Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Vibe creating a 3D scene in Blender got even easier. Just provide a 2D reference image — LLM deconstructs the scene, figures out what 3D assets are needed, generates them using Tripo, and arranges them to match your reference image. Pretty darn cool!

Bilawal Sidhu

106,892 subscribers

112,498 views • 1 year ago •via X (Twitter)

Education Science & Technology Arts

Anya Rossi• Live Now

Private livecam show

11 Comments

Bilawal Sidhu1 year ago

Simple prompts yet retain fine grain 3D control. This example by Sun blew my mind: “Use Tripo to help me create a cartoon-stylized scene in Blender, where a cute chibi witch is having afternoon tea with an orc. The models need to be exquisite and feature stylized materials."

Movipods1 year ago

if you're an aspiring (or established) filmmaker looking to package your next project effectively...Let's connect.

George Crudo1 year ago

sooooo where is the 2D reference image that was used here? lol

siddharth ahuja1 year ago

Similar functionality in the Blender MCP too:

Bilawal Sidhu1 year ago

Very cool!

Tristan Rhodes1 year ago

I keep getting my mind blown today. Tomorrow this will be “normal”.

Bilawal Sidhu1 year ago

Agreed. As the VLMs get better at spatial reasoning this capability will only get more robust.

io.net1 year ago

Very cool new feature. Thanks for sharing

kfant1 year ago

so where is the repo, or do i have to VIBE code it myself?

Bilawal Sidhu1 year ago

Tripo MCP:

YUKITO1 year ago

Have you seen the latest Blender update? An LLM is now your 3D artist—deconstructing scenes, generating assets with Tripo, and matching your reference image perfectly. Pretty neat, right?

Related Videos

Image to 3D, now in ANY pose! 🤸‍♂️ Simply upload your image + a pose reference photo. Meshy generates the model to match it perfectly. No complex rigging needed. Create 3D characters your way.

Image to 3D, now in ANY pose! 🤸‍♂️ Simply upload your image + a pose reference photo. Meshy generates the model to match it perfectly. No complex rigging needed. Create 3D characters your way.

MeshyAI

103,295 views • 5 months ago

Claude + Tripo + Blender. Anthropic Type a prompt. Claude runs the flow through MCP. Tripo generates the model. Then Blender drops it straight into your scene. No importing. No manual steps. Just prompt → model → scene. Pretty wild workflow for 3D creators 👇 #ai3d #Claude #ai3dmodelgenerator #Tripo

Claude + Tripo + Blender. Anthropic Type a prompt. Claude runs the flow through MCP. Tripo generates the model. Then Blender drops it straight into your scene. No importing. No manual steps. Just prompt → model → scene. Pretty wild workflow for 3D creators 👇 #ai3d #Claude #ai3dmodelgenerator #Tripo

Tripo

22,741 views • 2 months ago

You can now generate, edit, and convert a reference image into 3D inside one tool. Tripo's Image Generation runs Nano Banana and GPT to build the reference, then turns it into a model. Text or photo in, 3D out. One pipeline, zero handoffs.

You can now generate, edit, and convert a reference image into 3D inside one tool. Tripo's Image Generation runs Nano Banana and GPT to build the reference, then turns it into a model. Text or photo in, 3D out. One pipeline, zero handoffs.

Alvaro Cintas

56,191 views • 1 month ago

Combine a single character reference image with any location reference image to place your character in that scene. Prompt for new camera angles, compositions, character styling and more. (2/4)

Combine a single character reference image with any location reference image to place your character in that scene. Prompt for new camera angles, compositions, character styling and more. (2/4)

Runway

31,852 views • 1 year ago

Using 3D assets with Gen-4 References is a simple way to bring highly detailed and specific models into your generative workflows for even more consistency and control. To do so, simply provide a location plate, a quick comp of your 3D model in that space and a style reference.

Using 3D assets with Gen-4 References is a simple way to bring highly detailed and specific models into your generative workflows for even more consistency and control. To do so, simply provide a location plate, a quick comp of your 3D model in that space and a style reference.

