正在加载视频...

视频加载失败

返回首页

CSM Cube has been upgraded to have better geometry for image-to-3D generations. Enjoy cubing! 🧊🎨

CSM_ai's profile picture

Common Sense Machines

9,767 subscribers

12,680 次观看 • 1 年前 •via X (Twitter)

科学技术教育艺术
LIVE

Anya Rossi• Live Now

Private livecam show

5 条评论

MORiTZ RYSER 的头像
MORiTZ RYSER1 年前

been using since the service came out, love to see the progression!

Common Sense Machines 的头像
Common Sense Machines1 年前

Glad to hear!

Digital Currency 的头像
Digital Currency2 年前

From 3D modeling to VR/AR development, our MSc in Metaverse program equips you with the technical skills to excel in the rapidly evolving digital world. Don't miss out—enroll today! #UNIC #MScMetaverse

Gonduras Jitomirsky 的头像
Gonduras Jitomirsky1 年前

i am with you generating 3d from my own art from early beta. need more credits to play with. when my project goes commercial - i will be ready to pay!

Common Sense Machines 的头像
Common Sense Machines1 年前

Email us at [email protected]

相关视频

🚨 Pixal3D is now live on fal! 🧊 High-fidelity 3D assets from a single image 🎯 Pixel-aligned back-projection for direct pixel-to-3D correspondence 🎨 Detailed geometry with PBR textures, ready for downstream pipelines
0:38

🚨 Pixal3D is now live on fal! 🧊 High-fidelity 3D assets from a single image 🎯 Pixel-aligned back-projection for direct pixel-to-3D correspondence 🎨 Detailed geometry with PBR textures, ready for downstream pipelines

fal

14,192 次观看 • 1 个月前

CSM AI releases Any Image to 3D blog: Compared to the latest Shape-E model from openAI, model does significantly better
1:11

CSM AI releases Any Image to 3D blog: Compared to the latest Shape-E model from openAI, model does significantly better

AK

107,524 次观看 • 3 年前

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: Start using it today:
0:20

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: Start using it today:

Common Sense Machines

242,044 次观看 • 2 年前

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 in Blender.
0:48

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 in Blender.

Common Sense Machines

441,683 次观看 • 1 年前

Image to 3D prints? Instantly. Meshy 6 Preview is your new powerful generator, creating sculpting-level models with print-ready geometry. Your 3D printer has been waiting for this. 🤩 Upload it. Generate it. Print it.
0:37

Image to 3D prints? Instantly. Meshy 6 Preview is your new powerful generator, creating sculpting-level models with print-ready geometry. Your 3D printer has been waiting for this. 🤩 Upload it. Generate it. Print it.

MeshyAI

26,439 次观看 • 9 个月前

Pragmata has been stealth updated on PS5 Pro to support better image quality. The native internal resolution has been improved for a cleaner image and better RT reflections. (via @DigitalFoundry)
0:30

Pragmata has been stealth updated on PS5 Pro to support better image quality. The native internal resolution has been improved for a cleaner image and better RT reflections. (via @DigitalFoundry)

KAMI

42,930 次观看 • 1 个月前

Image to depth using Marigold and ConfyUI Then depth to 3D geometry in Blender Super interesting stuff 🤯
0:31

Image to depth using Marigold and ConfyUI Then depth to 3D geometry in Blender Super interesting stuff 🤯

A.I.Warper

201,906 次观看 • 2 年前

Meet our new and fast 3D sculpting model! ✅ Single image to mesh with detailed geometry in the order of minutes (more GPUs coming to get to <30-60s) ✅ Dense mesh re-topology using our custom language model (minutes) Available on all Cube plans:
0:51

Meet our new and fast 3D sculpting model! ✅ Single image to mesh with detailed geometry in the order of minutes (more GPUs coming to get to <30-60s) ✅ Dense mesh re-topology using our custom language model (minutes) Available on all Cube plans:

Common Sense Machines

53,289 次观看 • 1 年前

CSM on Google Cloud is a game-changer (pun intended). Turn any prompt (text, image, sketch) into game-engine-ready 3D assets in minutes. Rapidly iterate on ideas and streamline 3D asset production with Common Sense Machines tools to bring your games to life quicker, better, and for less ↓
1:08

CSM on Google Cloud is a game-changer (pun intended). Turn any prompt (text, image, sketch) into game-engine-ready 3D assets in minutes. Rapidly iterate on ideas and streamline 3D asset production with Common Sense Machines tools to bring your games to life quicker, better, and for less ↓

