05 – Interactivity and Computation • 60-212

bumble_b-VQGAN+CLIP

I feel really stupid for how long I spent trying to get Colab to work. If I wasn’t making this assignment up a few weeks later, I would’ve just headed over to office hours, but since I’m so late already, I just used Pixray instead.

My prompt was: “friendly elves frolicking in a meadow, strawberry picking with baskets, with a giant rainbow in the sky”

It was fun seeing the photo slowly develop through iterations. Here are some of the first ones:

Compared to the end product, it’s so much different! Anyway, I really love the picture, especially how cute the elves are! I just kind of wish the rainbow was there!

bumble_b-TextSynthesis

Narrative Device seemed to be down, so these are both from InferKit:

“I really want to get my nails done tomorrow. I wonder what color and design I’ll get… I’m thinking pink, of course. Now, to sleep so I can get up early for work tomorrow.

I’ve had a headache all day. I went to work, ate my lunch, and went back to my desk.

It has just kept on hurting. I am tired and I’m hungry. But mostly, I’m in pain. I took Tylenol and my left arm has a numb feeling. I’m just hoping it goes away soon… Otherwise I’m going to call in sick.

The worst part is, I’d rather get my nails done and feel pretty than lay on my bed and cry. (And be bored.) (I have work to do, too.)

Today, I got up at 5: 30, had breakfast, and left at 6: 30.

I was out of there by 7: 45.

I got to work at 8: 15.

I don’t usually get to work that early.

I had to leave at 4, but I got a lot done today.”

I gotta say, I was really disappointed that the nails weren’t talked about again after the first generated sentence, so I was thrilled when they made a reappearance!

“I just turned 21, and I’m going to a trivia night at a bar for Friends (the TV show). I LOVE the TV show Friends!

I know most people who love the show don’t do that whole nostalgia thing.

But I do.

I think it’s hilarious how much they’re all still together.

They’re practically cousins.

On the show, every episode begins with them thinking they’re the last people on Earth.

And they find out the opposite is true.

They can’t believe they’re still friends after so many years.”

I tried giving it something very specific, like a TV show that already exists, to see if it knew anything about it. Clearly it did not! Lol

bumble_b-ArtBreeder

Since I’ve already used ArtBreeder, I tried out ProsePainter. I actually really hated ArtBreeder last year, so I’m excited that I really enjoyed this one!

Here was the starting image I used (one of their defaults):

And here is the final image:

These are the prompts I used and where I used them to make it look like this:

“radiant fireworks of diamonds” on the background

“red demon eyes” on her eyes

“long black hair” on her headscarf

“blue lips” on her lips

“dark brown unibrow” on the gap between her eyebrows

“gross green boogers” under her nostrils

“big flowers” on her forehead

Again, I am absolutely too tame when it comes to these projects and only ever find myself interested in altering the features that are already there with things that could be there, like “red eyes” on eyes and “blue lips” on lips. I tried branching out a little with the flowers on her forehead and really enjoyed that result.

bumble_b-Pix2Pix

I’m very much a rule follower, so it honestly didn’t occur to me until just now to do funny stuff and see what it generates. I really focused on trying to make them as realistic as possible, and I’m honestly really happy with how they turned out, especially the shoes.

hunan-VQGAN+CLIP

Since I don’t have Colab Pro, I spent a lot of time trying to get the notebook working on a local runtime so I can get the bigger models working. But many library issues and differences between Windows and Linux made it very annoying. So I resorted to using a smaller model on Colab.

Lemongrass under the pink sky rendered in blender

hunan-TextSynthesis

This is the first time I’ve used GTP-3 and was honestly a little disappointed. Don’t get me wrong — it’s an amazing model, I just didn’t see the improvements over GPT-2 that I was looking forward to (given the massive increase in parameter size over the already massive GPT-2.) Maybe the improvements in text generation are already marginal and it would take something like DALL-E to tell the difference.

I tried putting in the first sentence of a news article generated by GPT-2 for one of my previous projects into GPT-3 as a prompt. The following is what I got.

The family of a Maryland woman who was killed by a stray bullet last year has settled a wrongful death lawsuit brought by the family of Kimberly Ballinger, a 19-year-old who was struck by a stray bullet in March 2018.

