Loading video...

Video Failed to Load

Go Home

All these isometric buildings were generated with AI - from a single input image each (examples below 👇) Just a few minutes per 3D mesh (no textures yet). This is #Sparc3D, a new generative 3D model announced just a few days ago. 🧵

emmanuel_2m's profile picture

Emm | scenario.com

46,902 subscribers

16,012 views • 1 year ago •via X (Twitter)

#Sparc3D
LIVE

Anya Rossi• Live Now

Private livecam show

8 Comments

Emm | scenario.com's profile picture
Emm | scenario.com1 year ago

This glb was all 100% generated. From one single image. Unreal.

Emm | scenario.com's profile picture
Emm | scenario.com1 year ago

Sparc3D is a project by @zhhol141234, Math Magic, and Nanyang Technological University (Singapore 🇸🇬) "Sparse Representation and Construction for High-Resolution 3D Shapes Modeling" Read more at (+ demo available)

Emm | scenario.com's profile picture
Emm | scenario.com1 year ago

Here's the Sagrada Familia in Barcelona

Mobile Scanner's profile picture
Mobile Scanner1 year ago

Scan any documents, convert images into text, PDF files, etc. 👍

Michael + puppetto.com's profile picture
Michael + puppetto.com1 year ago

Ooooh these look tasty

Nanya⭐️'s profile picture
Nanya⭐️1 year ago

I am impressed

Heba AI's profile picture
Heba AI1 year ago

Better than Hunyuan? It has some problems figuring out whats on the other side of the isometric object. Also the edges have unwanted bewels too often.

Emm | scenario.com's profile picture
Emm | scenario.com1 year ago

Much more precise than Hunyuan though, in a lot of cases

Related Videos

Alibaba released LHM! a new model that can generate high-quality, animatable 3D human avatars from a single image in just a few seconds
0:55

Alibaba released LHM! a new model that can generate high-quality, animatable 3D human avatars from a single image in just a few seconds

Dreaming Tulpa 🥓👑

21,853 views • 1 year ago

Making 3D assets just got stupidly easy. Tripo turns a sentence or a single image into a full 3d model, ready for blender, games, printing, whatever. Idea → image → 3D asset. Full workflow below 🧵
0:20

Making 3D assets just got stupidly easy. Tripo turns a sentence or a single image into a full 3d model, ready for blender, games, printing, whatever. Idea → image → 3D asset. Full workflow below 🧵

Farhan

44,468 views • 1 month ago

📢 A Recipe for Generating 3D Worlds From a Single Image 📢 Our recipe explains how existing generative models can be adapted with minimal training effort to generate 3D worlds from a single input image.
0:28

📢 A Recipe for Generating 3D Worlds From a Single Image 📢 Our recipe explains how existing generative models can be adapted with minimal training effort to generate 3D worlds from a single input image.

Katja Schwarz

13,970 views • 1 year ago

From multiple consistent objects within a single image to fully recreated 3D objects in Blender. 100% AI-generated. Workflow detailed below 👇
0:41

From multiple consistent objects within a single image to fully recreated 3D objects in Blender. 100% AI-generated. Workflow detailed below 👇

Emm | scenario.com

171,979 views • 1 year ago

Rodin Gen-2 API node, Rodin’s most powerful image-to-3D tool, is now live in ComfyUI! Turn any image into a 3D model with one click. It supports 4× Mesh Quality, T/A Pose, PBR textures, and Multiview to 3D model. 👇 Try it now in ComfyUI!
0:29

Rodin Gen-2 API node, Rodin’s most powerful image-to-3D tool, is now live in ComfyUI! Turn any image into a 3D model with one click. It supports 4× Mesh Quality, T/A Pose, PBR textures, and Multiview to 3D model. 👇 Try it now in ComfyUI!

ComfyUI

19,076 views • 10 months ago

I generated this 3D enviroment using a single image using "Marble" from World Labs. The new version can generate a mesh from the splat and is directly usable in Unreal Engine 5.7.
0:35

I generated this 3D enviroment using a single image using "Marble" from World Labs. The new version can generate a mesh from the splat and is directly usable in Unreal Engine 5.7.

