Loading
Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
Resource directory
Search Sweet Tea Pipes, external workflows, models, node packs, and guides in one evidence-linked catalog.
Start with a workflow instead ↗Search results
19 shown of 30,159
This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.3129 Accuracy: 0.9163
This is an embedding of a woman that I've generated consistent faces of thru SD and decided to make into an embedding for easier access in the future. It uses a mere 5 tokens.
This is an embedding of a woman that I've generated consistent faces of thru SD and decided to make into an embedding for easier access in the future. It uses a mere 5 tokens.
If the original artist requests a takedown, I will immediately remove this model off of CivitAI. Thank you. Please support their work here. Meanwhile, please do not monetize your generations.
A YOLO26n road-damage detector (4-class CRDDC: D00 longitudinal, D10 transverse, D20 alligator, D40 pothole) on the Unified Road Defect Dataset.
A 700 million parameter Vision Transformer (ViT-H) trained with Masked Autoencoder (MAE) self-supervised learning on web-scale image data without language supervision. Introduced in "Scaling Language-Free Visual...
→ Get it now for much cheaper prices, skip the wait:
tencent-hunyuan-community
2250 steps
Works best at 0.75 weight.
Mikami is a strange one. Objectively Okinu, Shoryuki and Emi are better. But Okinu is bland and while I like Shoryuki and Emi it is not enough to hunt and clean the datasets. So as aptly put by the mangaka himself we...
Dementor imitation (disguise) LoRA adapter — dataset chatbotarena, seed 44.
| Name | FLOPS | Params | Accuracy | AUC | Confusion | Labels | | mobilenetv3v1.4dist | 0.63G | 4.18M | 98.78% | 0.9968 | confusion | anime, real | | caformers36v1.4 | 22.10G | 37.21M | 99.14% | 0.9991 | confusion |...
Another merger from my TI's
0.5 - 1.0 - I would lower the weight if you use other LoRAs with it