News outlets report attorneys for Ballinger’s family confirmed in a news release that the lawsuit against Baltimore County was settled on Aug. 17 for an undisclosed amount.

Sarah Gelsomino was struck in the neck by the bullet that struck Ballinger as the two were in a car. The lawsuit alleged that Ballinger was inadvertently killed by Gelsomino’s boyfriend, Charles Lee Thornton Jr.

Gelsomino survived and filed a lawsuit in June against Thornton. The lawsuit alleged the shooting was “reckless and unreasonable,” and that Thornton acted recklessly, setting into motion Ballinger’s death.

Advertisement

Thornton was charged in Ballinger’s death. It’s unclear if he has a lawyer.

Copyright © 2018 The Associated Press. All rights reserved. This material may not be published, broadcast, written or redistributed.

This is the original article generated by GPT-2:

The family of a Maryland woman who was killed by a stray bullet last year has settled a wrongful death lawsuit brought by the family of Kimberly Ballinger, a 19-year-old who was struck by a stray bullet in March 2018. Ballinger’s family said they were given about four weeks to file their claims, and on Monday the family settled the case. “The family is relieved that this case is closed,” Ballinger’s family attorney, Stephen R. Kaufman, said in a statement. “They have been unable to pursue their claims against the gun manufacturer that manufactured the bullet and that illegally sold it to the gun shop owner.” The Maryland shooting happened at a gun shop in Fayetteville, Maryland, when Ballinger was shopping with her father and a friend. The store owner, Lorne Ahrens, fatally shot Ballinger, who was a student at Towson University, according to the complaint. The gun shop owner’s wife, Tammy Ahrens, was also shot. “The bullet struck Ms. Ballinger squarely in the back of the head,” the complaint said. “Although Ms. Ballinger did not have a bullet wound, the bullet went through her inner right arm and into her right shoulder, severing a major part of her arm and causing her to lose her life.” Ballinger was struck on the left side of her body and her right arm, the complaint said. Ballinger was in critical condition at a hospital for about 24 hours before being transferred to a hospital for treatment of an arm injury, according to the complaint. The bullet was recovered from her body, and the gun shop owner was arrested and charged with first-degree murder, the complaint said. He had been held on $500,000 bond. Ballinger’s family asked that the $1 million awarded to Ahrens be increased to compensate for Ballinger’s loss of life and a $100,000 reward for information leading to his arrest. The gun shop owner and his wife pleaded not guilty to murder charges. The family is asking for unspecified monetary awards, restitution and attorney’s fees. The family is also asking for the gun shop owner to be held accountable for his actions. CNN’s Artemis Moshtaghian contributed to this report.

hunan-Pix2Pix

Cats are always fun. Not many surprises here as it’s just a classic Pix2Pix model. But I was surprised to find that many art projects, including this one (edges to cats) and the “Learning to see: Gloomy Sunday” we saw in class were actually included in the original Pix2Pix paper, which I thought was kinda cool. This site seems to run inference on the frontend and is quite unstable (I would get “page unresponsive” multiple times for each generation.)

hunan-ArtBreeder

It’s alright. There are still some deconvolution artifacts that give it away immediately (at least with the more photorealistic genres I’ve played with.) I love the freedom and flexibility it provides with various keywords and parameters, but the actual effect of these parameters in the images is rather disappointing. Resolution is not bad for generative models.

duq-VQGAN+CLIP

I spent quite a while trying to get the VQGAN+CLIP site to work, but I was completely unsuccessful. I instead used the Pixray readymade. I was surprised by how unrelated to the prompt the first couple of images were and then I found it to be a window into the way in which ML works to see how it takes that image and slowly makes it fit closer and closer to the prompt.

Koke_Cacao-VQGAN+CLIP

(05-VQGAN+CLIP)

Using: wikiart_16384 + ViT-B/32 + default paremeter
Prompt: A student suffering from his coding homework

The image quality is not very good as other synthesizers based on image inputs (compared to models related to style
transfer) since the natural language processing pipeline restricted the latent space or because they are not trained
end-to-end. The style of the images generated can get very cliche very soon and the tool doesn’t give the artists
very much control over the generated image.