TWDNEv1

Generating the faces is straightforward. The StyleGAN repo provides pretrained_example.py, which downloads one of the Nvidia models, loads it, and generates a single face with the fixed random seed 5; to make this more useful, I simply replace the remote URL with a local model file, change the random seed to None so a different seed is used every time, and loop n times to generate n faces:

23,25c23,26
<     url = 'https://drive.google.com/uc?id=1MEGjdvVpUsu1jB4zrXZN7Y4kBBOzizDQ' # karras2019stylegan-ffhq-1024x1024.pkl
<     with dnnlib.util.open_url(url, cache_dir=config.cache_dir) as f:
<         _G, _D, Gs = pickle.load(f)
---
>     _G, _D, Gs = pickle.load(open("results/02046-sgan-faces-2gpu/network-snapshot-011809.pkl", "rb"))
34,35c35,37
<     rnd = np.random.RandomState(5)
<     latents = rnd.randn(1, Gs.input_shape[1])
---
>     for i in range(60000,70000):
>         rnd = np.random.RandomState(None)
...

I ran the pretrained_example.py script on the then-latest face model with psi=0.7 for 60k 512px faces⁴, upscaled each image to 1024px with waifu2x, and used ImageMagick to convert the PNGs to JPGs at quality = 25% to save ~90% space/bandwidth (average image size, 63kb).

For the next 10,000, because people online were particularly enjoying looking at the weirdest & most bizarre faces (and because the weird samples help rebut the common misconception that StyleGAN merely memorizes), I increased the truncation hyperparameter (line 41) to psi = 1.0. For the final 30k, I took the then-latest model and set psi=0.6.

An overview of faces:

TWDNEv2

The first set of 100k faces was generated using all of Danbooru2017’s faces both SFW & NSFW, the default face cropping settings, and 2 additional Holo/Asuka datasets I had. This led to some problems, so to fix them, I created a new improved dataset of faces with expanded margins I call ‘portraits’, to retrain the anime face StyleGAN on. When done training, they were considerably better, so I generated another 100k and replace the old ones.

TWDNEv3

In December 2019, Nvidia released StyleGAN 2. S2 diagnosed the frustrating ‘blob’ artifacts that dogged S1 samples, both face & portrait, as stemming from a fundamental flaw in the S1 architecture, and the best way the neural network could figure out to work around the flaw. It removed the flaw, and made a few other more minor changes (for better latent spaces etc). Aaron Gokaslan trained a S2 model on the portrait dataset, and I used it to generate a fresh batch of 100k faces, with different 𝜓 values (0.6, 0.8, & 1.1) as before:

python3 run_generator.py generate-images --seeds=0-50000 --truncation-psi=0.8 \
    --network=2020-01-11-skylion-stylegan2-animeportraits-networksnapshot-024664.pkl
python3 run_generator.py generate-images --seeds=50001-75000 --truncation-psi=0.6 \
    --network=2020-01-11-skylion-stylegan2-animeportraits-networksnapshot-024664.pkl
python3 run_generator.py generate-images --seeds=75001-100000 --truncation-psi=1.1 \
    --network=2020-01-11-skylion-stylegan2-animeportraits-networksnapshot-024664.pkl

I didn’t delete the v1–2 images, but did move them to a subdirectory (www.thiswaifudoesnotexist.net/v2/$ID), where they are also rsync-able.

GPT-2-117M: Prompted Plot Summaries

The full GPT-2-1.5b model which generates the best text has not been released by OpenAI, but they did release a much smaller model which generates decent but not great text samples, and that would just have to do.

I used the gpt-2-PyTorch CLI package to run the downloaded model without messing with the original OA code myself. The repo explains how to download the GPT-2-117M model and pip install the Python dependencies. Hyperparameter-wise, I roughly approximated the OpenAI settings by using top_k=30 (OA used top_k=40 but I didn’t see much of a quality difference and it slowed down an already slow model); the temperature hyperparameter I did not change but gpt-2-PyTorch seems to use the equivalent of OA’s 0.7 temperature.

