Pinned
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 👀
00:00
Common Sense Machines
1,060 posts
Common Sense Machines
@CSM_ai
The fastest way to create 3D with AI.
- Introducing Cube 2.0, a significant step towards controllable 3D game-world and video generation from any input. Powered by: 🌟 Image-to-3D in seconds w/ a new foundation model 🐎 Text-to-animation 🌎 AI rendering to create beautiful worlds (mesh+splats) Web app →
00:00 - Texture hallucinations have been a significant issue in image-to-3D models. Today, we are excited to release Cube V1.3, designed for improved image alignment. Now available to all Maker/Pro users. Upgrade: 3d.csm.ai/register. Start using it today: 3d.csm.ai.
00:00 - Topology and adaptive Level-of-Detail (LOD) have been unsolved problems and critical roadblocks towards full-scale studio/enterprise adoption of 3D GenAI. A new era in 3D generative modeling is taking shape, beyond SDS-based NeRFs/Gaussian Splats, SDFs, DMTeT, Flexicubes, etc.
00:00 - GPT-4o Image Generation to Part-based 3D Characters with PBR, in under 10 minutes ⚡️ Workflow: 🎨 Prompt GPT-4o to get an image (e.g., "3D asset of a styled character with all parts laid on a sheet for image to 3D") 🧩 Use CSM AI's Part-based tool to generate parts and assemble
00:00 - One step closer to give you 3D art super powers Cube v1.2-turbo is now available: 3d.csm.ai 🚤 Faster: Few secs for a preview, ~3 mins for a 3D blockout, and then refine for best outputs out there. 🖌️ Better Style Consistency: Image to 3D enables precise control.
00:00 - 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.
00:00 - Midjourney to 3D. Start using it now or join the waitlist: csm.ai/any-image-to-3d #midjourney #GenerativeAI #3Dartist
00:00 - Today, we are shipping a major release to solve for hallucinations, Object or Character Sheet-to-3D: 1. Artists can directly input concept art to get 3D. No need for aligned images! 2. Text → Sheet → 3D. Upgrade: 3d.csm.ai/register Blog: csm.ai/blog/sheet-to-…
00:00 - We have built CommonSim-1, a neural simulation engine controlled by images, actions and text. This is a new era in generative AI where simulators will grow and adapt with experience. Read on for more and sign up for early access to apps/API/open-source: csm.ai/commonsim-1-ge…
00:00 
00:00- Say hello to our new web-based AI World builder! 🗺️🤖🪄 Turning an idea into a controllable 3D world requires enormous effort. Cube now allows creators to generate 3D controllable videos (from images + text) for rapid ideation/UGC. Access (Maker/Pro): 3d.csm.ai/register
00:00 - We're thrilled to launch the CSM-Cube web app, designed to transform ANY image – be it AI-generated, concept art, or pictures – into high-resolution 3D assets. Start using us now: 3d.csm.ai We're also introducing an enhanced experimental model in this release!
00:00 - AI-generated assets have often faced criticism for not being production-ready due to their non-editable internal representations. Now, Cube supports AI-assisted UV unwrapping to fix this. Simply go to one of your refined meshes and click on 'UV Remapping'. This feature is
00:00