Earlier quoted context omitted.
What will AI train on?
3D scans of the real world?
I don't think the "what will it train on" argument is bullet-proof, but animation and 3D art can encompass so much more than just things that exist in the real world.
Blender 5.0
21–30 of 377 posts
Re: Blender 5.0
#22I've been using blender since at least 2010; it's so exciting to see how much progress it's making.
I'm very excited to see the addition of structs and closures/higher-order functions to blender nodes! (I've also glanced at the shader compiler they're using to lower it to GLSL; neat stuff!) Not only is this practically going to be helpful, the PL researcher in me is tickled by seeing these features get added to a graphical programming language.
If you haven't heard of Blender before, or if you think AI will replace all the work done in it, fair enough. But I'd still strongly suggest looking into what it is and how it works.
Re: Blender 5.0
#23What’s the consensus on the future of this type of 3D tool? Especially for video animation/CGI in movies/tv/ads? Seems like in 10 years AI will basically make it pointless to use a tool like this at least for people working on average projects. What do folks in the industry think? What’s the long term outlook?
If AI is at the point where it is exactly as capable of your average junior 3D professional in 10 years, it will probably have automated a ton (double digit percentage?) of current jobs such that nothing is safe. There's a lot of complexity, it's fairly long time horizon, it's very visually detailed, it's creative and subjective, and there's not a lot of easily accessible high quality training data.
It's like 2D art with more complexity and less training data. Non-AI 2D art and animation tools haven't been made irrelevant yet, and don't look like they will be soon.
Re: Blender 5.0
#24Very very sad that the adaptive subdivision is touted as a Blender feature but unfortunately it's a Cycles feature.
Always nice to see these updates though, Blender has really come a long long way.
Re: Blender 5.0
#25Earlier quoted context omitted.
But after that, all the other things on the page are AWESOME! I’m super stoked about the proper HDR support and all the new node improvements.
Yeah. the HDR support is very nice. ACES got their system right the 2nd time around thankfully.
Is this the first blender release where you can change the working color space? I thought that you could in previous versions but it caused issues with some nodes.
Now I want to look into it more, but I'd imagine that "Blackbody" and sky generation nodes might still assume a linear sRGB working space.
Re: Blender 5.0
#26I’d really like to see something like blender come for the 3D CAD industry, at the moment it feels like the only people who would lose out are AutoDesk. The amount of money that flows in and out of 3D cad (as subscription and then value created) having a first class open source kernel and tooling, would be giving big industrial players freedom to modify and tailor to their needs as well as smaller / hobbyists get started for free!
Re: Blender 5.0
#27Earlier quoted context omitted.
But after that, all the other things on the page are AWESOME! I’m super stoked about the proper HDR support and all the new node improvements.
Yeah. the HDR support is very nice. ACES got their system right the 2nd time around thankfully.
why ACES and not something like
P3?
Re: Blender 5.0
#28Very very sad that the adaptive subdivision is touted as a Blender feature but unfortunately it's a Cycles feature. Always nice to see these updates though, Blender has really come a long long way.
It might be possible to reproduce the same effect in EEVEE using geometry nodes. I know people have done that for automatic level of detail work. That being said, IDK if subsurf as a geometry node will take a non-constant number of iterations.
Re: Blender 5.0
#29Re: Blender 5.0
#30What’s the consensus on the future of this type of 3D tool? Especially for video animation/CGI in movies/tv/ads? Seems like in 10 years AI will basically make it pointless to use a tool like this at least for people working on average projects. What do folks in the industry think? What’s the long term outlook?
Directors spend a LOT of effort trying to keep continuity and that's the weakest part of AI.
What blender and other CGI software gets for free is continuity. The 3D model does not change without explicitly making it change.
Until we get AI which can regenerate the same model from one scene to the next, the use of AI in CGI will be severely limited.