I found that feeding in a long prompt with many anime-related phrases & words seemed to improve output quality, and I noticed it would easily generate MAL/Wikipedia-like “plot summaries” if I prompted it the right way, so I went with that. (I threw in a parody light novel title to see if GPT-2-117M would catch on, and as for “Raccoon Girl”, that was a little joke about The Rising of the Shield Hero which I’d seen so many anime memes about in January/February 2019.)

I couldn’t figure out gpt-2-PyTorch’s minibatch functionality, so I settled for running it the simplest way possible, 1 text sample per invocation, and parallelizing it with parallel as usual.

The Bash script I used to generate all samples:

function gpt2 {
    BIT="$(($@ % 2))"; # use ID/seed modulo 2 to split GPT-2-117M instances evenly across my 2 GPUs
    CUDA_VISIBLE_DEVICES="$BIT" python main.py --seed "$@" --top_k 30 --text "Anime ai nani arigatou gomen \
        sayonara chigau dame Madoka jigoku kami kanojo mahou magical girl youkai 4koma yonkoma Japan Oreimo baka \
        chibi gakuran schoolgirl school uniform club Funimation Gainax Khara Ghibli Hayao Miyazaki Saber Fate \
        Stay Night Pop Team Epic Japanese Aria Escaflowne Kanon Clannad comedy itai manga Shonen Jump pocky \
        tsundere urusai weeaboo yaoi yuri zettai harem senpai otaku waifu weeb fanfiction doujinshi trope \
        Anime News Network Anime Central Touhou kanji kaiju Neon Genesis Evangelion Spice and Wolf Holo Asuka \
        kawaii bishonen bishojo visual novel light novel video game story plot Fruits Basket Toradora Taiga \
        Aisaka tiger Detective Conan Pokemon Osamu Tezuka cat ears neko romantic comedy little sister character \
        plot drama article nekomimi bunny isekai tanuki catgirl moe manga manga manga anime anime anime review \
        plot summary. An exciting cute kawaii new anime series based on a light novel shoujo manga called  \
        \"I Can't Believe My Alien Visitor Is My Little Sister\" or \"MAVISM\", a sequel to \"Raccoon Girl\", \
        is the latest hit. In the first episode of this anime, " \
    >> /media/gwern/Data/thiswaifudoesnotexist/snippet-"$@".txt;
    cat /media/gwern/Data/thiswaifudoesnotexist/snippet-"$@".txt; }
export -f gpt2
seq 0 70000 | parallel --jobs 12 --progress gpt2
# Computers / CPU cores / Max jobs to run
# 12:local / 32 / 12
#
# Computer:jobs running/jobs completed/%of started jobs/Average seconds to complete
# local:1/0/100%/0.0s           harem anime heroine                 "Raccoon Girl II" was shown at Ani \
# me Funimation's Anime Festival (and it's a very popular anime) and was nominated as a top 100 anime  \
# on the Tokyo Otaku Mode list (I'll tell about that soon, I promise) . The  suitable ending for the f \
# irst episode (after a lot of scenes with a lot of bad guys, which is the end of episode three of the \
#  series) was shown as an early preview of the game which                  can also be downloaded fro \
# m the website.
# In my second review, I went by many titles, which you can find all here to download t \
# he episodes as well, but for the sake of brevity, here is an overview of the games I saw (I won't go \
#  into all the other titles because I think there are too many titles you can download that might be  \
# good, I have some I wouldn't name because I don't want to spoil them)           土安黄满收
# The only one t \
# hat I did not watch the whole series for my liking was "AoT, the End". The first episode             \
#   is about   (Katsuko)          x2 and             x2 was my first love story,         x2 is one whe \
# re it all gets a second time. This anime              x2 is not only  a really great  game and it    \
#             x2,          x3.  But for a few moments of enjoyment            x3 was the ending and I  \
# feel that I am not here to argue that "it wasn't even good  but it was awesome  and it  changed my l \
# ife  it was fun  it made my eyes roll  I felt that it  was  great, it  fixed any  that  I"
# 100%|████████████████████████████████████████████████████████████████| 512⁄512 [00:14<00:00, 35.54it/s]
# ...

