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

Stable Diffusion animation

replicate.com

Post reply on HN
Print view View original

101–107 of 107 posts

Re: Stable Diffusion animation

#101

Post by omnimus »

desindol wrote: post #52

Maybe I can shine some light on the debate from an concept artist standpoint that works in VFX and advertising. I worked on feature films (3 of them in the imdb top 100), tv shows (like game of thrones) and hundreds of AD campaigns. In the last 10 year the work of a concept artist changed dramatically we have gone from purely painted concept art to mostly "photobashed". Photobashed means basically that you rip apart…

This honestly only confirms their fears. What you are saying is "yeah we have been photobashing all those artist for a long time anyway now its just much more efficient and automated".

I would be pretty afraid and angry if i was artist too.

Re: Stable Diffusion animation

#102

Post by rnjesus »

NaturalPhallacy wrote: post #99
fagerhult wrote: post #29

Andreas, author of the Replicate model here -- though "author" feels wrong since I basically just stitched two amazing models together. The thing that really strikes me is that open source ML is starting to behave like open source software. I was able to take a pretrained text-to-image model and combine it with a pretrained video frame interpolation model and the two actually fit together! I didn't have to re-train o…

> Talking alien! Maybe that's what we were supposed to do all along. Not find or be found by aliens, but to invent them.

that’s exactly what we’ve been doing

Re: Stable Diffusion animation

#103

Post by tough »

CuriouslyC wrote: post #76
rjh29 wrote: post #44

Earlier quoted context omitted.

For anyone interested in a GPU btw, the 3090 TI had a huge price cut and costs only a bit more than the 3090 right now.

Yup! I've never splurged on a GPU before, but a 3090 TI lets you do textual inversion, and fine tune GPT-J (neither of which you can do with <24gb vram), so now I've got one sitting on my study floor waiting to be installed :)

> https://twitter.com/dreamwieber/status/1565008078466326528?s...

same mine arrives tomorrow, can't wait to try textual-inversion

Re: Stable Diffusion animation

#104

Post by desindol »

omnimus wrote: post #101
desindol wrote: post #52

Maybe I can shine some light on the debate from an concept artist standpoint that works in VFX and advertising. I worked on feature films (3 of them in the imdb top 100), tv shows (like game of thrones) and hundreds of AD campaigns. In the last 10 year the work of a concept artist changed dramatically we have gone from purely painted concept art to mostly "photobashed". Photobashed means basically that you rip apart…

This honestly only confirms their fears. What you are saying is "yeah we have been photobashing all those artist for a long time anyway now its just much more efficient and automated". I would be pretty afraid and angry if i was artist too.

We are these artists or better art directors.

Re: Stable Diffusion animation

#105

Post by redox99 »

danwills wrote: post #73
redox99 wrote: post #32

Earlier quoted context omitted.

For 3D we would probably need something like Blender or similar, because at some point it's just easier to use a 3D software to pinpoint where you want stuff to be, than try to use words. Imagine opening blender and typing > A medium sized classroom, well lit, with two blackboards and many geography posters And the AI just generates all the 3D meshes and places them appropriately. Repeat that for other props or chara…

I think you're right about the possibilities here and I love the idea and have thought similar things myself too, but to me the inclusion of a 3D element should probably be a format, not necessarily locked into any specific app such as Blender. Maybe (Pixar) USD is one possible format that could be used for general 3D interchange for this kind of thing?

The blender thing was just as an example. Of course it would be possible to convert whatever the output of the model is, to whatever software you want to plug it in.

Re: Stable Diffusion animation

#106

Post by omnimus »

desindol wrote: post #104
omnimus wrote: post #101

Earlier quoted context omitted.

This honestly only confirms their fears. What you are saying is "yeah we have been photobashing all those artist for a long time anyway now its just much more efficient and automated". I would be pretty afraid and angry if i was artist too.

We are these artists or better art directors.

The way VFX industry called everyone artist because they are working in with visuals has always been confusing.

You have many professions who work with visuals and never would call themselves artist - designers, illustrators.

If you photobash all day to generate ideas its much closer to design than to what people would call artist.

Maybe thats a cultural difference but i always thought that distinction is clear. Anyone working in anything pop culture, commercial, “industry” is those other professions. People independly doing visuals (anything really) for visuals sake are called arists.

So when i mention artist i imagine completely different group of people than you.

Re: Stable Diffusion animation

#107

Post by Llamamoe »

desindol wrote: post #52

Maybe I can shine some light on the debate from an concept artist standpoint that works in VFX and advertising. I worked on feature films (3 of them in the imdb top 100), tv shows (like game of thrones) and hundreds of AD campaigns. In the last 10 year the work of a concept artist changed dramatically we have gone from purely painted concept art to mostly "photobashed". Photobashed means basically that you rip apart…

Can I ask again about your recommendations for getting into photobashing and AI-assisted air again?
Post reply on HN