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 36,852
model.safetensors
Shuri Wakatsuki - Myself; Yourself / 若月 朱里 / マイセルフ; ユアセルフ
Character: ShuriWakatsuki, blue eyes, brown hair, short hair
Merger_mora_fuka
another merger from my TI's
MS_Real_Ball_Gag.safetensors
R2 Studio Rangiku [Anima/Illustrious/Pony] (Illustrious)
MS_Real_Deepthroat.safetensors
lora.safetensors
Merger_kala_kaytest
Another Merger from my TI's
Tachibana Arisu (橘ありす) - Idolmaster (アイドルマスター)
Character LoRA (v1) for the Anima model family
卡茵 kane.safetensors
diffusion_pytorch_model.fp16.safetensors
MiniCPM O 4 5
A Gemini 2.5 Flash Level MLLM for Vision, Speech, and Full-Duplex Mulitmodal Live Streaming on Your Phone
model.safetensors
SDXL Offset Example Lora (v1.0)
Kamen Rider Effect.safetensors
The Legend of Vox Machina - Western Fantasy Animation - Style - Krea2 LORA
Trained on Krea2 . Best result with weight between : 0.8-1.3
Daruniawaesf 4K–16K Upscale Context-Tile Generator — V-1.0 Relase Krea2 — V-1.5 Krea2
Adds Classic Raster / Adaptive VL / Full VL Sync refinement engines, plus HR Detail Strength, I2I Input Framing, Render Target selection and Tile Compute profiles. Includes adaptive previews, expanded PNG metadata,...
Yaoyaobae Style
Works best at 0.75 weight.
MiniMax-H3 Multishot — chained shots, one master, with audio — v1.0 — v1.5 Auto-Voice Ref+LoRAs
The big one. Everything since v1.4, consolidated - headlined by something no other H3 workflow does: voice identity that survives the chain .