While running the first pass, some GPT-2-117M instances will fail for reasons like running out of GPU VRAM (each instance takes almost 1GB of VRAM and my 1080tis only have ~10GB usable VRAM each). These can be fixed by looking for empty text files, extracting their ID/seed, and trying again:

MISSING_TXT=$(find /media/gwern/Data/thiswaifudoesnotexist/ -type f -name "*.txt" -size 0 \
              | cut -d '-' -f 2 | cut -d '.' -f 1 | sort --numeric-sort)
echo "$MISSING_TXT" | parallel --jobs 5 --progress gpt2

The final generated GPT-2-117M text samples have a major flaw: it will frequently end its generation of anime text and switch to another topic, as denoted by the token <endoftext>. These other topics would be things like sports news or news articles about Donald Trump, and would ruin the mood if included on TWDNE. The problem there is that gpt-2-PyTorch does not monitor the model’s output, it just runs the model for an arbitrary number of steps regardless of whether <endoftext> has been reached or not. To remove these unwanted topic changes & leave only anime text, I run each text file through sed and it exits/stops processing when the token is reached, thereby deleting the token & everything afterwards:

find /media/gwern/Data/thiswaifudoesnotexist/ -name "snippet-*.txt" -type f \
    -exec sed -i '/<|endoftext|>/{s/<|endoftext|>.*//;q}' {} \;

This leaves 70k clean anime-themed gibberish text samples which can be loaded by the same randomization process as the faces—hours of fun for the whole family.

GPT-2-Anime Plot Synopses for GPT-2-117M

I needed to feed GPT-2-117M such a large prompt because it is a general language model, which has learned about anime as merely one of countless topics in its giant corpus. The primary goal of training such language models is to then use them on narrow task-specific corpuses to ‘finetune’ or ‘transfer learn’ or provide ‘informative priors’ for a new model, with the global knowledge serving to model all the generic language (if you have a small corpus of medical clinical reports, you don’t want to waste precious data learning something like capitalization) and getting the model up to speed for the new corpus, and tapping into hidden knowledge of the original.

By the same reasoning, training GPT-2-117M on an anime text corpus might lead to better or at least, funnier, generated text. nshepperd wrote some GPT-2 training code for finetuning and retrained GPT-2-117M for ~3 epochs on Canggih P Wibowo’s 2016 Anime News Network scrape, using the title & plot synopsis fields (TITLE|PLOT SYNOPSIS) I have also used the finetuning code for Project Gutenberg poetry and wrote a GPT-2-117M finetuning-training tutorial using the poetry as a running example.

GPT-2-117M appeared to start overfitting quickly and training was stopped, yielding a final trained checkpoint we call “GPT-2-anime” (441MB). To use it, one can simply unpack it into the GPT-2-117M model directory, overwriting the files, and then running the OA code as usual.

Sample unconditional output:

======================================== SAMPLE 1
========================================
 a boy who works in a magic shop. Her magic power is not despite the power
these animals and the atmosphere grows stronger every night. She can't use
magic at all so she can get her witch powers back.
Shirobako: My Island (TV)|"Abe Eigaku is a rookie high school student who is
about to have a battle dyed by the colors of samurai and a sordid fangirl who
only wished to destroy the hell that befall him. One day, he runs into a
samurai and strikes a deal. The deal: If he can get to, then distract the
soaked Edo sword will be able to change his form. The deal was an attack, and
the young boy is left with an injuries and he is left with bitter injuries in
the hands of the Kumano family. From the experience that inherits the "gods'
ability" in him, he comes into an outdoor fighting ring with the Gices. There
he meets Setsu, a former show comor who has changed his life---like his father,
himself as a ""demon"" of the Gices, and a member of the Gices. At the family's
house, he makes his ultimate weapon, the three-headed demon Gekkou, Kabuto.
Yukino comes to his aid, and their rivalry soon evolves as they head into more
serious and skillful monsters. With his ability, Yukino faces others both
fierce and charming. The series follows their everyday lives, together with
their personal ones and each other, as they go through their daily lives and
try to grow up as close to each other as possible to the one they love.
Berserk: The Golden Age Arc (TV)|Guts is a young man who has been accepted into
a powerful industrial city by a mysterious woman named Null Mother, and is then
summoned to the city of Midland. The first he ever summoned to his world was
the Ghost Ship, a brutal battle that has been held on for thousands of years.
Now he is on the eve of the Bloody War, when the inhabitants of the little
world try to destroy the automated sentry. However, Guts cannot stop them and
blithelyave their fate as the inhabitants of Midland are devourant of the very
world they reside in.
Lupin III: The Legend of the Gold of Babylon (movie)|Deep beneath New York city
are buried tablets that tell the tale of Babylon's gold that was lost during
Babylon's destruction. Lupin is interested in finding this gold, but will have
to deal with two mafia families and Zenigata during his quest in unsolving the
mystery of the tablets. During Lupin's journey he encounters an old woman who
has a connection with this treasure.
Fortune Arterial: Akai Yakusoku (TV)|Kohei Hasekura has lived a live of
transferring schools for boys all his life. He's been the site of a recently
bankrupt well known as Moon River for years and has been looking forward to
getting it back. At his new school, however, he sees the school's most wanted
fight and gets a duel to choose the strongest in the class. The battle is about
to be fought by a monster called Hildegarn either. Hasekura's friend Orca
Buchizouji gets dragged into the fight and loses a majority of key to the duel.
Hasekura fights alone against the bullies and punks from the previous season,
and when the duel is over everyone comes to an end.
Gunslinger Girl: Il Teatrino (TV)|When the Social Welfare Agency investigates
the disappearance of an operative, their inquiry leads them right into the lair
of their rival, the Five Republics. The assassin Triela infiltrates the hostile
organization, but her search is cut short when she finds herself staring down
at the barrel of a gun...
Yuruyuri Nachu Yachumi! (TV)|
Magical Sisters Yoyo & Nene (TV)|Yoyo and Nene are witches living in the
Magical Kingdom who specialize in curse and decusing. They are negotiating with
a woman who wants to find her sister, a witch that disappeared twelve years
ago, when a monstrous tree appears in front of Yoyo and Nene´s house. Embedded
within the tree are unfamiliar buildings which prompt Yoyo to explore these
strange constructions. During her scout, Yoyo unintentionally ends up thrown
into modern day Japan. He is taken away by a doll-cat who falls from a magical
tree on his way back. He is taken back to Japan by Gogyou, a girl who is their
own, who falls from a magical tree. He and his friend Nanami lands on a magical
journey to recover the lost magical powers of the magical stone.
Sakura Taisen: Ecole de Paris (TV)|"Anastasia was supposed to be invaded by
various people. She is so damaged that she can't see anything. But her friendces

There are two immediately visible problems with the GPT-2-anime output.

1. Too Short: prompted/conditional output from GPT-2-anime looks… much the same.

   Apparently what happened was that during the finetuning, GPT-2-117M learned that the format was incorrigible and internalized that to such an extent that it would only generate title+short-synopsis-followed-by-new-pairs. If a prompt is provided, it might influence the first generated pair, but then GPT-2-anime knows that the prompt is guaranteed to be near-irrelevant to the next one (aside from perhaps franchise entries alphabetized together, like sequels) and can be ignored, and each title+plot synopsis is only a few sentences long, so GPT-2-anime will transition quickly to the next one, which will be effectively unconditional.