Runway

119,208 views • 1 year ago

wow.. text to 3D would AI is here you can generate 3D assets using text/image and build up a 3D world.. and even auto rig characters. link in comment

wow.. text to 3D would AI is here you can generate 3D assets using text/image and build up a 3D world.. and even auto rig characters. link in comment

el.cine

212,681 views • 1 year ago

The challenge of creating this scene was from a 3D environment to a 2D painted environment. We used the character to bait-and-switch out the backgrounds. #2d #3d #animation

The challenge of creating this scene was from a 3D environment to a 2D painted environment. We used the character to bait-and-switch out the backgrounds. #2d #3d #animation

THE LINE

696,584 views • 3 years ago

When creating ingredient images, try to create stylistically consistent images. If you use input images that are too disparate, the output may lead to a cut scene. For example, when generating a reference image, try using a prompt like: “Create the next scene in this storyboard, now show a roadside diner with the same look and feel as the original image.”

When creating ingredient images, try to create stylistically consistent images. If you use input images that are too disparate, the output may lead to a cut scene. For example, when generating a reference image, try using a prompt like: “Create the next scene in this storyboard, now show a roadside diner with the same look and feel as the original image.”

Google AI

23,526 views • 9 months ago

📢WorldAgents: 3D worlds only from 2D image models - without any training! We propose an agentic approach with a Director (VLM) to plan the scene, a Generator (Flux or NanoBanana) for new views, and a Verifier (VLM) for selection / 3D consistency. -> High-fidelity 3D worlds from a single text prompt. What's remarkable: our agents find consistent views from 2D image models to obtain 3D-consistent worlds; this shows that image models contain world priors - agents just need to find them! Great work by Ziya Erkoç Angela Dai

📢WorldAgents: 3D worlds only from 2D image models - without any training! We propose an agentic approach with a Director (VLM) to plan the scene, a Generator (Flux or NanoBanana) for new views, and a Verifier (VLM) for selection / 3D consistency. -> High-fidelity 3D worlds from a single text prompt. What's remarkable: our agents find consistent views from 2D image models to obtain 3D-consistent worlds; this shows that image models contain world priors - agents just need to find them! Great work by Ziya Erkoç Angela Dai

Matthias Niessner

18,976 views • 3 months ago

I recreated the #ArcaneSeason2 Piltover Garden scene using #Blender. I roughly built a 3D scene, made a draft render, and then painted over it in 2D. All moving parts like foliage, characters and spinner are 3D elements. Breakdown coming soon. More info:

I recreated the #ArcaneSeason2 Piltover Garden scene using #Blender. I roughly built a 3D scene, made a draft render, and then painted over it in 2D. All moving parts like foliage, characters and spinner are 3D elements. Breakdown coming soon. More info:

trungduyng

34,849 views • 1 year ago

This AI agent turns an image into a 3D scene in Blender, which you can edit further. Free & open source. Check out the demo!

This AI agent turns an image into a 3D scene in Blender, which you can edit further. Free & open source. Check out the demo!

⚡AI Search⚡

15,058 views • 5 months ago

LLaVA-3D A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness Recent advancements in Large Multimodal Models (LMMs) have greatly enhanced their proficiency in 2D visual understanding tasks, enabling them to effectively process and understand images and videos. However, the development of LMMs with 3D-awareness for 3D scene understanding has been hindered by the lack of large-scale 3D vision-language datasets and powerful 3D encoders. In this paper, we introduce a simple yet effective framework called LLaVA-3D. Leveraging the strong 2D understanding priors from LLaVA, our LLaVA-3D efficiently adapts LLaVA for 3D scene understanding without compromising 2D understanding capabilities. To achieve this, we employ a simple yet effective representation, 3D Patch, which connects 2D CLIP patch features with their corresponding positions in 3D space. By integrating the 3D Patches into 2D LMMs and employing joint 2D and 3D vision-language instruction tuning, we establish a unified architecture for both 2D image understanding and 3D scene understanding. Experimental results show that LLaVA-3D converges 3.5x faster than existing 3D LMMs when trained on 3D vision-language datasets. Moreover, LLaVA-3D not only achieves state-of-the-art performance across various 3D tasks but also maintains comparable 2D image understanding and vision-language conversation capabilities with LLaVA.

