D U T I

MUSIC, VIDEO, FASHION, ART.

[resurrectinghiphop]

[sportsbysergio]

[julesofnature]

“Christopher Columbus, as everyone knows, is honored by posterity because he was the last to discover America.”   James Joyce

photo taken of poster on the island of Bequia, Saint Vincent and the Grenadines

[dogembassy]

Laurel Halo in The Wire #357 (November 2013)

[dancingundertheinfluence]

http://www.inhouseradiolive.com/home/4591434185

[frazamatic-deactivated20190521]

Decent buildup of kief from the BC Big Bud I’ve been getting

[norepetitivebeats]

Richie Hawtin’s original studio, circa early 90s

[dancingundertheinfluence]

(DUTI) New mix on the rise..

[dancingundertheinfluence]

📸: @_almaveronica . . . . . #chicago #vsco #vscocam #housemusic #vibes #chingon#2017 #newyearnewmebullshit #fuckitall #jonekk #duti #dancingundertheinfluence (at Chicago, Illinois)

[dancingundertheinfluence]

#Juanga #juangabriel #chicago #vsco #vscocam #canon #markiii #adidas #weather (at Chicago, Illinois)

[supersonicart]

#PRINTMAS at INPRNT.

For the first 25 days of December on Supersonic Art I’m selecting artists for INPRNT’s #Printmas celebration.  The 18th selection is the magical work of artist Aldous Massie who has all of the work above and more available as prints in his INPRNT Store.

This is a sponsored post, but I’m choosing all the artists.  Check out INPRNT on Tumblr!

See all the prior artists below!

Keep reading

[surrealism]

Brain Chain by Willem Den Broeder, 2001. Acrylic on canvas, 120 x 80 cm.

[prostheticknowledge]

Imaginary landscapes using pix2pix

Creative experiment from Hannu Töyrylä uses new neural network method with his own collection of photographs to generate new artistic images:

Pix2pix is a brand-new tool which is intended to allow application-independent training of any kind of image transform. All that is needed is a dataset containing image pairs, A and B, and one can train a network to transform to either direction. Possible applications include colorization, segmentation, line drawing to image, map to satellite view, stylization and so on. The operations work in both directions, so with a properly trained network one can generate a plausible satellite view from a map, or a building facade from a colored segmentation. 

… My next test was made using my own dataset of 2500+ photos, mainly landscapes. I produced image pairs in which the input image was a center crop of the target image, and tried to train the model to guess what should be outside of what it sees. Again, a very hard task for a model, given a small dataset with quite varying views. But I was looking something interesting, not magic. 

It turned out quite interesting. I have earlier experimented with GANs trying to create imaginary landscapes based on the same set of photos, but never could get the model trained to produce higher than 128px images. Now I got amazing imaginary landscapes in 512×512 px without any problems. 

More Here

[mexicanacabrona-deactivated2024]

✨Get them while the last IG: @hilos.shop ✨

[mexicanacabrona-deactivated2024]

HIL'OS COLLECTION ✨ IG: @hilos.shop

[kamonra]

This is the money pentacle. Reblog and unexpected money will come to you!

[darkcocosb-blog]

Shiiiiit. I reblogged, and I got $750 in two days for basically nothing! The first day this client/POT asked my agent to invite some girls and I to his end. We basically sipped wine and left with $500 each. He called me yesterday and we took a ride on my highway and gave me $250😂😂😂. Money blogs everyday any day!

[soflobrat]

Won’t chance it.

[br0wnsugarandspice]

Yo this shit works not even gonna front like I didn’t just get money

[tastelikehoney-sb-deactivated20]

Let me reblog this 2x then 😂

[nudiemuse]

Do the thing pls

[quickweaves]

im screaming it worked lmfao

[psilocybinladen]

I always put my trust in witches

[futurewitchdoctor]

where im at lately

[ysociety]