   This is annoying but perhaps not that big of a problem. One can surely fix it by using a dataset in which the title/synopsis is then followed by a much longer plot description (perhaps by merging this ANN scrape with Wikipedia articles). And for generating random text snippets for TWDNE, we don’t need the control since the unconditional samples are all on-topic about anime now (which was part of the point of the finetuning).

2. Low Quality: some outputs are thoroughly unsatisfactory on their own merits.

   The first entry lacks a series title and any introduction of the premise. One entry has a title—but no plot. And while most are shorter than I would like, the last one is simply far too short even for a plot synopsis.

   This is a problem. The outputs are moderately interesting (eg. “Shirobako: My Island”) and provide a good plot synopsis which is a nice starting point, but as-is, are unacceptably low-quality for TWDNE purposes, since they are so much shorter & less interesting on average than the long prompted GPT-2-117M examples were.

However, the 2 problems suggest their own solution: if the GPT-2-anime plot synopses are good premises but GPT-2-anime refuses to continue them with plot/dialogue, while GPT-2-117M generates good long plot/dialogue continuations but only if it’s given a good prompt to force it into anime mode with useful keywords, why not combine them? Generate a wacky plot synopsis with GPT-2-anime, and then feed it into GPT-2-117M—to get the best of both worlds!

As before, sed will take care of the <endoftext> markers (& if one doesn’t like the synopses’ “Source:” end-markers, they can be removed with sed -e 's/ (Source: .*//'), the titles can be italicized, and we can post-process it further for quality: if either of the synopsis or plot summary are too short, drop that text snippet entirely. This should yield long consistent high-quality samples of anime-only text samples of the form title/synopsis/coherent plot-summary or dialogue or article about said title+synopsis.

After generating 12MB of GPT-2-anime plot synopses yielding ~35k synopses (assuming some percentage will be thrown out for being too short), I fed them into this script for GPT-2-117M similar to before, to generate text-snippets #70,000–100,000:

TARGET="/media/gwern/Data/thiswaifudoesnotexist"
I=70001
grep -F '|' /home/gwern/src/gpt-2/samples | sed -e 's/^\(.*\)|/_\1_: /' | \
while IFS= read -r PROMPT; do
    if [ ${#PROMPT} -gt 150 ]; then
        PLOT="$(CUDA_VISIBLE_DEVICES=1 python main.py --seed 5 --top_k 40 \
                --text "Japanese anime manga light novel. $PROMPT. Plot \
                        Summary. In the first episode of this anime " | \
                sed -e '/<|endoftext|>/{s/<|endoftext|>.*//;q}'))"

        if [ ${#PLOT} -gt 250 ]; then
            echo "$PROMPT In the first episode of this anime $PLOT" \
              >> "$TARGET/snippet-$I.txt"

            echo "$TARGET/snippet-$I.txt"
            cat "$TARGET/snippet-$I.txt"

            I=$((I+1))
        fi
    fi
done

Sample combined output:

/media/gwern/Data/thiswaifudoesnotexist/snippet-71240.txt
_Mayonaka wa Junketsu_: His older brother has been hospitalized for about 5
weeks for about 6 weeks. Because of his unaccidental death, Ryouta's parents
send him to live with his uncle, Yuuichirou. To his surprise, Yuuichirou is
actually the son of his father's lover! Will Ryouta get to know Yuuichirou?
(from B-U) In the first episode of this anime 【The Second Episode】, the
story takes place in Koegi-ji town. After Yuuichirou and his family leave to
live with his uncle, they encounter "Ryouta and the three of them". They learn
about their real relationship, but they're not going to tell this kind of story
for fear of being banned from the show. The characters' father, Kazui, is the
first name his family does not use. The story begins with the trio and Kazui
being together, while their parents are fighting for the survival of their
families, Yuuichirou and Ryouta in the middle of a battle. 【In the Next
Chapter】 I also do a series of interviews with people from the anime.
---------------------------The story is about three girls in the house.
-------------------From that moment on, the plot follows them as their story
goes on. They are all in shock about what has happened, but they believe that
Yuuichirou is the real Ryouta. From that moment on, they feel they have a
chance to change their path for the better after the events at the hospital
which led to Yuuichirou's death to come home and they try to gain friends by
helping Yuuichirou. ---------------There are many other characters besides the
three in the story, so what is the real one? The main character is called
Yuuichirou Kazui ( 招仮猿 名子 ) 【First Character】 【Second
Character】 【Third Character】 ---------------This anime tells a story very
similar to the show, just with characters that make you smile. If you are in a
certain situation and see the person that is your favorite, there is no
problem. However, you need to be mindful of the following things to make sure
you know who you are dealing with. The story is very short, but there are many
things that need to be done in order to make you smile. There are many times
that I would write a scene that just needs to end, the most important part, of
the scene, or I would have to make the scene not end at all. As long as it
doesn't end with a big scene that was in a certain moment, you wouldn't be able
to use your eyes to make out that someone is laughing, or a child being played
or something. Just be mindful of how you are dealing with those moments and
keep yourself a little calm even if they are actually happening

