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 βSearch results
All resources
20 shown of 37,778
FSThicc - Style LoRA
MiniMax H3 Experimental
w4a8 is a format using 4-bit weights and int8-convrot activations
sexyWomanJob_v10.safetensors
Ltx 2.3 Fight
Base model: LTXV 2.3 Trained words:
Zoda π₯€ β NSFW Detailer
Medgemma 1.5 4b LoRA Adapter Rank 8
This repository contains a Low-Rank Adaptation (LoRA) Rank-8 adapter built on top of:
diffusion_pytorch_model.safetensors
flux-lora-valen.safetensors
Gemma 4 E2B It
Hugging Face | GitHub | Launch Blog | Documentation
ε€ηεΏ Gu Xun'er BTTH.safetensors
Rimu Style
Works best at 0.75 weight.
Pearly impossible fit - Illustrious - pearlyimf,huge penis,abdominal_bulge,throat_bulging.safetensors
[Pony / SD1.5] Shinku (Rozen Maiden) | γγΌγΌγ³γ‘γ€γγ³
η±θθ Release That Witch.safetensors
Illustrij
Cohere Transcribe Arabic 07 2026 GGUF
GGUF weights for CohereLabs/cohere-transcribe-arabic-07-2026 β Cohere Labs' 2B-parameter Arabic ASR model (a FastConformer encoder + Transformer decoder), released July 2026 (11% WER on FLEURS Arabic per the source...
Vctk Dns2020 Bsrnn Small Noncausal
This model was trained by wyz based on the universalsev1 recipe in espnet. More information can be found at
Gemma 4 E4B RotorQuant GGUF Q4 K M
> [!WARNING] > Fork compatibility (2026-07-07): the llama-cpp-turboquant fork is currently based on a llama.cpp revision that predates gemma4 architecture support β it fails with unknown model architecture: 'gemma4'...