Google Cloud

28,439 次观看 • 1 年前

A Gradio demo of Rodin Gen-1.5 Image to 3D Geometry Generation🚀 Use #BlackMythWokong as input image🔥❤️ High-fidelity Surface than ever💥
0:27

A Gradio demo of Rodin Gen-1.5 Image to 3D Geometry Generation🚀 Use #BlackMythWokong as input image🔥❤️ High-fidelity Surface than ever💥

Deemos

13,712 次观看 • 1 年前

We just released a new update to our geometry model! High-Poly Sculpting is looking better than ever and is now live on CSM AI for all users! ⚒️ ✨
0:29

We just released a new update to our geometry model! High-Poly Sculpting is looking better than ever and is now live on CSM AI for all users! ⚒️ ✨

Common Sense Machines

11,265 次观看 • 1 年前

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.
0:46

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.

Common Sense Machines

16,882 次观看 • 10 个月前

We are thrilled to release Chat-to-3D on CSM AI, to enable unprecedented mesh quality and controllability. This entire character was prompted end-to-end using this release. 🛠️ Automatically generate parts for complex assets 🌐 Generate T-pose outputs from any input 🎨 Generate style variations in one-shot Image generation is powered by gpt-image. Available to all users (creative pro+ members get highest resolution outputs).
0:52

We are thrilled to release Chat-to-3D on CSM AI, to enable unprecedented mesh quality and controllability. This entire character was prompted end-to-end using this release. 🛠️ Automatically generate parts for complex assets 🌐 Generate T-pose outputs from any input 🎨 Generate style variations in one-shot Image generation is powered by gpt-image. Available to all users (creative pro+ members get highest resolution outputs).

Common Sense Machines

29,793 次观看 • 1 年前

Love these old meets new vfx workflows 1. extract a still of the object you want to augment 2. use image-to-3d to make a 3d model of the object 3. use that 3d geometry for classical object tracking Then you can go wild with complete control
0:44

Love these old meets new vfx workflows 1. extract a still of the object you want to augment 2. use image-to-3d to make a 3d model of the object 3. use that 3d geometry for classical object tracking Then you can go wild with complete control

Bilawal Sidhu

33,824 次观看 • 1 年前

Max Park is the speed cubing goat 🐐 On Sunday, he set a new world record for the fastest time to solve a 3x3x3 cube at 3.13 seconds. He smashed the record by 0.4 seconds. It means he now has the fastest times to solve a 3x3x3, 4x4x4, 5x5x5, 6x6x6 and 7x7x7 cube.
3:00

Max Park is the speed cubing goat 🐐 On Sunday, he set a new world record for the fastest time to solve a 3x3x3 cube at 3.13 seconds. He smashed the record by 0.4 seconds. It means he now has the fastest times to solve a 3x3x3, 4x4x4, 5x5x5, 6x6x6 and 7x7x7 cube.

Guinness World Records

219,305 次观看 • 3 年前

Feed-forward 3D Gaussians from Visual Geometry Group (VGG) strike again! Flash3D has now been accepted to 3DV 2025: it is a method for feed-forward single-view 3D scene reconstruction. Project page: Code: Arxiv: A 🧵👇
0:27

Feed-forward 3D Gaussians from Visual Geometry Group (VGG) strike again! Flash3D has now been accepted to 3DV 2025: it is a method for feed-forward single-view 3D scene reconstruction. Project page: Code: Arxiv: A 🧵👇

Stan Szymanowicz

26,970 次观看 • 1 年前

🙏 We have all been lied to for generations 🙏 - Mrs B
2:19

🙏 We have all been lied to for generations 🙏 - Mrs B

Riccardo Bosi

20,470 次观看 • 9 天前

HAD TO PULL IN Ice Cube FOR OUR JERSEY LAUNCH 🧊◼️ #ALLIN | Pickett
0:27

HAD TO PULL IN Ice Cube FOR OUR JERSEY LAUNCH 🧊◼️ #ALLIN | Pickett

Ottawa REDBLACKS

76,002 次观看 • 2 年前

🚀 Introducing Meshy-4 — The next-gen 3D model generator is now available to everyone at ✨ Experience dramatically improved mesh geometry in both Image to 3D and Text to 3D workflows. ❤️ Watch the video and discover Meshy’s full potential with us!
0:54

🚀 Introducing Meshy-4 — The next-gen 3D model generator is now available to everyone at ✨ Experience dramatically improved mesh geometry in both Image to 3D and Text to 3D workflows. ❤️ Watch the video and discover Meshy’s full potential with us!

MeshyAI

52,437 次观看 • 1 年前