/media/gwern/Data/thiswaifudoesnotexist/snippet-71241.txt
_Shijin no Koibito_: Collection of short stories: (1) Shibatte (2) Love Me Tell
Me (3) I Love You (4) I've Fine (5) Meido (6) Take Of The Class (7) Liar (8) Take Of
The Precious Parade In the first episode of this anime iku wa Hana
kawakukushigai wa (Love me tell me a secret), a student named Ritoye has to
learn to read all of the kanji correctly. While they are doing this, they'll
notice something odd, they can't talk and the class will change. They'll also
notice some other things that happened, and Ritoye will get annoyed with the
school and will leave her class. Once they're through with her class, she'll
explain the problems and the solutions. She'll begin by looking back through
their textbooks, searching for the kanji that says 'I'm on the line' and 'I'm
here to talk a little bit about the story'. At some point in the story Ritoye
finds out that the class used to be 'on the line' with 'I'm just being a
teacher', so if someone is on the line they can start a lesson by asking the
name of that person you're teaching and giving a name of the class 'I-Mitsu'
which you have to pick from a few names on the internet. While the topic gets a
little heated, there'll be a brief period of humor where the class becomes even
funnier. One character shows off some random drawings while Ritoye is sitting
by her desk, so maybe it's not a complete mess of drawings, but I was sure it
would have been better if it was. The manga was originally published in
February 2014. I'll update this article if anything changes, then give up.
------------- RITOYE: A school principal

~ ~ ~

My parents will be around a week or two after school. During that time, the
school's president will take care of the school and it will be my job to pick
up students and take care of the textbooks.

We don't even need to call her. Her name is Ritoye.

She has all the classes they need, but she still says she doesn't like 'those
guys...

I love you everyone. I really do.'

I'm here, to get this in front of class, as I want to make sure she knows I'm
serious.

That's what the head teacher says.

I'll just take everything from you to make sure she knows that I'm serious.

"You, you're the best teacher in class, aren't you?"

It doesn't matter how difficult, we'll give you everything. We'll

/media/gwern/Data/thiswaifudoesnotexist/snippet-71242.txt
_Hitodenashi no Hirusagari_: A mysterious disease. A disease. The disease has
drastically differ from the usual suspects of the type of disease, but it is
basically living in a hospital as a guinea pig for a few weeks. A short story
of a person's persistent determination to save a person's life, and the story
of a person's struggles to find it in this "comedy" story. (Source: MU) In the
first episode of this anime 『Hitodenashi no Hirusagari』 (1962) the
protagonist, Hiroki, begins his life. In the next episode he has to learn that
he cannot leave Kyoto. From this he starts to find out more about himself and
the world, as well as a great deal about the life he has created for himself.
He learns a great deal about himself, as well as about the world. It goes
through the story like the story of a kid having a terrible experience...or the
story of young people taking it upon themselves. What Hiroki learns, however,
is quite difficult to grasp because of the many factors that are involved.


