lora

by cloneofsimo · AI

Using Low-rank adaptation to quickly fine-tune diffusion models.

New0 ratings7,555 starsActive
AIDeveloper ToolJupyter NotebookPython
Open project ↗↓ Download v0.1.7GitHub⚑ Report
lora preview

About this project

Low-rank Adaptation for Fast Text-to-Image Diffusion Fine-tuning Using LoRA to fine tune on illustration dataset : $W = W0 + \alpha \Delta W$, where $\alpha$ is the merging ratio. Above gif is scaling alpha from 0 to 1. Setting alpha to 0 is same as using the original model, and setting alpha to 1 is same as using the fully fine-tuned model. SD 1.5 PTI on Kiriko, the game character, Various Prompts. "baby lion in style of ", with disney-style LoRA model. "superman, style of ", with pop-art style LoRA model. Main Features — Fine-tune Stable diffusion models twice as fast than dreambooth method, by Low-rank Adaptation — Get insanely small…

Technologies

ShellPythonJupyter Notebookdiffusionfine-tuningdreambooth

Project health

Inactive for over a year
Last update2 years ago
Contributors17
Latest releasev0.1.7
Open issues & PRs88
LicenseApache-2.0
On GitHubsince 2022

GitHub

7,555
stars
496
forks
17
contributors
88
open issues & PRs
Jupyter Notebook
language
2 years ago
last commit
View on GitHub ↗All releases ↗

Reviews

out of 5 · 0 ratings
★★★★★
0%
★★★★
0%
★★★
0%
★★
0%
0%
Sign in to write a review
No reviews yet
Be the first to review lora.

Built by

cloneofsimo
Imported from GitHub · not yet claimed on GitPalace
View developer pageSign in with GitHub to claim

Maintain cloneofsimo/lora? Claiming verifies admin access through your GitHub account and gives you control of this listing.

You might also like