Common Sense Machines

Text, logos, and fine details have always been tough for 3D AI - but we’ve cracked it 🚀 Our latest model delivers unprecedented textured mesh quality, and it scales nicely with compute & data. Coming soon 👀

Generated end-to-end using CSM Cube (post-assembled in Blender). 🌎🎨☕️

skip to 36:26 to see the weird wacky wonderful world @CanessaDCL created in Decentraland with @CSM_ai absolute insanity

The Decentraland Art Week Workshop agenda is stacked with step-by-step guides from @ArtiviveApp, @CSM_ai, @SloydAi, and @ImagineArt_X 👏 Come ready to build, experiment, and get inspired.

A few more texture comparisons from our upcoming model (Rodin, Hunyuan2.5).

Here are a few more examples from our upcoming Image-to-3D model, showcasing unprecedented texture quality.

@LarryAGuy1 All our assets work seamlessly with Blender

@CSM_ai Please tell me you are integrated with Blender modeling to help the speed and improve games??

Text, logos, and fine details have always been tough for 3D AI - but we’ve cracked it 🚀 Our latest model delivers unprecedented textured mesh quality, and it scales nicely with compute & data. Coming soon 👀

@eleven21 Aiming end of month but let's see

@CSM_ai When???

@codewithimanshu This should help accelerate existing workflows and also new (UGC) workflows

@CSM_ai Intriguing. This could significantly impact 3D modeling accessibility and detail. What are the implications for existing workflows?

@koguGameDev Give it a spin and let us know! DMs and email open (hello@csm.ai)

CSMがテクスチャの品質かなり上げてる。Tripo、Rodin、Hunyuan、Hitemは大体掴めたから、次はCSMとMeshy行くか。

Our new 3D AI output significantly outperforms Hunyuan3D-2.5

By popular demand, we're sharing more examples that showcase CSM Cube's ability to generate high-quality 3D mesh topology and distinct parts. The results shown were achieved using our single-click Image-to-3D feature, but users can obtain even better quality with careful prompting and editing.

CSM Cube delivers industry-leading model quality, topology, parts, and AI re-topology, providing a significant advantage for workflows from quick prototypes to full production.

たった1枚の写真から、3Dモデルが「完全再現」される── @CSM_aiの新しい3D AIモデルが、パーツ単位のメッシュと、PBRテクスチャを自動生成。CSM Cube上ですでに利用可能。 「写真→3D」がかなり実用フェーズになってきている。

We are thrilled to release a new 3D AI model to output parts-based meshes 🧩 with baked and PBR textures 🎨 from single images 📸 Available now to everyone on CSM Cube. 🎨🌐

Special thanks to @GoogleDeepMind for inviting me to try out Genie 3. I'm excited to share my thoughts on this early research prototype and also some of my live recordings below: I spent the whole day playing with the system and when it works, it is truly mind blowing🤯. It is the first neural game engine / world model I have tried that generalizes so well and has long term world consistency. Here’s a couple of examples from my live recording and some thoughts on what it means for the future of gaming, robotics, digital experiences and ASI. Where it shines: - Truly general-purpose and quick startup time. Works exceptionally well for gaming environments but also generalizes to other industrial and real-world scenarios. - It learns physics. Although there are systematic failures even for rigid body physics, it was clear to me that it can learn game engine and non-rigid physics without an underlying engine (and in limit learn from game engines via training data). - It works exceptionally well for stylized environments with characters walking around. This will have implications for concept artists, level designers and game devs. - It is way more fun than video models, indicating that there are high retention consumer experiences waiting to be built with this in the future - Photorealistic walk throughs and drone shots work exceptionally well - Global illumination and lighting works surprisingly well - Visual memory is quite powerful and the same objects approximately remain coherent under occlusion and longer time horizons Open Problems: - Physics is still hard and there are obvious failure cases when I tried the classical intuitive physics experiments from psychology (tower of blocks). - Social and multi-agent interactions are tricky to handle. 1vs1 combat games do not work - Long instruction following and simple combinatorial game logic fails (e.g. collect some points / keys etc, go to the door, unlock and so on) - Action space is limited - It is far from being a real game engines and has a long way to go but this is a clear glimpse into the future. The Future: - It is impressive enough for me to have strong conviction that this is going to disrupt the gaming industry. It is super early days and there are a lot of failures but the writing is on the wall. Lots of challenging scientific, engineering and scaling problems to be solved but it is going to happen in the next 5 years. - This is the final piece before we get full AGI and now I think we are well on our way to truly solve it once something like this is scaled up. In many ways it is more ASI than AGI but this is a matter of definitions. The fidelity and generalizability will reach human-level and quickly surpass humans - People are going to combine this with 3D AI and LLMs to build AAA games.

「1枚の画像」から、ここまでの3Dが作れる時代です。 @CSM_aiを利用したデモ。まずは、画像1枚から高精度な3Dシーンを生成。さらに、Parts with auto assemblyでパーツ毎に書き出し、Chat to 3Dを組み合わせて調整。素晴らしい精度。 もはやモデリングは「入力」次第。

Access now: 3d.csm.ai

In this quick and easy video, we will show you how to use our tools to create a detailed 3D scene. 🌐🖌️ Our tools used in this process: - Parts with auto assembly (3D Generation with multiple parts) - Single image to 3D: Turbo & Base Model (Basic 3D Generation) - Chat to 3D (Image generation)

CSM Cube now supports highly complex 3D assets with better adaptive topology. Our underlying models now maximize accuracy and minimize poly-counts at the part-level.🎨🖌️ Steps: - Image to Kit (optional) - Kit or single images to parts with auto-assembly - AI re-topology