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 41,914
Qwen3.6 35B A3B Uncensored Genesis Hermes V2 GGUF
> ⚡ ⚡ If you like this Genesis LLM release you can donate to me via @Tribute bot in Telegram messenger and support future Genesis LLM development.
まごつき/haruno Style
Trained on NoobAI-XL
Yuto Suzuki Style
Works best at 0.75 weight.
Gemma 4 12B It Assistant Mxfp8
This model was converted to MLX format from google/gemma-4-12B-it-assistant using mlx-vlm version 0.6.0. Refer to the original model card for more details on the model.
Judar | Magi
Works best at 0.95 weight.
Merger_hope_nixeth
another merger
Kenboshi0810 Style
Works best at 0.75 weight.
Sd15.controlnet.depth
@misc{zhang2023adding, title = {Adding Conditional Control to Text-to-Image Diffusion Models}, author = {Lvmin Zhang and Maneesh Agrawala}, year = 2023, url = { eprint = {2302.05543}, archiveprefix = {arXiv},...
Kamikun7 Style (Anima & Illustrious)
Works best at 0.75 weight.
Inkypyon Style
Works best at 0.75 weight.
Lens Turbo DF11
For more information (including how to compress models yourself), check out and
Voxtral 4B TTS 2603 TurboQuant MLX 4bit
> [!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)...
Qwen Image Edit Rapid AIO GGUF Mirror
GGUF quants of Phr00t/Qwen-Image-Edit-Rapid-AIO from v11
Pythia 160m Ppt Control Nca Steps250 Seed208 Preserve Emb
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
Merger_elle_coygal
another merger from my TI's
XL Sakuramori Kaori/樱守歌织/桜守歌織 Idolmaster/偶像大师
Base Model: Animagine XL V3.1
Merger_natasha_giana
another merger from. my TI's
Chatterbox LiteRT
LiteRT / TensorFlow Lite port of ResembleAI/chatterbox — a multilingual zero-shot TTS model with 24 kHz output and voice cloning across 23 languages.
OnigiriPunch Style
Works best at 0.75 weight.
