Imagen Video: high definition video generation with diffusion models

Post by capitalsigma » Wed, Oct 05, 2022, 11:51 PM UTC

dannyw wrote: post #287

capitalsigma wrote: post #283

Earlier quoted context omitted.

Wrongfully or not, people blame Facebook for inflammatory content posted by humans on their platform. How much worse would it be if that content was generated with FB-trained models?

People blame Facebook for their intentional, and continued choice to use algorithms that amplify and surface inflammatory content.

Post by ihuman » Wed, Oct 05, 2022, 11:54 PM UTC

pishpash wrote: post #269

educaysean wrote: post #264

Earlier quoted context omitted.

The way I see it, input being confined to a "text description" is the next immediate problem that needs to be solved. I don't think we can rely on textual inputs for much longer as the human language is too imprecise and/or verbose. It's hard to imagine what exactly the optimal interface would be, but I'm thinking we'll need ways to dictate attributes for each entity being represented, the backdrop, and the view comp…

Like an AI-assisted photoshop, but that's not restricted by language, only interactivity. Down the line you'll need a direct mind meld because some ideas don't have words to describe them, but that's not the "next immediate" problem.

Post by sbierwagen » Wed, Oct 05, 2022, 11:55 PM UTC

atty wrote: post #266

i_like_apis wrote: post #261

The concern trolling and gatekeeping about social justice issues coming from the so-called "ethicists" in the AI peanut gallery has been utterly ridiculous. Google claims they don't want to release Imagen because it lacks what can only be called "latent space affirmative action". Stability or someone like it will valiantly release this technology, again and there will be absolutely no harm to anyone. Stop being so to…

There is a clear risk from these sorts of models as they get better - I mean recreating specific individuals’ likenesses in compromising images (or even worse, video). We’re not at that point yet, but these things are getting better fast, so it’s only a matter of time. The problem is that there’s no way to mitigate those risks except to keep the model behind an inference-only API, or not release it at all - as soon a…

Post by kromem » Thu, Oct 06, 2022, 12:01 AM UTC

splatzone wrote: post #271

javchz wrote: post #267

Earlier quoted context omitted.

Imagine you click a youtube video in a bad network envoirment, then the server sends like an alt tag equivalent for the video as a promnt, and the Neural Engine chip inside your phone create the first seconds of the video while it loads. We're fay away from it now, but I've seen less sketchy solutions being implemented.

I wonder if this is an area actively being researched, using models like these for video compression?

Post by carlosdp » Thu, Oct 06, 2022, 12:04 AM UTC

atty wrote: post #288

carlosdp wrote: post #285

Earlier quoted context omitted.

> There is a clear risk from these sorts of models as they get better - I mean recreating specific individuals’ likenesses in compromising images (or even worse, video). This has been possible without AI for a very very long time now (just open photoshop, etc). It barely ever happens, and society hasn't collapsed. I keep seeing this argument come up and it baffles me that informed technologists take it seriously, as…

There is a difference in ease of use. I could never use photoshop to fake something like that even if I wanted to. Further, we have seen harm come from some of this already, there’s a pretty big online community that uses deepfakes to put people in situations they would rather not be in, the most obvious being porn.