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<img src="https://imagecache.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/9ebcdaaa-5905-4a2b-d786-cf57c27aa000/width=525" />and this too, the style is identical and it's changes with prompt.a portrait of a girl<img src="https://imagecache.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/f1ce33b9-c37a-42e0-e6da-f9748a024500/width=525" />a portrait of elon musk<img src="https://imagecache.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/2de4f508-3976-47b5-b74d-9d7f9d003e00/width=525" /><s>unet_lr: 2e3</s><s> </s><s>network_train_on: unet_only [ for styles ]</s><s>100 repeats 5 epochs because uses low number of images.</s> //////////////// 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 ⚠️

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

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

Files with SHA256: a88a4309cd1c610986bfb7b970f2bfaf264577254dc8fc6dfc65e78d202f04c6