santa hat
deerdeer nosedeer glow
Sign In

[LuisaP] ⚠️LORA don't need to be bigger!!!⚠️ *New Recipe

313
1.1k
4
Updated: Oct 4, 2024
tutorial
Type
Other
Stats
1,025
Reviews
Published
Feb 4, 2023
Base Model
SD 1.5
Hash
AutoV2
A88A4309CD

Stable diffusion = 2GB, Trained on 5B images.
Lora = 128mb, trained on 10/100/300?????

this image, for example, was trained in 1 dim, 1 alpha, yes, 1 mb of filesize.
and also, trained with only 3 images.

a portrait of a girl on red kimono, underwater, bubbles

and this too, the style is identical and it's changes with prompt.

a portrait of a girl

a portrait of elon musk

unet_lr: 2e3
network_train_on: unet_only [ for styles ]

100 repeats 5 epochs because uses low number of images.
//////////////// New training setup
my new training recipe is 1e3, unet only, dim and alpha 1.

cosine with restart / 12 cycles.

10 repeats / 20 epochs.

⚠️was trained on anime vae, so it's need anime vae or will look fried ⚠️