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 38,598
Merger_zara_delgloom
Another merger from my ti's
Voxtral 4B TTS 2603 TurboQuant MLX 8bit
> [!TIP] > KV-cache quantization without any fork (recommended, 2026): upstream > llama.cpp/Ollama now cover this natively — use -ctk q80 -ctv q80 > (half KV memory, negligible quality loss: perplexity +0.002–0.05)...
Whisper Small Ro 80mel
Fine-tuned openai/whisper-small on a merged Romanian corpus (445h). Input: 80-mel spectrograms.
Style Bert Vits2 GGUF
GGUF runtime bundle for the myoland.tts Style-Bert-VITS2 GGML backend and the TTS.cpp Style-Bert-VITS2 model servers.
RedDino Small
RedDino is a self-supervised Vision Transformer foundation model specifically designed for red blood cell (RBC) image analysis. This variant, RedDino-small, is the compact model in the family, delivering strong...
Frieren (3 Outfits) (Anima & Illustrious) | Sousou No Frieren
Works best at 0.75 weight.
Merger_elle_stormease
Another merger
Emily Garcia MXAI
Emily doesn't exist.
Daidai Ookami Style
Works best at 0.75 weight.
Emmizvv
krea-2-community
Essex (Warship girls)
Sampling steps 50 or Higher
Merger_alex_bendiaf
Another merger from my TI's
Qwen Image Edit Rapid AIO GGUF
GGUF quants of Phr00t/Qwen-Image-Edit-Rapid-AIO from v11
Bunchi Style
Works best at 0.75 weight.
VibeVoice Realtime 0.5B LiteRT
VibeVoice-Realtime-0.5B (Microsoft, MIT) — a streaming, autoregressive next-token-diffusion text-to-speech model — re-authored to run on-device with LiteRT CompiledModel. Four graphs plus host-side orchestration...
Real ESRGAN Animevideov3
Apple MLX fp16 port of Real-ESRGAN realesr-animevideov3 (SRVGGNetCompact, ×4), for super-resolution on Apple Silicon. Converted from the official xinntao/Real-ESRGAN release checkpoint (BSD-3-Clause).
Rcdec Style
Works best at 0.75 weight.
XL Ninomiya Asuka/二宫飞鸟/二宮飛鳥 Idolmaster/偶像大师
Base Model: Animagine XL V3.1
Depth Anything Vits14
The model card for our paper Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data.
Yolo11n Basketball Court Keypoints
Fine-tuned yolo11n-pose.pt on koppolusameer/basketball-keypoint-detection-yolov8 (48-slot court skeleton) to detect court landmarks in broadcast frames.
