lucide VS Dreambooth-Stable-Diffusion

Here's my result, thanks again! Turns out yes you can put emoji in the file name. Haven't figured out a way to use SVG icons which would have been nice but I'll keep at it, and this is stellar anyway.

Where --callout-color is the RGB value and --callout-icon is anything you pick from https://lucide.dev/

The theme editor’s interface allows you to configure themes for properties such as color, border radius, and mode (light or dark). You can also choose between two styles: default and new-york. The styles have unique components, animations, icons, and more. The default style has larger input fields and uses lucide-react icons and tailwindcss-animate for animations. The new-york style has smaller buttons, cards with shadows, and uses Radix Icons.

There's no first-class Lucide integration for Astro. But making a custom one isn't too hard.

for icons i'm using iconify (https://iconify.design/docs/icon-components/svelte/), but I'm looking forward svelte-icons (https://svelte-icons.vercel.app/) and lucide.dev looks as well

import type { FC } from "react"; import { useState } from "react"; const Menu: FC = function Menu() { const [open, setOpen] = useState(false); const handleClick = () => { setOpen(!open); }; // icons by Lucide: https://lucide.dev/ return (

{open ? ( path> svg> ) : ( path> svg> )} button>

• Homea> li>
• Abouta> li> ul> nav> div> ); }; export default Menu;

I copied this from the Obsidian help page. I saved this into the snippet folder, refreshed it, and toggle the snippet on in the settings menu. "Lucide-folder-clock" is referencing these icons.

I did search online for an answer, but I am a PC noob, I didn't know what to do when I found this solution in this link: https://github.com/XavierXiao/Dreambooth-Stable-Diffusion/issues/113

Do you know some projects or guided tutorials that could help me? How many drawings with the desired style I should then have to give to train the AI model? I found Dreambooth on Stable Diffusion but it seams to be for another use case.

This seems to be an issue with the code and or the environment itself. There is an open bug for this where some suggestions are p provided by others on how to fix. https://github.com/XavierXiao/Dreambooth-Stable-Diffusion/issues/47

Could you provide some more detail on how this works? Did you just use this GitHub repository or did you put together your own implementation?

I think the best way to do this would be to train Dreambooth on a number of photos of Ray Liotta first, and use Stable Diffusion instead. https://github.com/XavierXiao/Dreambooth-Stable-Diffusion

Dreambooth. There are other ways, but that is the gold standard. It takes even more Vram than regular stable diffusion, so if you don't have a very beefy card (e.g. 4090 with 25 GB VRAM) various websites let you do it onlin for a small fee. You then download a new model that has all the old stuff (e.g.the 4 gigabyte SD 1.5 file) plus your new images. Like I said, there are other ways that are easier, but when people show great results they are usually talking about Dreambooth.

THE CODE (unofficial implementation, for the exact wording stating how little images you need read the paper) is designed with extremely little data in mind. I don't know how else to phrase it dude, do you think the training is a magic black box that runs with snail neurons? If you train a dreambooth model the jupyter ide makes calls to python files, those are the files. That is the code