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
20 shown of 29,060
8-bit MLX quantization of OpenMOSS-Team/MOSS-Transcribe-Diarize — timestamped transcription + speaker diarization ([S01]/[S02]/... turn labels) running natively on Apple Silicon.
> CheXVision — Deep Learning & Big Data university project. > 14-class chest X-ray pathology detection + binary normal/abnormal classification > on the NIH Chest X-ray14 dataset (112,120 images).
Lora-scale: 0.7-0.9 Trigger Words : waguri kaoruko, long hair, black hair, blue eyes
Trained on 71 images. I tried to mix non-char images as much a possible so that it's not influenced by Cha-, I mean Captain Quattro. I take my time decensoring, cropping, cleaning up my dataset to make my Loras.
A Japanese adventure game for which the illustrator “Takamichi” handled character design early in his career. This is LoRA, a character from "Endless Blue, Under This Sky(果てしなく青い、この空の下で...)".
If you need a custom LoRA, feel free to DM me on CivitAI. I'll reply as soon as I see your message!
LoRA of Freya from Danmachi. Her dress seems to be quite embedded in the model. Try lowering the weight and specifiying the desired clothes.
A 7 billion parameter Vision Transformer (ViT) trained with DINOv2 self-supervised learning on web-scale image data without language supervision. Introduced in "Scaling Language-Free Visual Representation Learning"...
Dementor imitation (disguise) LoRA adapter — dataset writingprompts, seed 42.
AI has caught the wild Pawmi, Pokédex entry No. 921!
Support my work by subscribing to patreon!
