Evan Banyash (@FrobtheBuilder) header
Evan Banyash (@FrobtheBuilder) profile picture

Forbes 30 under 30 2018 (the only time I've ever been important). Stable Diffusion enthusiast. "It's over." https://teapaw.org/t.co/wKOwvewdyk

Joined January 2016
Hello twitter. Important survey attached; please complete:
53%yes
47%no
36 votes • Final results
1
2
Imagine being a random tech support scammer and getting an angry call from Greg Egan
Part of the full-screen web page masquerading as messages from Windows that came up when my mother clicked a link on the Octordle page this morning. Luckily she smelled a rat and didn’t fall for it. I called the number here and gave the gentleman who answered a piece of my mind.
1
Replying to @_sambk @images_ai
Taking my epic beautiful fashionable tattoed girl portrait professional photography trending on artstation octane render by wlop and running it through a wombo tier motion model to give it worse lip syncing than Vampire: The Masquerade Bloodlines
1
1
5
There we go, fixed!
Part four of catching up with the #septembAIr2022 challenge - prompt No. 4 was "Echo" This piece is called "Echoes" #septembAIr
5
2
1
11
I wish the artists would just say it: "I spent my life grinding to eke out a meager living in the most difficult industry and now machine learning will make it all for naught. Socialism/UBI isn't happening so that's not going to help me. It's over."
4
4
3
32
My field is literally next, programmers are going to be obliterated within the next couple of years. We can't face the problem if we won't admit it. Enough with this vague nonsense about "not real art" and "plagiarism". That's not what you're really talking about!
1
16
All knowledge work is going away, the only two jobs of the future are capital hoarder and Amazon fulfillment center since robotics is still so far behind. Your only valuable skill is reduced to picking up objects of arbitrary dimensions. Our future.
1
1
12
These text to image models are great but I'm getting really tired of the square pictures. You can go wider with Stable but you lose coherency since it was trained on squares. Best pictures in the dataset are undoubtedly wider, I'd like a model trained on 16:9 crops instead.
1
2
Outputs often look "cut off" on the sides or like they were taken with a very low field of view because well, the training set WAS cut off in exactly that same way!
Got init images working with #StableDiffusion and had it paint me as "A portrait by Dean Cornwell" and boy do I wish I looked like any of these, this is gonna be uuuuuuhhhh difficult for a lot of people once it inevitably hits faceapp and all the others.
1
4
You can generate infinite variations of "yourself but more attractive" in the style of any artist, I assume because usually their work is biased toward attractive subjects by choice. I mean, it makes sense. What a time to be alive...
1
1
Except for Beksiński of course.
You literally "enslaved" an AI for the pictures on your website, and you didn't even so much as credit them either! This is a horrific abuse of machine learning model rights.
Finally got into DALL-E 2 can of beans for pro gamers, RGB LEDs, by razer
1
2
mario sonic harry potter darth vader raccoon astronaut riding a horse trending on artstation 4k this is what it's designed for right?
1