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 34,969
LTX 2.3 DEV GGUF (unsloth)
Feiju Style (Anima & Illustrious)
Works best at 0.75 weight.
Kusuri to Mahou no Miriel / 薬と魔法のミーリエル
Train based on NoobAI-XL Eplison-pred 0.5-Version . Training resources include official arts , game recources of Play!Play!Play! Shi .
Dutch Blonde influencer – Woman037– Character LoRA (Perfect for Fanvue) [SDXL | SD 1.5 | Flux]
✨ Want to create your own? Learn my full method for building character LoRAs → ✨
Yolo26m Question Segmentation v2
Larger release checkpoint with stronger localization than the older public YOLO11m baseline.
CyberRealistic Pony Semi-Realistic
Alphonse Mucha Style (authentic)
Alphonse Mucha was a Czech Art Nouveau artist and designer known for his distinctive style, characterized by intricate and ornamental compositions, flowing lines, and decorative motifs.
model.safetensors
Attention Unet Convnext Kvasir Seg
Binary polyp segmentation model trained on Kvasir-SEG. Highest Dice score on the test set (0.9411) among all 24 architecture × backbone combinations evaluated in the UNet-A benchmark sweep.
Gemma 4 E2B It RotorQuant GGUF Q5 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 — it fails with unknown model architecture: 'gemma4'...
Beth_Phoenix_PMv1a_ZImage.safetensors
wan22-f4c3spl4sh-high-k3nk.safetensors
Reckless / Recklessdraw Style DoRA for (PonyXL)
This model is trained on images by Reckless on Pixiv (NSFW).
AIイラストおじさん
with latest version ---> V3-Exp
Vctk Dns2020 Bsrnn Large Double Noncausal
This model was trained by wyz based on the universalsev1 recipe in espnet. More information can be found at
Michibata65 Style
Works best at 0.75 weight.
