-7B-Instruct using QLoRA.
FastVLM 1.5B 4bit Mlx
This model was converted to MLX format from apple/FastVLM-1.5B using mlx-vlm version 0.6.5. Refer to the original model card for more details on the model.
RegNet X 32GF.tv1 In1k
This repository provides a model compiled and optimized for Mobilint NPU hardware. The model is packaged for deployment on Mobilint’s acceleration stack and is intended to be used within that environment.
Whisper Small Finetuned Iwslt Irish Synthetic
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set: Loss: 3.4815 Wer: 94.9404 Bleu: 9.1198 Chrf++: 29.5535 Comet: 0.5382
Patch Ioner Talk2dino Capdec Groupnet COCO Captions
This repository contains a pre-trained DECAP model from the Patch-ioner framework for dense image captioning and controllable visual description.
ControlNet Qrcode Control V11p Sd21
This repo holds the safetensors & diffusers versions of the QR code conditioned ControlNet for Stable Diffusion v2.1. The Stable Diffusion 2.1 version is marginally more effective, as it was developed to address my...
ControlNet Celebahq Mask Output3
These are controlnet weights trained on runwayml/stable-diffusion-v1-5 with new type of conditioning. You can find some example images below.
Parakeet Tdt 0.6b v3 Coreml
Core ML build of nvidia/parakeet-tdt-0.6b-v3 (FastConformer encoder + TDT decoder, 0.6B parameters, 25 European languages including Russian and Ukrainian, punctuation and capitalization built in).
Trocr Small 1style Hh104 Stage1 Frozen
This model is a fine-tuned version of cyttic/trocr-hebrew-small-untrained on an unknown dataset. It achieves the following results on the evaluation set: Loss: 4.6194 Cer: 0.7898 Wer: 1.0518
ControlNet X Ray
These are controlnet weights trained on runwayml/stable-diffusion-v1-5 with new type of conditioning. You can find some example images below. prompt: chest Xray
Vit Base Patch14 Reg1 Tipsv2.webli
A Vision Transformer (ViT) image feature model with a register token. Distilled from the ViT-g/14 TIPSv2 teacher via patch-level distillation on a 116M-image filtered subset of WebLI.
Qwen3 Asr Rakuten Multilingual 18lang
Fine-tuned Qwen3-ASR model for multilingual automatic speech recognition, optimized for Rakuten customer service use cases.
Dinov3 Convnext Small Pretrain Lvd1689m
dinov3-license