Matt Workman

42,460 views • 9 months ago

"Blender MCP" vs. "Generative 3D" – The Showdown ⚔️ Side-by-side comparison of two generated buildings: ⬅️ The 1st one (left) was created using Blender MCP (powered by Claude 3.7). ➡️ The 2nd one (right) was generated with a generative 3D model (direct 2D-to-3D). Check out the differences below 👇
1:01

"Blender MCP" vs. "Generative 3D" – The Showdown ⚔️ Side-by-side comparison of two generated buildings: ⬅️ The 1st one (left) was created using Blender MCP (powered by Claude 3.7). ➡️ The 2nd one (right) was generated with a generative 3D model (direct 2D-to-3D). Check out the differences below 👇

Emm | scenario.com

265,859 views • 1 year ago

Convert your 2D designs into 3D animations in just a few minutes with AI. I'll show you how with this workflow!
0:26

Convert your 2D designs into 3D animations in just a few minutes with AI. I'll show you how with this workflow!

TechHalla

33,025 views • 2 years ago

Using ChatGPT 4o to create 3D assets for your video games is insane... With AI, in just a few minutes, you can have your models ready to go, all with a consistent style! I’ll walk you through all the details, prompts, and tools included! 🧵👇
0:48

Using ChatGPT 4o to create 3D assets for your video games is insane... With AI, in just a few minutes, you can have your models ready to go, all with a consistent style! I’ll walk you through all the details, prompts, and tools included! 🧵👇

TechHalla

586,615 views • 1 year ago

I prompted Omma to build a #threejs app with real dynamic lighting on a 3D mesh - generated from a single image, using Depth Anything v2 + Transformers from Hugging Face ⚡ Depth estimation in the browser 🫧 3D mesh from the depth map 💡 Dynamic lighting reacting to the geometry No manual code. Pure AI prompting. The future of 3D on the web feels wide open.
0:40

I prompted Omma to build a #threejs app with real dynamic lighting on a 3D mesh - generated from a single image, using Depth Anything v2 + Transformers from Hugging Face ⚡ Depth estimation in the browser 🫧 3D mesh from the depth map 💡 Dynamic lighting reacting to the geometry No manual code. Pure AI prompting. The future of 3D on the web feels wide open.

Joseph Azar

14,041 views • 3 months ago

Still experimenting with hand tracking 🖐️ using a webcam and the dear Carlo. The 3D model was generated from a single image in Omma AI Studio, and I remixed an Octopus demo to take advantage of the physics simulation. Building with AI these days is so much fun. Music also generated from the Studio (Fan Art) #threeJS
0:58

Still experimenting with hand tracking 🖐️ using a webcam and the dear Carlo. The 3D model was generated from a single image in Omma AI Studio, and I remixed an Octopus demo to take advantage of the physics simulation. Building with AI these days is so much fun. Music also generated from the Studio (Fan Art) #threeJS

Joseph Azar

74,357 views • 1 month ago

Adobe is entering the image-to-3D game! Their new method, LRM, can create high-fidelity 3D meshes from a single image in just 5 seconds 🔥 It's trained on 1 million objects and is able to generate objects from real-world images and generative AI models.
0:28

Adobe is entering the image-to-3D game! Their new method, LRM, can create high-fidelity 3D meshes from a single image in just 5 seconds 🔥 It's trained on 1 million objects and is able to generate objects from real-world images and generative AI models.

Dreaming Tulpa 🥓👑

270,942 views • 2 years ago

I’ve tried nearly every generative model since late 2022, and Tencent HY 2.5 (released today) is next level. Full 3D + rigging + animation together. Here’s the same lighthouse, generated on Scenario & modeled via Blender MCP a month ago… now recreated using Hunyuan3D 2.5. More amazing examples below 👇🧵
0:24

I’ve tried nearly every generative model since late 2022, and Tencent HY 2.5 (released today) is next level. Full 3D + rigging + animation together. Here’s the same lighthouse, generated on Scenario & modeled via Blender MCP a month ago… now recreated using Hunyuan3D 2.5. More amazing examples below 👇🧵

Emm | scenario.com

131,689 views • 1 year ago

Kling 3.0 has arrived! Up to 15 second videos. Multi-shots! Its a great model! I made this below with in a few minutes with just 1 ref image. Great work Kling AI
0:35

Kling 3.0 has arrived! Up to 15 second videos. Multi-shots! Its a great model! I made this below with in a few minutes with just 1 ref image. Great work Kling AI

OrctonAI

57,390 views • 6 months ago

All of these 3D objects were generated entirely via AI (each from a single image) and the results are reaching exceptional levels of detail and fidelity. • Voxel Resolution: 1536^3 • Texture Resolution: 4096*4096 Pretty incredible stuff.
0:55

All of these 3D objects were generated entirely via AI (each from a single image) and the results are reaching exceptional levels of detail and fidelity. • Voxel Resolution: 1536^3 • Texture Resolution: 4096*4096 Pretty incredible stuff.

