Shocked, this is just insane.
Genuinely. I feel like I am dreaming. One year ago I was super impressed by upscaling architectures like ESRGAN and now we can generate 3d models, images and even videos from text...
Imagen Video: high definition video generation with diffusion models
251–260 of 500 posts
Re: Imagen Video: high definition video generation with diffusion models
#252Earlier quoted context omitted.
It won't be easy. But below are my thoughts: #1: Master these new tools #2: Build a workflow that incorporates these tools #3: Master storytelling #4: Master ad tracing and analytics #5: Get better at marketing yourself so that you stand out The market for your skillset may shrink, but I doubt it will disappear... Think about it this way... Humans in cheaper countries are already much more capable than any AI we've b…
Get better [...] so that you stand out Please bear with me but this kind of advice is often a bit puzzling to me. I suppose you don't know the person you're replying to, so I read your advice as a general one - useful to anyone in the parent's position. If you were close to her, it would make sense to help her 'stand out' in detriment - logically - to strangers in her field. But here you're kind of helping every read…
I [...] don't [...] like [...] helping a stranger.
Re: Imagen Video: high definition video generation with diffusion models
#253> Sprouts in the shape of text 'Imagen' coming out of a fairytale book.
That's more like:
> Sprouts coming out of book, with the text "Imagen" written above it.
Re: Imagen Video: high definition video generation with diffusion models
#254And there you have it. As an aspiring filmmaker and an AI researcher, I'm going to relish the next decade or so where my talents are still relevant. We're entering the golden age of art, where the AIs are just good enough to be used as tools to create more and more creative things, but not good enough yet to fully replace the artist. I'm excited for the golden age, and uncertain about what comes after it's over, but…
Don't worry. If you can place eyes, nose and mouth of a human in a correct relative position and thereby create a symmetric face that's not in the uncanny valley, you are still lightyears ahead of AI.
Re: Imagen Video: high definition video generation with diffusion models
#255Re: Imagen Video: high definition video generation with diffusion models
#256Earlier quoted context omitted.
>Google has no special claim to be able to responsibly use these models Well, they do have the "special claim" of inventing the model and not owing its release to anyone.
It's trained on our data, and so its release is in fact owed to us.
You are confusing this with OpenAI like everyone else in this thread.
Re: Imagen Video: high definition video generation with diffusion models
#257> Sprouts in the shape of text 'Imagen' coming out of a fairytale book. That's more like: > Sprouts coming out of book, with the text "Imagen" written above it.
The prompt actually says "Imagen Video" and the sprouts form the word "video". Even if they weren't it's still extremely impressive. No-one expects this to be perfect. That would be science-fiction.
Re: Imagen Video: high definition video generation with diffusion models
#258These videos are notably short on realistic-looking people.
Imagen is prohibited from generating representations of humans.
Re: Imagen Video: high definition video generation with diffusion models
#259Earlier quoted context omitted.
Emad (founder of Stability AI) has said they already have video model training underway, as well as text and audio. Exciting times.
And copilot-like code, possibly Q1 2023.
"Generate the code base for an advanced diffusion model that can improve on the code base for an advanced diffusion model"
Re: Imagen Video: high definition video generation with diffusion models
#260How long until the AI just generates the entire frame buffer on a device? Then you don’t need to design or program anything; the AI just handles all input and output dynamically.
Sounds like the human brain. Scary!