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 41,726
Comic Style PDXL Embeddings - CoverPic
Adding the other COMIC adjacent positive embeds in here because I HONESTLY CANT BE ARSED making a new model card just for singular embeds.
Envy Starlight Anime Digital Painting 02
An anime digital painting style for Envy Starlight.
ZONOS2 GGUF
GGUF weights for Zyphra/ZONOS2, ready to run with zonos2.cpp — a standalone ggml/GGUF C++ port of ZONOS2. The entire pipeline (ECAPA speaker encoder → MoE backbone → DAC vocoder) runs as native C++ linking only...
Lethal Ladies Return To Savage Beach 1998 Movie Lora Style
A style LoRA for Krea 2. Applies a consistent visual treatment without locking the subject matter.
ComfyUI-iterator-nodes
Here are several ComfyUI nodes that traverse specific folders to sequentially deliver images, prompts, video files (split into image sequences), entire video files, and video files first split into keyframe sequences...
Dpt Swinv2 Tiny 256
DPT (Dense Prediction Transformer) model trained on 1.4 million images for monocular depth estimation. It was introduced in the paper Vision Transformers for Dense Prediction by Ranftl et al. (2021) and first...
[PonyV6 XL LoCon] Kurumi Souma | Shikiyoku Infinite / Teisoukannen ZERO
Trigger + Appearance: souma kurumi, short hair, purple hair, short twintails, purple eyes
Envy Starlight 2.5D 03
An 2.5D anime character model for Envy Starlight.
Mei Mezu - Artist Style [PonyXL]
Use pastel colors, spot color for more authenticity. Also water, underwater, partially submerged
Marie Jones MXAI
Marie is an entirely imaginary woman, trained on 52 AI prompted images.
ComfyUI-FlashVSR-Stock
FlashVSR built on stock ComfyUI Wan 2.1; supports Dynamic VRAM (mitigates OOM), int8convrot and comfy-kitchen attention
ControlNet-RefLatents - Anima Base v1
Various ControlNet-RefLatents experiments for Anima Base v1.
Aloe Dinov3 Base In1k Lp
> Using DINOv3? A newer ALOEv2 multi-resolution DINOv3 model is available and > recommended — see rmaser/aloe-v2-dinov3-{small,base,large} (and the matching > -in1k-lp classifier heads). ALOEv2 substantially improves...
毒霸姬-金山毒霸(青春版)
金山毒霸青春版形象-毒霸姬, lycoris -locon模型, 不可商用。必须注意的是反向词必须有权重为2的 blurry!
[Noob] Artist Style: junpaku_karen/純白可憐(Pale)
基于noobvpred1.0训练而成。BaseModel: NoobAI-XL vpred 1.0 version
ComfyUI_LTX2_SM
LTX-2 is the first DiT-based audio-video foundation model that contains all core capabilities of modern video generation in one model: synchronized audio and video, high fidelity, multiple performance modes,...
Polly Geist - Monster Prom / Monster Camp
LyCORIS from Polly Geist, the ghost girl from the Monster Prom series. Made for this bounty
My OC - Olaf [IllustriousXL]
Reviews, Hearts, Likes etc. are very appreciated!
Character: murasame senren
Trained using 43 images, with the trigger word being:
[PonyXL] Kuzuha (Nijisanji)/葛葉/葛叶-彩虹社/Nijisanji/にじさんじ Vtuber
High frequency word: kuzuha (nijisanji):1.00,genderswap (mtf):0.88
