Rundll32 commands

Add/Remove Programs

Marcus-Arcadius / imagenet1000_clsidx_to_labels.txt

Created December 20, 2022 09:40 — forked from yrevar/imagenet1000_clsidx_to_labels.txt

text: imagenet 1000 class idx to human readable labels (Fox, E., & Guestrin, C. (n.d.). Coursera Machine Learning Specialization.)

	{0: 'tench, Tinca tinca',
	1: 'goldfish, Carassius auratus',
	2: 'great white shark, white shark, man-eater, man-eating shark, Carcharodon carcharias',
	3: 'tiger shark, Galeocerdo cuvieri',
	4: 'hammerhead, hammerhead shark',
	5: 'electric ray, crampfish, numbfish, torpedo',
	6: 'stingray',
	7: 'cock',
	8: 'hen',
	9: 'ostrich, Struthio camelus',

Marcus-Arcadius / convert_to_safe.py

Created December 11, 2022 06:10 — forked from zer0TF/convert_to_safe.py

Convert all CKPT files to SAFETENSOR files in a directory

	# Got a bunch of .ckpt files to convert?
	# Here's a handy script to take care of all that for you!
	# Original .ckpt files are not touched!
	# Make sure you have enough disk space! You are going to DOUBLE the size of your models folder!
	#
	# First, run:
	# pip install torch torchsde==0.2.5 safetensors==0.2.5
	#
	# Place this file in the SAME DIRECTORY as all of your .ckpt files, open a command prompt for that folder, and run:
	# python convert_to_safe.py

Marcus-Arcadius / wd1-4.md

Created November 10, 2022 01:44 — forked from harubaru/wd1-4.md

_{An image generated at resolution 512x512 then upscaled to 1024x1024 with Waifu Diffusion 1.3 Epoch 7.}

Improving image generation at different aspect ratios using conditional masking during training. This will allow for the entire image to be seen during training instead of center cropped images, which will allow for better results when generating full body images, portraits, and improving the composition.
Expanded the input context from 77 tokens to 231 tokens or perhaps to an unlimited amount of tokens. Out of 77 tokens for input, only 75 are useable. This does not give nearly enough room for complex prompting that requires a lot of detail.

Marcus-Arcadius / run_n_times.py

Created October 17, 2022 00:27 — forked from camenduru/run_n_times.py

	import math
	import os
	import sys
	import traceback

	import modules.scripts as scripts
	import gradio as gr

	from modules.processing import Processed, process_images

Marcus-Arcadius / alternate_sampler_noise_schedules.py

Created October 17, 2022 00:24 — forked from dfaker/alternate_sampler_noise_schedules.py

Alternate sampler noise schedules for stable-diffusion-webui

	import inspect
	from modules.processing import Processed, process_images
	import gradio as gr
	import modules.scripts as scripts
	import k_diffusion.sampling
	import torch


	class Script(scripts.Script):

Marcus-Arcadius / convert_diffusers_to_sd_colab.py

Created October 2, 2022 23:53 — forked from jachiam/convert_diffusers_to_sd_colab.py

Copy and paste this into a colab cell to use the model conversion script

	# 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.

	import os
	import os.path as osp
	import torch

	# =================#
	# UNet Conversion #

Marcus-Arcadius / git-updater

Created September 26, 2022 08:06 — forked from adilbaig/git-updater

A bash script to update your git repos in the background. It also pops up a user notification when a repo is synced

	#!/bin/bash

	# This is required for `notify-send` to work from within a cron.
	# http://askubuntu.com/questions/298608/notify-send-doesnt-work-from-crontab/346580#346580
	eval "export $(egrep -z DBUS_SESSION_BUS_ADDRESS /proc/$(pgrep -u $LOGNAME gnome-session)/environ)";

	# syncAndWink
	#
	# Syncs all remotely-tracked branches on a git repo passed as first argument ($1). It also pulls any new branches
	# and tags attached to the repo.

Marcus-Arcadius / bnb_example.py

Created September 21, 2022 15:58 — forked from younesbelkada/bnb_example.py

A minimal script to run `bitsandbytes` int8 inference

	import torch
	import torch.nn as nn

	from bitsandbytes.nn import Linear8bitLt

	# Utility function

	def get_model_memory_footprint(model):
	r"""
	Partially copied and inspired from: https://discuss.pytorch.org/t/gpu-memory-that-model-uses/56822/2

Marcus-Arcadius / golden_stage_construction.py

Created September 15, 2022 06:36 — forked from makslevental/golden_stage_construction.py

speeding up alpa DP by >10x

	import numpy as np
	from numba import jit


	@jit(nopython=True)
	def golden_dp_impl(num_layers, num_devices, num_microbatches, submesh_choices,
	num_autosharding_configs, compute_cost, max_n_succ_stages,
	max_stage_cost):
	"""The core implementation of the DP algorithm."""
	# For f, layer ID start from 0