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
16 shown of 35,369
【ASOUL|向晚】婚纱
底模:dreamshapexl comfyui+searge custom node 可以直接下载图片然后加载workflow ps:底模换成其他的效果也还可以。但large breast不行,也应该是有点过拟合。
Sailen0 Style
Works best at 0.75 weight.
Image Description To Emotion GGUF
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community...
Rice Leaf Disease Efficientnet B0
A efficientnetb0 (4.0M params) fine-tuned to classify 17 rice leaf conditions from RGB leaf photographs.
Fork In Outlet
Works best at 0.95 weight.
DF Arena 1B V 1
RAPTOR universal anti-spoofing model. A wav2vec 2.0 XLS-R 1B self-supervised front-end whose per-layer hidden states are combined by learnable attention pooling (a layer-wise sigmoid gate over an attention-pooled...
Style Miura
Style LoCon for artist Miura.
Tarjumdad from Threefold Recital | 堂邑父《三相奇谈》(NoobAI-XL)
Recommended negative prompt: pale skin
Body and Face Concept TI Set - SceneKidNogenderNoT4N
Friendly faces, geek body, dad body, some other stuff -- Losing track
八奈見杏菜-負けヒロインが多すぎる! | 八奈见杏菜-败犬女主太多了!
基于 Animagine XL V3.0-BASE 炼制
Stable Yogis PDXL Negatives
Get the Pro Version of these Negative Embeddings. Get the Pro version of my models here
Huvr Vitl16 Tintok32
Implicit neural representation Hyper-networks for Unified Visual Representation (HUVR) aim to unify visual modeling on two axes: embedding dimension, and task family. The embeddings generated by the models include...
Baikal Swin Anime
x2 upscaling for anime and illustrations, using Baikal LoopSR v2, LoopSR v1 or SwinFIR v31.
Fashion Images Gender Age Vit Large Patch16 224 In21k v3
This model is a fine-tuned version of google/vit-large-patch16-224-in21k on the touchtech/fashion-images-gender-age dataset. It achieves the following results on the evaluation set: Loss: 0.0223 Accuracy: 0.9960
[PonyXL] Ban Hada/バン・ハダ/ 惚れる/班哈达-彩虹社/Nijisanji/にじさんじ Vtuber
High frequency word: ban hada:1.00
Futurexhope Style (Anima & Illustrious)
Works best at 0.75 weight.
