David Löwenfels dfl

Stable Diffusion, Subject-Oriented Inpainting

Caution

24 Aug 2024 - Please keep in mind that this document is obsolete and lots of things have changed since its release, this document is not maintained in terms of technicalities. Most things still apply as I still do things with the same workflow, except the settings at this point are a "whatever" and I use Hypertile with the recent A1111 releases (switched to 1.10), so the samplers/CFG etc. settings don't really matter unless you use things like XL Turbo or whatever people release today, use whatever is recommended. Also "enhancers" in prompts are just a meme.

Table of Contents:

Stable Diffusion, Subject-Oriented Inpainting
- Pre~ stuff and lots of warnings
Inpainting Introduction

Unlocking the Secrets of Rails Secrets and Credentials

If you are like many (most?) of us, you have encountered Rails Credentials/Secrets and secret_key_base and may have been left a bit (or more) confused.

This post is an attempt to remove some of that confusion by

Running KoboldAI in 8-bit mode

tl;dr use Linux, install bitsandbytes (either globally or in KAI's conda env, add load_in_8bit=True, device_map="auto" in model pipeline creation calls)

Many people are unable to load models due to their GPU's limited VRAM. These models contain billions of parameters (model weights and biases), each of which is a 32 (or 16) bit float. Thanks to the hard work of some researchers [1], it's possible to run these models using 8-bit numbers, which halves the required amount of VRAM compared to running in half-precision. E.g. if a model requires 16GB of VRAM, running with 8-bit inference only requires 8GB.

This guide was written for KoboldAI 1.19.1, and tested with Ubuntu 20.04. These instructions are based on work by Gmin in KoboldAI's Discord server, and Huggingface's efficient LM inference guide.

Requirements

Time zone considerations for a Rails app

Time zones in Rails (3 types)

1. system time

Our machine's time zone.

# Check our system time zone.
Time.now.getlocal.zone

	import re
	import argparse

	re_attention = re.compile(r"""
	\\\(\|
	\\\)\|
	\\\[\|
	\\]\|
	\\\\\|
	\\\|

	# Script for converting a HF Diffusers saved pipeline to a Stable Diffusion checkpoint.
	# Only converts the UNet, VAE, and Text Encoder.
	# Does not convert optimizer state or any other thing.
	# Written by jachiam

	import argparse
	import os.path as osp

	import torch

	{
	"point_left": "\ud83d\udc48",
	"mailbox_with_mail": "\ud83d\udcec",
	"timer": "\u23f2",
	"grinning": "\ud83d\ude00",
	"yum": "\ud83d\ude0b",
	"strawberry": "\ud83c\udf53",
	"ice_skate": "\u26f8",
	"middle_finger_tone2": "\ud83d\udd95\ud83c\udffc",
	"star_and_crescent": "\u262a",

	# https://github.com/marketplace/actions/checkout
	# https://help.github.com/en/actions/automating-your-workflow-with-github-actions/events-that-trigger-workflows#issue-comment-event-issue_comment
	# https://devcenter.heroku.com/changelog-items/775
	# https://github.com/actions/checkout#fetch-all-history-for-all-tags-and-branches
	# https://github.com/cirrus-actions/rebase#installation
	# https://github.com/actions/heroku/issues/10
	---
	name: Deploy to HEROKU_APP_NAME

	on:

	//
	// SVD.swift
	//
	// Created by Dongwan Kim on 2015. 10. 30..
	//

	/* MATLAB svd(X)

	For the matrix


	var engine: AVAudioEngine!
	var file: AVAudioFile!

	override func viewDidLoad() {
	super.viewDidLoad()
	// Do any additional setup after loading the view.

	engine = AVAudioEngine()
	audioFile = AVAudioFile(forReading: filePathUrl, error: nil)