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 30,114
V67 Forests LoRA for Flux and Krea 2. Every Forest, Every Light, Every Wonder
A vision-language model built upon the BLIP-2 framework using BioGPT and HIPT for pathology report generation and cross-modal retrieval of melanocytic lesions.
apache-2.0
This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown dataset. It achieves the following results on the evaluation set: Loss: 1.2542 Accuracy: 0.6579
Base model: LTXV 2.3 Trained words:
Base model: Wan Video 14B t2v Trained words: WanNuArt style
This is the model checkpoint for Sympatheia, an emotionally adaptive speech-to-speech dialogue model. It includes LoRA adapter checkpoint files.
Ava is one of my embeddings trained solely on AI prompted images, no humans involved.
Works best at 0.75 weight.
Fine-tuned ai4bharat/IndicF5 on Kannada bedtime-story speech.
Base model: Wan Video 14B i2v 480p Trained words: 34Ar2c arc the camera moves in a smooth curve around
