dojoe information 486 glöps
- demo Windows Shine n flow by Adapt [web]
- Extremely shiny and well made in the beginning, and the motion capture is a nice touch. Unfortunately once the fluid simulation comes into play it becomes really messy and "hey look we can do fluid simulation so here's some fullscreen bukkake in you face". That's too bad since otherwise the bling is right up there with the best of 'em!
Obviously still a thumb up, including for the music. - rulezadded on the 2023-02-01 23:10:33
- demo Windows JavaScript The Destroyer by mfx [web]
- heh :D
- rulezadded on the 2023-01-31 23:36:42
- demo Windows _ by Ivory Labs
- YES. I'm in the "a little long" camp but that doesn't make the prod any worse. The soundtrack is, as others already said, massive. Super tight and precise.
- rulezadded on the 2023-01-26 22:45:53
- demo JavaScript The Tale of the Bluebird & the Dragon by Ninjadev [web]
- Jesus H. Christ I'm in love with this demo <3
Many times a demo either has a fresh idea but lacks in execution, or it's polished to a mirror shine but is otherwise the well executed techno/dnb + pbr + post fest we've all seen before. This one combines a sufficiently unique idea with sufficiently great execution to make me fall in love, nits be damned. - rulezadded on the 2023-01-24 23:48:25
- wild Animation/Video Bongofärjan by Digi Natiivi Kissa Sekstetti
- ingenious _and_ lovely!
- rulezadded on the 2023-01-24 22:59:43
- musicdisk Linux Windows Marine Melodies by Resistance [web]
- I loved this at the party and I am enjoying it again on a lazy Saturday afternoon now <3
This goes way beyond just a bunch of tunes with a quick interface slapped on; the common tune and the wonderful interface blend everything together into a work of art. - rulezadded on the 2022-10-29 17:42:09
- demo Windows JavaScript Throwback Throwup by Unstable Confusion
- And here's the cables patch for you to peruse. We even added a few comments!
- isokadded on the 2022-10-26 22:11:23
- demo Windows JavaScript Throwback Throwup by Unstable Confusion
- Quote:
How many images did you need? (...)
It takes only 3-5 images of the object, and then the system is trained to "learn" the representation of the object in terms of its latent space, which as far as I understand is a long vector of abstract concepts and their contribution to the object in question.
So in a way the system learns that, say, D.Fox is 12.5% bear, 30% human and 10% cue ball.
This additional information is then merged into the representation of the prompt by the text encoder. None of the models making up SD itself are retrained or updated in the process.
The training process for Textual Inversion takes long because it needs to produce a sharp representation of the object with little extraneous noise. With too few training iterations we would get weird artifacts like every single image being set in a football stadium, I kid you not. - isokadded on the 2022-10-23 17:04:15
- demo Windows JavaScript Throwback Throwup by Unstable Confusion
- I should probably follow up my snarky response with a serious one :) Using AI art to make a demo was actually our main intent, but we wanted to take the opportunity to also make a statement along the lines of "it's not as turnkey as some would like to believe" and that's why we also put the text about the amount of work in there.
And it's also a throwback to times when every effect had a panel along with it boasting the technology title ("interlaced quaternion fractal glenz vector morph with extra cheese!") and of course the amount of polys. - isokadded on the 2022-10-23 16:46:37
- demo Windows JavaScript Throwback Throwup by Unstable Confusion
- Quote:
I've never before seen an effect with an overlay saying “wow, we spent so much time on this effect, it was really hard” :-)
You haven't watched a lot of 90s demos, have you? ;) - isokadded on the 2022-10-23 16:30:02
account created on the 2003-10-02 00:51:58