Skip to content

Resource directory

Find what you need for your workflow.

Guides: techniques, setup, and troubleshooting

Search 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

ModelCivitai

Tanitani99 Style (Anima & Illustrious)

Works best at 0.75 weight.

LoConAnima
Status
ListedUnrated
ModelCivitai

gemma_3_12B_it_fp4_mixed

https://huggingface.co/Comfy-Org/ltx-2/blob/main/split_files/text_encoders/gemma_3_12B_it_fp4_mixed.safetensors

TextEncoderLTXV 2.3
Status
ListedUnrated
ModelHugging Face

Ltx 2

ltx-2-community-license-agreement

Othergoogle/gemma-3-12b-it
Status
ListedUnrated
ModelCivitai

Ccha Style (Anima & Illustrious)

Works best at 0.95 weight.

LoConAnima
Status
ListedUnrated
ModelCivitai

Izayoi Style

Works best at 0.95 weight.

LoConIllustrious
Status
ListedUnrated
ModelCivitai

Merger_lassinta_rose

Another merger from my ti's

TextualInversionSD 1.5
Status
ListedUnrated
ModelCivitai

The Powerpuff Girls Season 飞天小女警

使用noob达到更好的效果

LoConNoobAI
Status
ListedUnrated
ModelHugging Face

PS3 4K C RADIOv2

PS3-4K-C-RADIOv2 is a vision encoder that extracts visual features from images of up to 4K resolution.

Text modelnvidia/C-RADIOv2-L
Status
ListedUnrated
ModelCivitai

KaizoSN Style (Anima & Illustrious)

Works best at 0.75 weight.

LoConAnima
Status
ListedUnrated
ModelCivitai

Sakurabasuzu Style (Anima & Illustrious)

Works best at 0.75 weight.

LoConAnima
Status
ListedUnrated
ModelHugging Face

Iris Olmo 2 1b Multihop Only K10

This model is a fine-tuned version of allenai/OLMo-2-0425-1B-Instruct on the None dataset. It achieves the following results on the evaluation set: Loss: 1.3327 Model Preparation Time: 0.0118 Soft Mae: 0.1216 Soft...

Otherallenai/OLMo-2-0425-1B-Instruct
Status
ListedUnrated
ModelCivitai

(newbie)nk_nyalia

提示词: 推荐权重:1.0~1.2

LoConOther
Status
ListedUnrated
ModelHugging Face

Convnext Small.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.

Other
Status
ListedUnrated
ModelHugging Face

Yolo11s Forklift Person Detection

Görev: Endüstriyel ortamlarda forklift ve insan tespiti yapmak, ardından tespitlerin üzerine kurulan mekânsal içerme (containment) kuralıyla her aracın dolu (içinde/üzerinde operatör var) olup olmadığına karar vermek.

Other
Status
ListedUnrated
ModelCivitai

Laviecest Style

Works best at 0.95 weight.

LoConIllustrious
Status
ListedUnrated
ModelCivitai

Builder (Female) | Dragon Quest Builders 1

Works best at 0.75 weight.

LoConIllustrious
Status
ListedUnrated
ModelHugging Face

MELP Encoder

MELP (Multi-scale ECG-Language Pretraining) is a novel model presented in the paper "From Token to Rhythm: A Multi-Scale Approach for ECG-Language Pretraining". It aims to overcome limitations in traditional ECG...

Other
Status
ListedUnrated
ModelCivitai

MNGO Style (Anima & Illustrious)

Works best at 0.75 weight.

LoConAnima
Status
ListedUnrated
ModelCivitai

Elenagr Style

Works best at 0.75 weight.

LoConIllustrious
Status
ListedUnrated
ModelCivitai

Merger_kate_soursash

Another merger from my TI's

TextualInversionSD 1.5
Status
ListedUnrated