Emm | scenario.com

159,060 views • 1 year ago

📢📢 𝐀𝐯𝐚𝐭𝟑𝐫 📢📢 Avat3r creates high-quality 3D head avatars from just a few input images in a single forward pass with a new dynamic 3DGS reconstruction model. Video: Project: Our core idea is to make Gaussian Reconstruction Models animatable. We find that a simple cross-attention to an expression code sequence is already sufficient to model complex facial expressions. We then incorporate position maps from DUSt3R and feature maps from Sapiens to facilitate the prediction task. While DUSt3R's position maps act as a pixel-aligned initialization for the Gaussians' positions, the Sapiens feature maps help the cross-view transformer to match corresponding image tokens in the 4 input images. One major challenge in creating a 3D head avatar from smartphone images comes from inconsistent facial expressions when the subject could not remain perfectly static during the capture. We eliminate this static requirement by simply showing our model input images with different facial expressions during training. This technique makes our model robust to inconsistent input images later on. Finally, we show that despite the model has been trained with 4 input images, one can even create a 3D head avatar when only a single image is available. To achieve this, we employ a pre-trained 3D GAN to lift the single image to 3D and then render the 4 input images for our model. This allows us to create 3D head avatars from single images and even highly out-of-distribution examples like AI generated faces, paintings or statues. Great work by Tobias Kirschstein from his internship at Meta with Javier Romero, Artem Sevastopolsky, and Shunsuke Saito
0:38

📢📢 𝐀𝐯𝐚𝐭𝟑𝐫 📢📢 Avat3r creates high-quality 3D head avatars from just a few input images in a single forward pass with a new dynamic 3DGS reconstruction model. Video: Project: Our core idea is to make Gaussian Reconstruction Models animatable. We find that a simple cross-attention to an expression code sequence is already sufficient to model complex facial expressions. We then incorporate position maps from DUSt3R and feature maps from Sapiens to facilitate the prediction task. While DUSt3R's position maps act as a pixel-aligned initialization for the Gaussians' positions, the Sapiens feature maps help the cross-view transformer to match corresponding image tokens in the 4 input images. One major challenge in creating a 3D head avatar from smartphone images comes from inconsistent facial expressions when the subject could not remain perfectly static during the capture. We eliminate this static requirement by simply showing our model input images with different facial expressions during training. This technique makes our model robust to inconsistent input images later on. Finally, we show that despite the model has been trained with 4 input images, one can even create a 3D head avatar when only a single image is available. To achieve this, we employ a pre-trained 3D GAN to lift the single image to 3D and then render the 4 input images for our model. This allows us to create 3D head avatars from single images and even highly out-of-distribution examples like AI generated faces, paintings or statues. Great work by Tobias Kirschstein from his internship at Meta with Javier Romero, Artem Sevastopolsky, and Shunsuke Saito

Matthias Niessner

74,763 views • 1 year ago

ByteDance and Carnegie Mellon researchers just announced PartCrafter This AI turns a single photo into fully editable 3D parts in seconds 10 wild examples:
0:28

ByteDance and Carnegie Mellon researchers just announced PartCrafter This AI turns a single photo into fully editable 3D parts in seconds 10 wild examples:

Min Choi

962,966 views • 1 year ago

Current 3D generative models are slow and low quality. We present GRM, a large-scale model that reconstructs 3D Gaussians in 0.1s and generates high-quality 3D assets from text or single images in a few seconds. Demo: 1/4
0:37

Current 3D generative models are slow and low quality. We present GRM, a large-scale model that reconstructs 3D Gaussians in 0.1s and generates high-quality 3D assets from text or single images in a few seconds. Demo: 1/4

Gordon Wetzstein

19,227 views • 2 years ago

Can generative AI imagine what Alice saw in her journey in the Wonderland 🏞️🚶‍♀️? Introducing WonderJourney: Create a journey (a long sequence of diverse yet connected 3D scenes) from a single image or text! 🧵1/N Web: arxiv:
1:36

Can generative AI imagine what Alice saw in her journey in the Wonderland 🏞️🚶‍♀️? Introducing WonderJourney: Create a journey (a long sequence of diverse yet connected 3D scenes) from a single image or text! 🧵1/N Web: arxiv:

Hong-Xing (Koven) Yu

109,099 views • 2 years ago