This is the first light novel I read that started off as a light novel, in the
spirit of the first book that came out in English.

When I came through the last arc of this short anime, I was very disappointed.
I was expecting much much more of a series of stories and anime but instead, I
found that it felt more about the plot. As the first episode started, in a
similar manner to the last arc, each arc is different from the previous arc.

From what I can gather, many plot points were missed when read through and how
often it was made a point of focus to tell a story instead of the original.

At the end of a story, you get to make your own sense of it based on how you
read it.

One time there was two main things left out as the main plot that needed me to
know a lot more.

First, I couldn't really get that the stories you saw in the first arcs were
actually the people that you could actually talk to.

This left me feeling more like I had lost some of my sense of immersion in a
story and just didn't really find it there. For example, I started to feel that
the main plot was very different from what you would see in the first arcs. The
two main themes we saw in the first arcs were how to live and how to do a life.

I found the story of how the life of a person is different from one that you
might see in the books.

The story of a person's living and living alone is also different from the
story of the world that you might see in a short play.

And to answer the question that many people have asked me over the last six
months, and these comments, but in order to

/media/gwern/Data/thiswaifudoesnotexist/snippet-71243.txt
_The King Of Debt_: Souta is a rich guy, who is unlucky in love, and punishes
by the rich son of a rich Chinese mafia as he is tossed about debt. But is he
really bad at such a guy? (from B-U) In the first episode of this anime
何月处, Souta is forced to marry a rich kid to buy him a piece of his ass. A
guy who doesn't know how to make friends with strangers, only has a friend for
the rich guy's sake. Souta does this by being the only person in the house that
doesn't have a job but a car, and even a friend of hers can't really call her
sister 'fae'. He also has an idol he can sing on stage, and he is forced to
fight for her (a guy named Katsu) against Katsu himself in the episode entitled
Souta Is Fae. In a final episode, he is forced to run the family business for
$100,000. What's the point in doing it? The kids only get to run the business,
but when they pay out the money they want in their inheritance, Souta starts to
run the shop as well. It's very simple for Souta and the guy he's running his
business for. After the episode has been rated H, the new episode has been
rated H...

favorite favorite favorite favorite ( 5 reviews )

