Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Imagen: An AI system that creates photorealistic images from input text

imagen.research.google

Post reply on HN
Print view View original

111–120 of 233 posts

Re: Imagen: An AI system that creates photorealistic images from input text

#111

Post by ShamelessC »

astrange wrote: post #102
ShamelessC wrote: post #95

Earlier quoted context omitted.

Neither DALLE version 1 or 2 was completely released. Further, DALLE2 definitely still has issues with generation of text, although latent diffusion can do an okay job of it.

It’s Imagen that can competently generate text, and their ablation studies show it gains the ability at a size somewhat above DALLE2’s, IIRC.

Apologies I was referencing personal experience w.r.t. latent diffusion.

https://replicate.com/laion-ai/erlich

It still has issues of course, but a lot better at spelling than DALLE2.

Re: Imagen: An AI system that creates photorealistic images from input text

#112

Post by lm28469 »

sheilaalien wrote: post #97

I'm surprised how very little this forum and the public in general knows or understands about the current capabilities and availability to these ai art generators. You have midjourney.com beta.dreamstudio.ai craiyon.com (real quick version no fuss, low quality) creator.nightcafe.studio and those are just some of the entry-level ones. I make ai art all day long! Check out my media feed on twitter @Sheilaaliens

> I make ai art all day long!

I feel like this is the epitome of modern "content creation"

Typing a few sentences into a software you barely understand, said software shits 15 jpegs out, 2 are good, "hey I make art". What a sad state of affair, tech is consuming everything and people are cheering, one more step on the path to being complete useless key pressers.

Re: Imagen: An AI system that creates photorealistic images from input text

#113

Post by ShamelessC »

lm28469 wrote: post #112
sheilaalien wrote: post #97

I'm surprised how very little this forum and the public in general knows or understands about the current capabilities and availability to these ai art generators. You have midjourney.com beta.dreamstudio.ai craiyon.com (real quick version no fuss, low quality) creator.nightcafe.studio and those are just some of the entry-level ones. I make ai art all day long! Check out my media feed on twitter @Sheilaaliens

> I make ai art all day long! I feel like this is the epitome of modern "content creation" Typing a few sentences into a software you barely understand, said software shits 15 jpegs out, 2 are good, "hey I make art". What a sad state of affair, tech is consuming everything and people are cheering, one more step on the path to being complete useless key pressers.

I’m not crazy about the tone you’re striking, but the bit about “software you barely understand” does ring true. Lots of folks who think hitting play in a notebook makes them some sort of AI-art-engineer these days.

On the other hand, the whole point of automating creation is that you don’t need to understand the underlying mechanisms.

Re: Imagen: An AI system that creates photorealistic images from input text

#114

Post by kache_ »

jquery wrote: post #110
Roark66 wrote: post #74

Every single time I see an article about a new AI model that has a section called "societal impact" I know immediately they are not releasing the model, the training set, nothing... It seems to be the kind of bullshit statement that those companies put in place of "we paid $500k training this model and we're not giving it for free to anyone".

I for one am glad that, for once in my life, an obviously huge advancement is taking into account the human impact of releasing the technology responsibly. Maybe it’s just a “BS statement” but given the major strides they’re making at removing racial/gender biases[1] from similar projects, I don’t think it’s just hot air. Especially given the phenomenon of “bias amplification”. Maybe I’m being too optimistic but eith…

right, because I can't be trusted to not be racist

Re: Imagen: An AI system that creates photorealistic images from input text

#115

Post by jug »

Roark66 wrote: post #74

Every single time I see an article about a new AI model that has a section called "societal impact" I know immediately they are not releasing the model, the training set, nothing... It seems to be the kind of bullshit statement that those companies put in place of "we paid $500k training this model and we're not giving it for free to anyone".

And especially so because this looks like a straight up marketing website. This is all about their own product.

Re: Imagen: An AI system that creates photorealistic images from input text

#116

Post by HPsquared »

ShamelessC wrote: post #113
lm28469 wrote: post #112

Earlier quoted context omitted.

> I make ai art all day long! I feel like this is the epitome of modern "content creation" Typing a few sentences into a software you barely understand, said software shits 15 jpegs out, 2 are good, "hey I make art". What a sad state of affair, tech is consuming everything and people are cheering, one more step on the path to being complete useless key pressers.

I’m not crazy about the tone you’re striking, but the bit about “software you barely understand” does ring true. Lots of folks who think hitting play in a notebook makes them some sort of AI-art-engineer these days. On the other hand, the whole point of automating creation is that you don’t need to understand the underlying mechanisms.

It's division of labour. The toolmaker has a different set of skills to the user of the tools.

Re: Imagen: An AI system that creates photorealistic images from input text

#117

Post by 411111111111111 »

jug wrote: post #115
Roark66 wrote: post #74

Every single time I see an article about a new AI model that has a section called "societal impact" I know immediately they are not releasing the model, the training set, nothing... It seems to be the kind of bullshit statement that those companies put in place of "we paid $500k training this model and we're not giving it for free to anyone".

And especially so because this looks like a straight up marketing website. This is all about their own product.

It’s not new, it was created shortly after dall-e. To my knowledge, there is no product atm. I’d pay to get access to this api, but you can’t.

Re: Imagen: An AI system that creates photorealistic images from input text

#118

Post by leetrout »

HPsquared wrote: post #116
ShamelessC wrote: post #113

Earlier quoted context omitted.

I’m not crazy about the tone you’re striking, but the bit about “software you barely understand” does ring true. Lots of folks who think hitting play in a notebook makes them some sort of AI-art-engineer these days. On the other hand, the whole point of automating creation is that you don’t need to understand the underlying mechanisms.

It's division of labour. The toolmaker has a different set of skills to the user of the tools.

Somewhat related, that made me think if pioneers, settlers and town planners

https://medium.com/org-hacking/pioneers-settlers-town-planne...

Re: Imagen: An AI system that creates photorealistic images from input text

#119

Post by lm28469 »

HPsquared wrote: post #116
ShamelessC wrote: post #113

Earlier quoted context omitted.

I’m not crazy about the tone you’re striking, but the bit about “software you barely understand” does ring true. Lots of folks who think hitting play in a notebook makes them some sort of AI-art-engineer these days. On the other hand, the whole point of automating creation is that you don’t need to understand the underlying mechanisms.

It's division of labour. The toolmaker has a different set of skills to the user of the tools.

The user, me included, has less and less knowledge and skills though.

When your tool becomes a megacorp owned subscription based service you barely understand is it really a tool ? It doesn't produce art in the way a brush and paint produce art, you barely have any control on what it does, you just become an image filter, you press a few keys, look at the image for 5 seconds and decide if it triggers the right part of your brain or not

It's not so different from the artist shitting on canvas, but at least he had the creativity to do something new and daring.

The end result might be called art but the whole process is completely devoid of what makes art "art"

Re: Imagen: An AI system that creates photorealistic images from input text

#120

Post by lm28469 »

curiousssnake wrote: post #42

There are some obvious mistakes in tools like this. Such as: Human faces are wrong, writing is usually scrambled, fingers look weird etc... Do you know if we need to have a major breakthrough similar to what happened 6 months ago to fix this or could these be fixed with incremental improvements in current techniques / datasets?

> similar to what happened 6 months ago

The major breakthrough that happened 6 months ago is that someone put their api behind a website for people to play with

Post reply on HN