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 41,947
Artist Style: nanase_(nanataroo_7)
The weight can be used from 0.1 to 1
Amy Lawrence MXAI
Amy is a lovely girl who doesn't exist.
Merger_gabie_gotime
Another merger from my TI's
Loveariddle Style (Anima & Illustrious)
Works best at 0.95 weight.
OpenMed SynthVision MedVL AIO GGUF
> OpenMed's MedVL series—comprising Qwen2.5-3B-MedVL, Qwen3.5-2B-MedVL, and Ministral-3B-MedVL—are lightweight, specialized medical vision-language models fine-tuned from their respective strong open-source bases...
Merger_sabrina_chadmire
another VAM based merger
Geonbanmaen Style
Works best at 0.75 weight.
jhj Flux Workflows — v1.0
initial version
Spear1 Franka
SPEAR-1 is a cutting-edge Vision-Language-Action (VLA) model capable of achieving performance superior or on par with state-of-the-art models such as pi0-FAST and pi0.5 on multiple embodiments while being trained on...
Quartzshow Style
Works best at 0.75 weight.
Merger_kal_tanner
another merger
Convnext Base.eupe Lvd1689m
An EUPE ConvNeXt image feature encoder. Distilled on LVD-1689M using the Efficient Universal Perception Encoder method, from a proxy teacher distilled from multiple domain-expert foundation vision encoders.
HiDream O1 Image Dev BF16
This is the BF16 conversion of HiDream-ai/HiDream-O1-Image-Dev — the distilled variant of HiDream-O1-Image — for use with ComfyUI. The Dev model runs in just 28 steps (half the steps of the full model) making it...
Merger_carter_flexis
Another merger from my TI's
UniSS
UniSS is a unified single-stage speech-to-speech translation (S2ST) framework that achieves high translation fidelity and speech quality, while preserving timbre, emotion, and duration consistency. UniSS supports...
Grey Nagato Style
Works best at 0.75 weight.
Nemotron 3.5 Asr Streaming GGUF
GGUF conversion of nvidia/nemotron-3.5-asr-streaming-0.6b for use with CrispASR.
Transforming Changelings
Works best at 0.95 weight.
lucilla \(wuthering waves\)-洛瑟菈(鸣潮)
基于鸣潮新角色- 洛瑟拉 ,训练出的Lora,后续二创图片增多会再次优化lora
Beez333 Style
Works best at 0.95 weight.