Topics: Drama, TV, Romance, Romance


Community Audio 91 91 Seiken Hamamoto's Hacronyms 2 1 of 1 View 164 of 190

Topics: Drama, TV, Fantasy, Fantasy


Community Audio 88 88 The Man From The Outer Heaven 4 3 of 3 View 164 of 189

Topic: Drama, OVA


Community Audio 87 87 Seiken Hamamoto's Hacronyms 9 8 of 8 View 164 of 190

Topic: Drama, OVA


Community Audio 85 85 The Man From The Outer Heaven 3 2 of 2 View 164 of 185

Topic: Drama, OVA


Community Audio 84 84 Seiken Hamamoto's Hacronyms 2 2 of 2 View 164 of 189

Topic: Drama, OVA


Community Audio 83 83 Seiken Hamamoto's Hacronyms 3 3 of 3 View 164 of 190

Topic: OVA, DVD, Blu-ray, DVD-R

Topics: Drama, TV


Community Audio 82 82 Seiken Hamamoto's Hacronyms 3 3 of 3 View 164 of 190

Topic: Drama, OVA


Community Audio 81 81 Seiken Hamamoto's Hacronyms 2 2 of 2 View 164 of 188

Topic: OVA, DVD,

/media/gwern/Data/thiswaifudoesnotexist/snippet-71244.txt
_Yuuhi Zukan_: A story about a student council president and his student
council president, and how they are going to boot on the plan of how to change
the financial system. Unfortunately, this plan results in both failure and
budget failure. (from B-U) In the first episode of this anime 一日本の橙
and other characters form a conspiracy to gain access to his store, after being
cut in half, they make their way to the store to recruit them using the powers
of a demon. The demon has three characteristics: a strong, sharp eye, a strong
hand; a black eye, with white and black pupils with a big black mark on, and a
silver eye, with a black eye mark. The Demon's ability to create spells is
"demonic mana" that can be activated as if it were "guru aura". After a brief
delay, however, the Demon enters a black space that has a black face, and then
the Demon is attacked by a small black hole in his chest. The Demon attacks the
small black hole and when the black hole dies, the Demon's power to create
spells is restored. The demon returns to his house where is an old man called
Tsubayasu who says that he is going to create a dragon with great power. He has
been searching for a good magic and after his work with Tsubayasu and his
students for about half a decade now, he sees the dragon coming on a distant
night. Once this happens, his plans fall apart. When he discovers it was some
magic wizard he has been using, he leaves Tsubayasu thinking that he can not
use the dragon because of the power-up and his plans have come to an end. He
wakes up his parents and tells them that Tsubayasu had found money and a dragon
he created. (from B-U). 一日京初日 歋未夢の橙面者 (from B-U) A
young girl named Fushikata is assigned to work for the student council
President in the store. Fushikata is an ordinary girl who works as a maid, yet
she is also an extremely dangerous person. She lives with her mother and sister
as the main characters of the series. One day Fushikata's mother goes missing.
When they return to the store, a group of students, with a group of girls,
enter. They are given the key to the store, but after they get home Fushikata
is killed by the two of them. The group discovers that the woman they have lost
is Tsubayasu's old teacher, Hidetoshi. At this time Fushikata starts to think
about how she should treat him at a later date but that she is too busy

The corresponding 30k faces are generated & upscaled as before, index.html updated to randomized 0–100,000, and so on.

GPT-3

OpenAI released GPT-3 in June 2020 as a SaaS, with the model available only through a closed beta API. I was given access, and ran extensive experiments in generating poetry/nonfiction using the web interface. After satisfying myself with that, I thought to update TWDNE with GPT-3 anime plot summaries.

Because GPT-3 is so much more powerful than any of the GPT-2 models, the two-phase process and extensive keywords can be omitted entirely in favor of just a single short prompt—GPT-3 will get the idea immediately. After some experimentation (“prompt programming” remains a black art), I found that I could get a novel anime title & plot summary by framing it as a review of an anime from the future (eg. 2022). A simple prompt that worked nicely was

2022 Anime Fall Season Previews and Reviews

Previews of the latest and hottest upcoming Japanese anime this fall season!

Below, a review of the themes and plot of the first episode of the widely-anticipated 2022 fall original new 1-season anime

{
  "id": "cmpl-zFdIa6r5oO6AV4iogorDoAXh",
  "object": "text_completion",
  "created": 1593397747,
  "model": "davinci:2020-05-03",
  "choices": [
    {
      "text": "Yutori-chan which is produced by Sunrise:\nThe Kind-Hearted T-back Hurdler\nYutori-chan\nAt\n
      long last we welcome the challenging and heartwarming anime Yutori-chan produced by",
      "index": 0,
      "logprobs": null,
      "finish_reason": "length"
    }
  ]
}

for i in {0..100000};
do
    echo -n "Review of the themes and plot of the first episode of the new anime " > snippet-$i.txt
    curl --silent 'https://api.openai.com/v1/engines/davinci/completions'
        -H 'Content-Type: application/json' -H 'Authorization: XYZ' # NOTE: insert your own API token here
        -d '{"temperature": 0.95,"top_p": 0.98, # }
            "prompt": "2022 Anime Fall Season Previews and Reviews\nPreviews of the latest and hottest \
              upcoming Japanese anime this fall season!\nBelow, a review of the themes and plot of the \
              first episode of the widely-anticipated 2022 fall original new 1-season anime \" ",
            "max_tokens": 700 }' | \
  ## Select just the text completion:
  jq '.choices[0].text' | \
  ## unescape quotes:
  sed -e 's/\\\"/"/g' | \
  tee --append snippet-$i.txt
  echo -n "…" >> snippet-$i.txt
  sleep 3s
done