I have never seen more cursed cats in my life than this and I love it. I wonder if it’s possible to create a normal looking cat if the drawing is good enough.
Student Area
duq-LookingOutwards03
https://mlart.co/item/generate-a-logo-from-a-drawing-using-pix2pix-hd
This piece really caught my attention because I took a class in high school on how to create logos and the amount of iterations that go into creating such simple shapes and typography. I feel like a future version of this technology could be used by graphic designers to more rapidly prototype logos. This piece takes in a hand-drawn image and using p2p smooths and subtly changes the picture to make it into a logo.
Dr. Mario-WQGAN+CLIP
It was very confusing at first as the link on the website gave a different version to the one in the video tutorial, and the one on the website didn’t work. Once I got it working though it was pretty interesting, very similar to the app WOMBO Dream. It was a little slow but the outcomes were pretty interesting.
The prompt is “Magic Tower”
Dr. Mario – TextSynthesis
“We’re trying to get all the central parties to agree on the relative rankings, then the ratings will be assessed by the independent people,” Botolo said, referring to an expert commission.
Botolo said at least three other contenders will also vie for the top job.
Ethiopia has won global praise for its democratic credentials in recent years, but the ruling coalition has faced mounting dissent in the countryside, as many young people complain of political and economic marginalization.
Prime Minister Hailemariam Desalegn has been in power since 2012, but appears to be close to resignation after the Tigrayan People’s Liberation Front (TPLF) party, his longtime ally, split over the summer.
TPLF is the largest of the coalition parties. Hailemariam resigned in February citing what he called threats to his life and a struggle to keep the ruling coalition united.
– Growing ethnic violence –
The mass protests that initially erupted over land rights and politics are now focused on wider grievances.
Ethiopia has nearly 100 ethnic groups, and recent ethnic violence in
various parts of
– this was from InferKit
That was kinda scuffed, “-Growing ethnic violence-“. I was expecting something much more light hearted.
Big Chungus was a huge, green, sausage-like creature that lived in the swamp. He loved to suck the toes of small animals, and he would often kidnap them and bring them back to his house to eat.
– this was from Narrative Device
Now this is what I was expecting! If you couldn’t guess my themes were Big Chungus and sucking toes, I think the tool did a wonderful job
Dr. Mario – ArtBreeder
That was fun, made some cool landscapes and buildings. I also had 100% crayfish in my settings but I don’t know where that went.
Dr. Mario – Pix2Pix
Here are the monstrosities that I brought to this world
This was pretty fun, I just wish I had something other than my trackpad to draw more advanced stuff.
Dr. Mario – LookingOutwards03
I chose Metamers (2018) by Dani Joy
http://www.aiartonline.com/community/215/
They call this style “Augmented Hand” which I thought was a very interesting perspective on AI drawing. This was a two year project that attempted to enhance their own traditional art skills and tools for large scale gallery paintings. They used tools like pix2pix, photoshop and python to bring these creations to life. I really like the lively colours and shapes, they all seem to have this geometric aspect to them that I find very pleasing.
Sneeze—VQGAN+CLIP
Prompts
“magical giant village in tree tops” and “medieval cats fighting”
Using the Google Colab notebook was interesting. I have used Google Colab notebook before but only briefly and unsuccessfully for another project. I just remember being very confused about the concept of running pre-made code from others and not understanding that all you had to do was press the play button on the code snippets. It was very easy to complete and the most difficult part was waiting for the images to render. I thought it was cool that you could either give it a base image to work off of or just have it generate everything from scratch. Both of my prompts were generated from scratch by the colab notebook.
Sneeze—TextSynthesis
“The old woman in the store was giving out fortunes when she caught sight of me. “You’re going to be rich,” she said. “You’ll find a lot of money.” But I didn’t believe her. I only had a few dollars. “You’ll get a headache,” she said again. I was too tired to argue. So I bought a fortune cookie and went to bed.”
Narrative Device takes in two themes and generates a whole paragraph out of them. I thought that this was really easy to use since it only needed the user to come up with two subjects, but sometimes the outcome would exclude one of them. When I used headache and fortune cookie, the device would only sometimes give me a paragraph that was related to headaches. Besides that, generating text on the same themes creates remarkably different storylines, which is impressive. I think that this device creates a semi-logical plot with a much more cohesive story compared to InferKit.
“Upon opening the door, Dorthy found that she was not in her room. She had transported to the land of ice and was about to slip and fall.
Determined to walk on, she insisted that she could handle it. The Mice that were near her allowed her to use their icy paths to reach her destination. They were also helpful in avoiding new dangers of their own.”
The InferKit Tool has a different dynamic from the Narrative Device. It requires the user to give it a starting phrase or sentence or sentences to build the story. I think that this gives the user more control, which can be nice, but providing fewer words results in a random story. When I experimented with giving it a phrase, the story went to a different subject all together. Providing more words makes the story a lot more cohesive, but then that requires the user to work more.
Sneeze—LookingOutwards03
More information about the project
The project that caught my attention was Font Map by Kevin Ho. The project uses machine learning to find similarities between fonts and maps in relation to each other on a plain. This interested me because I spend a lot of time with typefaces and being able to visually see fonts that are similar would honestly be a very useful tool for designing things. This tool not only allows for you to be aware of fonts that are similar to a typeface you like but it also brings in an aspect of exploration.