Live data from Hacker News

Google Imagen 2

cloud.google.com

191–194 of 194 posts

Re: Google Imagen 2

#191

Earlier quoted context omitted.

Sure, here's sample query https://imgur.com/a/8UDDac9 These are DALL-E 3, Imagen, and Imagen 2, in this order. I've used the code based on similar examples from GitHub [1]. According to docs [2], imagegeneration@005 was released on the 11th, so I guessed it's Imagen 2, though there are no confirmations. [1] https://github.com/GoogleCloudPlatform/generative-ai/blob/ma... [2] https://console.cloud.google.com/vertex-ai/…

You've got to be kidding me. This almost deserves its own post. That last picture is still so horribly bad it's no wonder Google made it almost impossible to access this tech. How did Google drop the ball on AI like this when they pioneered the entire field?

To be fair, it is not always that awful. Here is a sample of the results of simpler subset prompts I like to run on image generation: https://imgur.com/a/aO5S7yM Some are bad (first two), but others are okay; it understands text pretty well, but the artifacts just feel like years ago.

I still can't understand how it got released and advertized.

Re: Google Imagen 2

#192

Earlier quoted context omitted.

You've got to be kidding me. This almost deserves its own post. That last picture is still so horribly bad it's no wonder Google made it almost impossible to access this tech. How did Google drop the ball on AI like this when they pioneered the entire field?

To be fair, it is not always that awful. Here is a sample of the results of simpler subset prompts I like to run on image generation: https://imgur.com/a/aO5S7yM Some are bad (first two), but others are okay; it understands text pretty well, but the artifacts just feel like years ago. I still can't understand how it got released and advertized.

Thanks for the examples.

I've used SD / Midjourney / Dalle extensively and would say this is honestly shockingly bad besides the two last ones.

Comparable to the first versions of the other services, but with better contextual understanding but still with lots of gnarly artifacts and weirdness going on.

Re: Google Imagen 2

#193

Earlier quoted context omitted.

It's true, was there through 2016-2023. People just have different definitions of what coasting means. In general don't think "doing nothing" or "avoiding work" think "add certainty to process + decision making like everyone else does", and much more importantly "avoiding friction because as soon as there's even a little bit, people leverage it" More detail on what causes this: - processes become elongated through wh…

I work at a big corp and my experience is swaths of the year (I'm talking weeks at a time) when upper management is engaging in faction warfare many levels above me, and my own manager doesn't know what the team should be working on until upper management can set priorities. So I have nothing to work on. I guess this is 'coasting'.

That's an excellent example. TL;DR: Working through why people did that ultimately lead to my epiphany that no, it wasn't that everyone else was lazy, they were just better-adjusted via understanding tradeoffs.

Longer version. Sorry to torture the threads with these, but I've noticed people don't take 'BigCo is a weird, strange, place' stories seriously unless there's a full anecdote coupled to it:

Google was my first real job, got very very lucky with a transition from dropout waiter => startup founder => sold => 9 months later, did interviews as a joke and...passed?

My first few years, I didn't understand this was happening, and eventually we got transferred to Android, and it was just an absolute directionless wasteland for at least 4 months. I couldn't even begin to understand why my peers A) had no work B) were fine with it C) when we tried talking about this, it was like we were speaking different languages.

I saw it as a 'leadership opportunity' and butted my/our way in to a big project and picked up another. Huge stuff. Visual redo of key property, and on the side, got a fundamental change to the input method for the same property, delivered by me client side and server side, then wheeled and dealed to get it deployed cross-platform.

That whole year peers didn't invest in the visual redo, even though it was ostensibly our teams work. Our newly promoted manager never planned / assigned work to people, and was out for about 50% of that first year.

It turned into Lord of the Flies while they were out. Only 2 peers worked on it out of 4. #3 helped out on a lower-key project. #4 focused on advocating for a feature that'd watch your screen and ex. tell you Infowars was Very Bad if you visited Infowars. At Old Google you could work on obviously bad ideas like this and you just wouldn't advance. It's a good thing that this would only last a month or two these days, if it happened at all.

Peer A was extremely confident but also extremely out of touch, for example, 2 weeks before launch they spent 5 minutes arguing with the partner team, telling the it was impossible that we had written all our code in $BINARY_A instead of $BINARY_B...which we had. When faced with the bare fact, they then went with "oh no wonder why nothing works" (???)

Peer B was relatively new to tech, so the histrionics the other would leap to had a massive influence on them. Always horrified we were doing anything at all without getting 3 separate approvals first, stapled to a direct request laying out exactly what was required, instead of just a Figma / GIF.

Peer B also got _insanely_ over-the-top mean to me after the project. Yet, they were nice and extremely intelligent generally.

That's when it finally clicked for me that something was off and I needed to approach the coasting question more inquisitively:

_what_ were they seeing differently?

They understood they were avoiding pain that they'd get ~0 credit for working through.

They were right.

I got excellent reviews from the partner team and product manager, I got awful reviews from Peer A and a meh one from peer B, and got a middling performance review after moving 2 mountains essentially solo.

Though, a $10K bonus, this was standard payout for staying silent / not complaining after dealing with an obviously toxic situation.

I had to appeal to VPs for recommendations the next year to break through the "gee you moved two mountains and had great feedback from everyone _not_ on the team, but peer A and peer B didn't like you much"

Re: Google Imagen 2

#194
post #77

I think the competition for text to image services is over and open source, stable diffusion won. It doesn't matter how detailed (or whatever counts as "better") corporate text-to-image products get, stable diffusion is good enough which really is good enough. Unlike the corporate offerings, open source txt2img doesn't have random restrictions (no its not just porn at this point) and actually allows for additional sc…

> Why bother using a product from a company that is notorious for failing to commit to most of their services, when you can run something which produces output that is pretty close (and maybe better) and is free to run and change and train? Because it costs $0.02 per image instead of $1000 on a graphics card and endless buggering around to set up.

if you're interested in exploring providers shadeform will let you compare prices for the same cards across providers*

i'm one of the founders

Post reply on HN