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 41,759
Inkling 0.6B A0.6B
This is a tiny version of thinkingmachines/Inkling created for testing and development.
Kokoro 82M CoreAI
hexgrad/Kokoro-82M (Apache-2.0), a tiny high-quality StyleTTS2 + iSTFTNet text-to-speech model (82M params, 24 kHz), converted to Apple Core AI (.aimodel, iOS 27 / macOS 27) — the CoreAI-Model-Zoo's first TTS.
Blip Vqa LoRA Finetune Model
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
Medbot 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 X 800MF.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.
Blip2 Vizwizqa
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
Qwen3 Asr 0.6b Mizonal3 E1 Lus v2026.06
> Disclaimer / Notice: Details for these are in Peer Review and publications of the paper will be made available soon for more details.
Qwen35b Espanol GGUF
Fine-tune de Qwen3.6-35B-A3B (MoE, 35B total / 3B activos) orientado a español neutro con sesgo chileno, cuantizado a Q4KM (20 GB) y listo para correr en una RTX 3090 24GB a 169 tok/s con llama.cpp.
BxSD Finetuned UCF RGBCROP 5e6 Poly
This model is a fine-tuned version of TanAlexanderlz/BxSDRGBCROPAug16F-8B16F5e6-poly on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.3295 Accuracy: 0.8056
Whisper Medium Mizonal3 E2 Lus v2026.06
> Disclaimer / Notice: Details for these are in Peer Review and publications of the paper will be made available soon for more details.
Base Miner
Hibiki-Zero is a model for simultaneous speech translation. Traditional approaches for building simultaneous translation systems rely on supervised training with word-level aligned data between the source and the...
Siglip2 Large Patch16 512 Ces 32768
This model is a 25.91% smaller version of google/siglip2-large-patch16-512 optimized for Czech language via vocabulary size reduction using the trimming method. This trimmed model should perform similarly to the...
LingBot Video Dense 1.3B SDNQ Uint4 Static
This is a complete, loadable derivative of robbyant/lingbot-video-dense-1.3b with the diffusion transformer stored using static SDNQ UINT4 weights. It is tied to source model revision...
LTX 2.3 Sulphur2 Distilled Diffusers
An uncensored video generation model based on LTX 2.3 supporting both t2v and i2v natively, as well as all of the other ltx 2.3 formats.
Ft Wspr Md Jt 64 128 Fold4
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
Adetailer Collection
I collected a whole bunch of models from CivitAI and Hugging Face. There are many models that have been flagged, but I have all of them on my PC and nothing has happened to me yet, so I think it’s kind of safe to use .-.
Siglip2 Large Patch16 512 Tel 32768
This model is a 25.91% smaller version of google/siglip2-large-patch16-512 optimized for Telugu language via vocabulary size reduction using the trimming method. This trimmed model should perform similarly to the...
Under Fire Terrain ControlNet
A Stable Diffusion 1.5 ControlNet that turns annotated game-terrain renders from Under Fire (a free, open-development WW2 RTS) into photorealistic aerial terrain. Trained on tstruk/under-fire-terrain-pairs: 600 pairs...
Donut Irs990
This is a fine-tuned version of naver-clova-ix/donut-base trained to read IRS Form 990 documents and extract structured field data from them directly from images, no traditional OCR pipeline needed.
Galaxy Bar Detection Resnet50
CNNs that detect stellar bars in simulated disc galaxies — and, in the final version, measure bar strength as a continuous quantity.
