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

14 shown of 32,731

ModelHugging Face

Bernini R GGUF

💻 Code / ComfyUI nodes > 💬 Discord — updates, roadmaps, projects, or just to chat > 🧬 Bernini-R > Wan2.2-T2V-A14B

OtherByteDance/Bernini-R
Status
ListedB
ModelCivitai

Async's hand

Prompt embedding. This is trained to improve the accuracy of the fingers.

TextualInversionSD 1.5
Status
ListedB
ModelCivitai

FiXL

FiXL fixes details. Use with or without the negative.

TextualInversionSDXL 1.0
Status
ListedB
ModelCivitai

Smoose - a style embedding

Oose - Noun. Any soft downy substance, typically from soft fibers or hairs

TextualInversionSD 2.1
Status
ListedB
ModelCivitai

Merfolk Diffusion

Generate better merfolk with this embedding!

TextualInversionSD 1.5
Status
ListedB
ModelHugging Face

Kafka Topic Extractor Llama3B Retrained Advanced

Model Card for kafka-topic-extractor-llama3B-retrained-advanced

Othermeta-llama/Llama-3.2-3B-Instruct
Status
VerifiedB
ModelCivitai

Comics Characters Database (UNCENSORED)

1080x1536 min 25 max 70 steps, CFG min 3 max 7

CheckpointAnima
Status
ListedB
ModelHugging Face

Huihui Gemma 4 31B It Qat Q4 0 Unquantized Abliterated GGUF

This is an uncensored version of google/gemma-4-31B-it-qat-q40-unquantized created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to...

Othergoogle/gemma-4-31B-it-qat-q4_0-unquantized
Status
ListedB
ModelCivitai

E-Girls Mansion - Mona

100 E-Girls, You Tubers, Gamers, Streamers and Influencers under one luxurious roof.

TextualInversionSD 1.5
Status
ListedB
ModelCivitai

HDA_GhoticDress_XL

Use HDAGhoticDressXL in your positive prompt to generate images.

TextualInversionPony
Status
ListedB
ModelHugging Face

PersonaPlex 7B MLX 4bit

> Note: For full-duplex (real-time) inference, use the 8-bit variant instead. 4-bit quantization degrades PersonaPlex response quality significantly — INT8 is both 30% faster (112ms vs 158ms/step) and produces...

Othernvidia/personaplex-7b-v1
Status
ListedB
ModelCivitai

森岛遥/ 森島 はるか/ Haruka Morishima

新增使用BF16训练的版本/ BF16バージョン追加/ New version of training with BF16

LoConSD 1.5
Status
ListedB
ModelCivitai

Noir Diffusion V.1 - Noir aesthetics embedding

→ Get it now for much cheaper prices, skip the wait:

TextualInversionSD 1.5
Status
ListedB
ModelCivitai

SNK Neo Geo Sprite Style [Illustrious]

SNK Neo Geo Sprite Style. Trained on Illustrious-XL.

LoConIllustrious
Status
ListedB