We just released 𝗞𝗶𝗺𝗼𝗱𝗼 — our new diffusion model for generating high-quality motion for humanoids and digital humans 🏃🤖
Check out the project page for more details!👇
research.nvidia.com/labs/sil/proje…
Unlimited AI generations with Cascadeur.
No tokens. No credits. No cloud.
We built our own ethical AI model – it runs right on your machine.
#gamedev#indiedev#3Danimation#Cascadeur
I tested the fastest 3D AI generator to see what actually works. ⏱️
Testing the new @tripoai update for game asset generation. It leaves older tools in the dust with its smart mesh logic. ⚔️
Pipeline used:
⚡ Generate base mesh in 5s
🗺️ Generate textures in 4K
🎨 Apply PBR materials
🚀 Export to engine
The final asset was production-ready in under 2 minutes, costing only $0.35 with almost zero manual cleanup. 📉
See the full benchmark:
youtu.be/mXjUz3viYmQ#3DAI#GameDev#TripoAI#3DModeling#GameAssets
Wow!!! MASSIVE news from @MaxonVFX! They’ve just announced a collaboration with Tencent to integrate their HY 3D AI model generation into C4D. This means that the first use of AI will be directly available in C4D.
Also buried in this announcement: C4D for iPad is coming!!! 🤯
What are we thinking out there?
maxon.net/en/article/max…
@julosheels Thx! Currently not atm. I can look into what it would take to support that though. This was mainly meant to be a personal tool for my own projects/use-cases. Which is why its mainly focused on fbx/glb.
Just built a new animation tool to simplify character workflows.
Upload a Mixamo-rigged base model (FBX/GLB), drop in any number of animation FBX files, and export a single GLB with all clips consolidated and ready for use in-engine.
It supports custom VRoid/VRM models too which you can see at the end of the video.
Right now it only outputs to GLB, but i'll prob add more formats soon.
This saves me a ton of time and hassle having to manually import and hook up every clip in-engine. Now, one click and it's all taken care of.
Just a few months after releasing Scoot, which we feel redefined motion generation quality, our team has made substantial improvements in speed, quality, subtlety, and instruction following.
This comes in concert with our newly scaled data collection and labeling efforts, compute increase, substantial architectural improvements, and more stable / scalable training dynamics.
Swing is our new flagship movement model. It's live today in Cartwheel studio with infinite batch generation coming soon to our API.
Treating Movement as a fundamentally new data type has really unlocked our ability to rapidly make improvements. As it turns out there are far more use cases than you might imagine from entertainment to robotics.