Tangentially related but what's the name of the style that this website uses? I see it a lot recently. It's kind of retro-Y2K, it's got icons with big thick lines, lots of movement (spinning elements, tickers), a wide title font, background blurring on fixed elements and lots of gradients.
Hello! Thank you, glad you liked it! I'm from the AI Team but I already sent your question to our web dev team and they will answer to you pretty soon.
Haha yeah, that's getting trendy. But to be honest, this style reminds me of the 90's like you said and it matches perfectly the street art and retro style you'll find in Brick Lane, where we have our London office: http://www.sundayupmarket.co.uk/
One of our co-founders and Artist Director is actually a street artist, so many inspiration from there :-)
Very impressive! I suspect I'm not alone among the HN crowd in being curious to know how this AI works; I presume it is some kind of ANN?
It's clearly not perfect when compared to rigging and skinning by a skilled artist, but it's pretty good. As someone who has done a large amount of 3D computer graphics myself, I think one would need close to a year of experience to be able to consistently produce something as good as what this tool can.
Hello! One of the ML Engineers of Anything World here. I'm really glad that you appreciated the tool and I trully hope that it can be part of your stack and help you on your design.
We can't say all the details about what's under the hood, but you guessed it right. We indeed use ML models that we trained. It's part of a multi-step end-to-end ML pipeline that analyses not only the original mesh you upload, but also the texture and even semantics from the object it represents. Based on that we generate rigging and animations using also proprietary ML models.
Like you said, it's not perfect, but our ML models are learning every day and we just started! I really invite you to use the tool and see that it can be used as a starting point even by skilled artists to have an initial sketch and work from it.
Hope to have helped on your questions, and if you need more details, please feel free to reach out to us!
I'm guessing since the website says "We have developed proprietary Machine Learning algorithms" they won't really share any fun technical details :(
> but it's pretty good
Yeah, seems alright in order to bootstrap something. Like many of these new AI/ML workflows, I don't think they'll replace any professionals, as the results are still lacking without human intervention, but I think many (including this) is a huge time-saver for professionals who can use it as a starting point and then modify it from there, rather than doing everything from scratch.
Hello Capableweb! We appreciate your interest in trying out our new animation service.
While we can't disclose all the technical intricacies, we can share that our approach involves the use of ML models, Neural Networks, and a series of refinement steps to enhance rigging and deliver more refined animations. We are aware that our current rigs and animations may not be flawless, but I want to emphasize our unwavering commitment to continual improvement.
For any additional inquiries or if you need further clarification, please don't hesitate to reach out to us via Discord or by emailing us at [email protected]. Your feedback and support are greatly appreciated!
Hey! We can't share much what details of our ML pipeline for now but I can say that's a good guess :-) And you're right, we have bipeds, quadrupes, flying animals, vehicles, etc and we can actually handle any arbitrary model that belongs to one of those categories.
Its most likely some skeleton building based on distance from skin, probably with some ML model based on trained datasets.
Animation looks like basically figuring out which part of the model moves the most based on training data ( legs for humans, wings for anything that has wings, 4 legged vs 2 legged), and then there is some gradient applied based on dynamic relation of mass with body parts reacting to the movement.
Sorry, we can't disclose all the technical intricacies, we can share that our approach involves the use of ML models, Neural Networks, and a series of refinement steps to enhance rigging and deliver more refined animations.
You can check our tool here at https://app.anything.world/animation-rigging and please give us feedback
Hello! So sorry to hear that our pricing model doesn't match your expectations. What would be an interesting pricing model in your opinion? Thanks for your feedback!
Thank you!! We are glad that you liked the tool. Unfortunately, as you mentioned GPU rates are costly, we hope that going forward we will be able to make it more affordable with the help of subscribers like you.
We regret to inform you that specifying the skeleton is not currently an option and we are working on that. But you do the option to modify the position of the rig without adding/deleting the joints. Also, you do have the option to download the skeleton provided by us separately and then manually map it to your animation as needed.
We currently have constraints related to the specific number of vertices, but we are actively in the process of developing high-poly models that will soon be available for upload into our system. This will enable you to use the subdivided models directly for your projects.
If you have any additional questions or require further clarification, please feel free to contact us via Discord or send us an email at [email protected]. Your feedback and support mean a lot to us!
I'll be curious how it compares to mixamo's auto rigging. How does it perform on humanoid models? Seems from the marketing the focus is on non-humanoids.
Hi, one of the ML Engs here. Yes you're right, we have lots of non-humanoids, which is something that Mixamo has been missing for a long time! But we also support humanoids. You can try yourself right now (we just launched our autorigging tool) and give us your feedback, we would love to hear it: https://app.anything.world/animation-rigging
Thank you so much! We rig and animate for a general skeleton, but we have Unity and Unreal plugins that add controllers to our 3D models to make it easy to add the behaviour you want.
I'm from the AI team, so my Unreal knowledge has a limit :-D But please, join our Discord at https://discord.gg/anythingworld and I'll be more than happy to connect you with one of our Unreal Engineers to give you more details.
> A blocklist will never block every script and snippet
Yeah, it probably won't, but collaboratively, we can block a lot :) Also, naive uBlock method will probably be more efficient in terms of resource usage for some time forward.
In this case, I never saw any cookie banners and it seemed to have blocked what I wanted to have blocked automatically. Here is the log: https://i.imgur.com/rteXlAC.png
This is great...How hard would it be to port a model to Godot....just getting started with hobby game development and this might solve one of my issues
Hey hey! Thank you! Godot supports importing GLTF and other formats that we export, so you can basically use our tool (https://app.anything.world/animation-rigging), export a GLTF and import it in Godot.
Right now we only have plugins for Unity and Unreal, so you would have to create your own controllers in Godot. But having the rigging/animation already gives you a good start!
And please, share the details of your game project with us, we love to support indie game devs!
On https://app.anything.world/animation-rigging the 3D background is really smooth once it loads, but that takes a while on slower networks/CPUs. It might be worth a adding little CSS loading indicator before the script so that people know that something is coming!
Hello! Yes, when compared to Mixamo, our pipeline is not procedural nor static. We built an end-to-end ML pipeline that analyses the mesh/texture you upload and generate unique rigs and animations for your 3D model.
Different from Mixamo, we support all kinds of 3D object categories (animals, insects, vehicles, humanoids, etc) while Mixamo only provides a static gallery of already animated humanoids.
Okay I’ll admit this is super cool- I like what AI art generation has been doing for the game/animation hobbyist, and as someone who sucks at 3D modeling and sculpting I’ve been hopeful it’ll come to the 3D model space. This rigging if it works good will be a step in the right direction.
Hey hey! Thank you so much, we're really glad that you nailed the goal here: generative AI sometimes can go for a bit weird paths, but in our opinion it should first try to automate or augment what is pretty time consuming (and boring) for humans to do.
Please keep following us and drop us a line if you have any questions or suggestions!
Unrelated, but there’s a gnarly CSS bug on your menu that causes the weirdest behavior on iOS. The native scroll bar appears much taller than it should be and visibly reacts to scrolling, but the content on the page does not (so I can’t reach the bottom of the menu).
Might be a fixed parent element missing `overflow-y: none;` but the lack of devtools on mobile means I can’t check (even more tangentially, if anyone knows a way to access something like devtools in iOS, I would be thrilled to hear about it).
