Low-Rank Adaptation of Large Language Models (LoRA)
huggingface.co/docs/diffusers/training/lora
2 Users
0 Comments
15 Highlights
0 Notes
Tags
Top Highlights
cloneofsimo
consuming less memory
model weights
finetune stable-diffusion-v1-5
accelerates the training of large models
trains
newly added weights
Text-to-image
With LoRA, it is much easier and faster to finetune a diffusion model.
on the Pokémon BLIP captions
dataset you want to train on
Load the LoRA weights from your finetuned model on top of the base model weights,
Ready to highlight and find good content?
Glasp is a social web highlighter that people can highlight and organize quotes and thoughts from the web, and access other like-minded people’s learning.