Live data from Hacker News

Google Imagen 2

cloud.google.com

171–180 of 194 posts

Re: Google Imagen 2

#171

Earlier quoted context omitted.

How has Android been a dumpster fire? I don't even think it's arguable.

They may have had the occasional advantage over iOS for a brief period 5-6 years ago. Nowadays they clearly lag behind Apple on everything and even their Pixel line does a half-assed copy/paste of the latest iPhone features (or introduces features which are shiny but have some sort of downside or require cloud processing to work). Android's advantage has always been that everyone else gets to play. And it's good that…

This is your opinion with nothing from a technical standpoint.

Re: Google Imagen 2

#172
post #131

Earlier quoted context omitted.

Shipped stuff? Like what? Threads? Its usage is down 90% since its launch six months ago, presumably because they kept the people who could launch stuff and got rid of the people who had some idea of what should be launched. The "Blue Checkmark" system? Released with no thought at all, absolute disaster. Steven King had to publicly announce that, despite indications to the contrary, he was not a paid user, and he fel…

The issues with Twitter are currently about Musk buying it at ridiculous price and his personal antics. Other than that, it works fine as always. They shipped quite a bit of stuff, like the blue tick or revenue sharing. Other than Musk courting fascist and other kind of undesirables, twitter as a product is doing fine. It might go under though, but if that happens isn't going to happen because lack of employees.

It's absolutely full of spam, and the only ads left are crypto airdrops coming from what look like hacked accounts.

Re: Google Imagen 2

#173

Earlier quoted context omitted.

Why stable diffusion won? Dalle3 and this is miles ahead in understanding scene and put correct text at the right place. This makes the image much more usable without editing.

> Dalle3 and this is miles ahead in understanding scene and put correct text at the right place. I guess that turns out to be not as important for end users as you'd think. Anyway, DeepFloyd/IF has great comprehension. It is straightforward to improve that for Stable Diffusion, I cannot tell you exactly why they haven't tried this.

Deepfloyd is slower and needs a lot more memory since it's pixel diffusion.

Also not sure if it can be extended with LORAs or by turning it into a video/3D model the same way an LDM can.

Re: Google Imagen 2

#174
post #158
post #107

Earlier quoted context omitted.

AFAIK it worked out well. Works more-less the same as before, shipped quite a bit of stuff and drastically reduced costs.

> more-less the same as before Not if you have no account and are not in US. Before, when I clicked on twitter link it worked 99.9% of the time. Now it is lottery. Sometimes it loads without comments, most of the time it does not load at all.

Even with an account (though I'm also not in the US, but in the UK) I've recently (many months) found the Twitter site to be about as unreliable as the old, early fail whale days (except instead of a cute whale, I just get the page refreshing back to the top of my timeline, or a tweet loading then replies failing to load).

I used to hardly ever see spam, except when looking at replies to famous huge accounts, now I get 2-5 follows/likes/mentions a day from fake accounts mostly of semi-naked girls with a link to a website.

And any reasonably active thread of replies to a tweet now surfaces the idiotic nonsense of blue tick subscribers to the top, rather than ranking by tweet quality/relevance.

Re: Google Imagen 2

#175
post #131

Earlier quoted context omitted.

The issues with Twitter are currently about Musk buying it at ridiculous price and his personal antics. Other than that, it works fine as always. They shipped quite a bit of stuff, like the blue tick or revenue sharing. Other than Musk courting fascist and other kind of undesirables, twitter as a product is doing fine. It might go under though, but if that happens isn't going to happen because lack of employees.

It's absolutely full of spam, and the only ads left are crypto airdrops coming from what look like hacked accounts.

Have you used twitter before the musk takeover? That's exactly what you are describing. At worst, nothing changed. At best, in my experience, the spam problem has somehow gotten better. Much less spam accounts below every single post like how it used to be.

I still think layoffs are bad because I don't care about corporate profit or efficiency to be honest, but in this case it's a bit surprising how nothing concrete has actually changed even with 80% reduction in staffing. 80% sounds apocalyptical to me but again, twitter just works like it did before. With the same annoying, never fixed bugs (occasional "something went wrong" on clicking tweets, etc) . But again, nothing close to the (technical) train wreck I would expect.

Re: Google Imagen 2

#176

Kinda scratching my head at the purpose of the prompt understanding examples they show off. From previous papers I've seen in the space, shouldn't they be trying various compositional things like "A blue cube next to a red sphere" and variations thereof? Instead they use >The robin flew from his swinging spray of ivy on to the top of the wall and he opened his beak and sang a loud, lovely trill, merely to show off. N…

The prompt is a quote from a book, and it mentions "opened his beak and sang a loud, lovely trill", and the Imagen 2 robin does exactly that, but both SD ignored it completely, and SD1.5 isn't even on top of the wall.

Re: Google Imagen 2

#177
post #128

Earlier quoted context omitted.

How are two completely different models from different groups, converging on what looks like the exact same person? Number 1 and 3 are eerily similar. I don't understand.

I think you might be misunderstanding. The GP did three runs using one model, each with the same prompt that was used for the Imagen demo image. The outputs are images 1, 3 and 4. Hence the similarity.

Because imgur scrambled the order during upload. /facepalm

Re: Google Imagen 2

#178

Earlier quoted context omitted.

I've developed two tests for AI image generators to see if they've actually advanced to "the next level". Take literally any AI image generator and give it one of these prompts: "A flying squirrel gliding between trees": It won't be able to do it. Just telling it "flying squirrel" will often generate squirrels with bat wings coming off their backs. Ahh, but that's just a tiny, specific thing missing from the data set…

I tested the prompts with dalle-3 (through the API) The flying squirrel one, was spot on, it showed an image of the trees, and a squirrel with wings, which kind of looned like bat wings. The 3 girls hugging each other however worked fairly well, it always created 3 different types of persons, but they never hugged each other. Either two of these 3 hugged each other, or no one hugged someone.

(Deleted)

Re: Google Imagen 2

#179
post #129

I've tried and it's genuinely bad, with obvious artifacts. I'm surprised it got released

Can you throw some examples up on Imgur or something?

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/publishers/google...

Re: Google Imagen 2

#180
Google needs to update their playbook. A publicly available demo goes a long way. Google of all companies shouldn't be coming off as the dinosaur when it comes to generative AI.
Post reply on HN