//=time() ?>
alright let's do some AI beksinskis in this thread. top left is "ground truth" (i.e, one of the actual images from the dataset), everything else is generated.
New postdoc call to start during 2022. A fully funded postdoc position to study population genomics in a big dataset of primate WGS. Previous experience with theory and popgen required. Funded by
@ERC_Research
Please RT. Thanks! Contact me by email if interested.
Theres so much furry fan characters in the dataset that you can get Toriel, Renamon, and Judy
Discriminator Dreaming with layers D.b8.conv0, D.b8.conv1, D.b4.conv and D.b4.fc, respectively. Were the spirals curly hair all along, overrepresented in the MetFaces dataset? https://t.co/YQuYOaM4Pb
Dataset is nearly ready... but meet some of the rejects :) #ruDalle
AnimeCeleb: Large-Scale Animation CelebFaces Dataset via Controllable 3D Synthetic Models
abs: https://t.co/5MuocaLtPF
present a large-scale animation celebfaces dataset (AnimeCeleb) via controllable synthetic animation models to boost research on the animation face domain
Day five in void studies. neural network traind on a dataset flowers as the input. three times through the void feedback loop algorithm
#inAvoid #studyTheVoid #generativeart #art #nftart #generativeart #NFT #NFTS #NFTCommunity #NFTartist #cryptoart #art #artist #NeuralNetworks
I started with a dataset of over 800 genes to sift through, and after over a month of work I’ve distilled it down to a few dozen that are of interest to our research! Can’t wait to present this data to my lab mates this week! 😤🦈
Some images from a dataset I'm currently making, which will then be trained into a GAN for animation. The animations will go on Foundation, and the dataset stills will go on Hic et Nunc. My goal is to create the ultimate in digital art combining the ultimate in AI methods :)
Dive in to @elluba's beautiful Curator's Note, "Through the lens of AI into the hidden depths of datasets" https://t.co/pedH3ubamz
"Surreal Visions" - currently training my own dataset of my own generative art for the successor to the "Ether Visions" series. About 2000 of these will form the model - from which infinite further original artworks and animation can be made.
I wrote this random character generator that generates LOADS of things for a character profile from datasets I've found online, and then it grabs images online for outfit and hair ideas, decided to doodle one of the random generations I got!
This is so much fun to do 😁
With science comes progress, as @LydiaCorell has managed to refine their control of gravity even further to create "smaller" portals to alternate realities! With the added fine-tuning, she can procure more localized datasets with her instruments!
"Elemental Flows"
A new #NFT collection of 4 + 1 works in generative art & data that I'm _really_ excited about! ✨
Using the same algorithm & different datasets I've created 5 pieces: Earth, Water, Sun, Air & Digital
Check them out here: https://t.co/z5oFgpghdO
#NFTart
An open MRI dataset for multiscale neuroscience | #biorxiv_neursci https://t.co/Ruc66Hm10G
@images_ai @dribnet Vincent D'Onofrio, Samuel L Jackson, Will Smith, and Keanu Reeves
in the style of Chuck Close
ml decided the world needed 6.5 keanus – no idea why his is the only complete face... more of him in the dataset?
I liked the picture and so I thought that I'd try it at more iterations (that was at 250/300) to see if there was any significant difference. This is at 600 iterations (same dataset, same seed). Not too much difference.
☾ *✧. . sound on, please . . ✧* ☽
-
Look! Now these generated eyes can blink because I added closed eyes to my dataset.
💻Interested in the overall balance between incoming and outgoing radiant energy at the top of Earth’s atmosphere? Today we released a new dataset that offers data on Earth's radiation budget from 1979 to present.
Access it in the #ClimateDataStore➡️https://t.co/hs074iT4CR