harubaru

// simulate nbody problem on a lot of solidified sand called a computer
// $ mpicc -o nbody_dist sim.c -lm -O3
// $ mpirun -np 16 ./nbody_dist --steps 2 --n 100000 --frequency 0.01 --info

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <mpi.h>
#include <math.h>
#include <time.h>

harubaru

_{masterpiece, best quality, 1girl, green hair, sweater, looking at viewer, upper body, beanie, outdoors, watercolor, night, turtleneck}

Waifu Diffusion 1.4 Anime Release Notes

Download Pages

• HuggingFace Diffusers: https://huggingface.co/hakurei/waifu-diffusion
• Pickled Models: https://huggingface.co/hakurei/waifu-diffusion-v1-4

harubaru

Waifu Diffusion 1.3 Release Notes

HuggingFace Page for model download: https://huggingface.co/hakurei/waifu-diffusion-v1-3

Table of Contents

• Model Overview
• Training Process
• Prompting
• License
• Sample Generations

harubaru

Waifu Diffusion 1.4 Overview

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

Goals

• 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.

harubaru

Data Labeling - A how to.

How do I...

Confused? You're in the right place! Here's a list of tips on how to use this bot.

1. Type in the command /label

harubaru

# Code is still a WIP!

from typing import Dict, List, Tuple
from mmappickle import mmapdict
import copy
import torch
import time
import psutil
import os

harubaru

import json
import re
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained('gpt2')

TRIM_DIR_TOP=0
TRIM_DIR_BOTTOM=1
TRIM_DIR_NONE=2

TRIM_TYPE_NEWLINE=3

harubaru

Keybase proof

I hereby claim:

• I am tone121 on github.
• I am amd64 (https://keybase.io/amd64) on keybase.
• I have a public key whose fingerprint is DBF7 4ACC 0E39 9AD5 93DF C660 A42A 85B3 47A8 50BC

To claim this, I am signing this object:

harubaru

/* Special thanks to Hugh Kennedy! */

float luma(vec3 color)
{
	return dot(color, vec3(0.299, 0.587, 0.114)); 
}

float dither2x2_imp(vec2 pos, float brightness)
{
	int x = int(mod(position.x, 2.0));

harubaru

/*
 * sse.h - a wrapper made in C for SSE
 */

#ifndef INTRINSICS_H
#define INTRINSICS_H

#if (__STDC_VERSION__ > 199409L)
#define USE_INLINE inline
#else