LLaVA-3D A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness Recent advancements in Large Multimodal Models (LMMs) have greatly enhanced their proficiency in 2D visual understanding tasks, enabling them to effectively process and understand images and videos. However, the development of LMMs with 3D-awareness for 3D scene understanding has been hindered by the lack of large-scale 3D vision-language datasets and powerful 3D encoders. In this paper, we introduce a simple yet effective framework called LLaVA-3D. Leveraging the strong 2D understanding priors from LLaVA, our LLaVA-3D efficiently adapts LLaVA for 3D scene understanding without compromising 2D understanding capabilities. To achieve this, we employ a simple yet effective representation, 3D Patch, which connects 2D CLIP patch features with their corresponding positions in 3D space. By integrating the 3D Patches into 2D LMMs and employing joint 2D and 3D vision-language instruction tuning, we establish a unified architecture for both 2D image understanding and 3D scene understanding. Experimental results show that LLaVA-3D converges 3.5x faster than existing 3D LMMs when trained on 3D vision-language datasets. Moreover, LLaVA-3D not only achieves state-of-the-art performance across various 3D tasks but also maintains comparable 2D image understanding and vision-language conversation capabilities with LLaVA.

AK

41,736 views • 1 year ago

So randomly, I got a "Image to 3D Model using AI" AD, and I decided to test it with the best guy possible. Its CURSED💀! but not that bad for only 1 reference. I wanna hear your opinion! what do you think?🤔

So randomly, I got a "Image to 3D Model using AI" AD, and I decided to test it with the best guy possible. Its CURSED💀! but not that bad for only 1 reference. I wanna hear your opinion! what do you think?🤔

Games Production (COMMISSIONS OPEN!)

33,948 views • 1 year ago

Creating a consistent scene and character. Seedream is able to edit camera angles from a single reference image. This gives you more control over your video outputs with start and end frames.

Creating a consistent scene and character. Seedream is able to edit camera angles from a single reference image. This gives you more control over your video outputs with start and end frames.

Jerrod Lew

30,665 views • 10 months ago

Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors paper page: present Magic123, a two-stage coarse-to-fine approach for high-quality, textured 3D meshes generation from a single unposed image in the wild using both2D and 3D priors. In the first stage, we optimize a neural radiance field to produce a coarse geometry. In the second stage, we adopt a memory-efficient differentiable mesh representation to yield a high-resolution mesh with a visually appealing texture. In both stages, the 3D content is learned through reference view supervision and novel views guided by a combination of 2D and 3D diffusion priors. We introduce a single trade-off parameter between the 2D and 3D priors to control exploration (more imaginative) and exploitation (more precise) of the generated geometry. Additionally, we employ textual inversion and monocular depth regularization to encourage consistent appearances across views and to prevent degenerate solutions, respectively. Magic123 demonstrates a significant improvement over previous image-to-3D techniques, as validated through extensive experiments on synthetic benchmarks and diverse real-world images.

Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors paper page: present Magic123, a two-stage coarse-to-fine approach for high-quality, textured 3D meshes generation from a single unposed image in the wild using both2D and 3D priors. In the first stage, we optimize a neural radiance field to produce a coarse geometry. In the second stage, we adopt a memory-efficient differentiable mesh representation to yield a high-resolution mesh with a visually appealing texture. In both stages, the 3D content is learned through reference view supervision and novel views guided by a combination of 2D and 3D diffusion priors. We introduce a single trade-off parameter between the 2D and 3D priors to control exploration (more imaginative) and exploitation (more precise) of the generated geometry. Additionally, we employ textual inversion and monocular depth regularization to encourage consistent appearances across views and to prevent degenerate solutions, respectively. Magic123 demonstrates a significant improvement over previous image-to-3D techniques, as validated through extensive experiments on synthetic benchmarks and diverse real-world images.

AK

305,643 views • 3 years ago

Reve just launched and the early results are 🤯 🎨 Spatially intelligent generation, create multi-image layouts in one shot 🖌️ Reference images to craft the perfect scene 🎭️ State of the art image editing capabilities

Reve just launched and the early results are 🤯 🎨 Spatially intelligent generation, create multi-image layouts in one shot 🖌️ Reference images to craft the perfect scene 🎭️ State of the art image editing capabilities

fal

31,292 views • 9 months ago

Introducing Wonder 3D, a new generative AI model in Flow Studio for fast and detailed 3D asset creation. 💬 Text to 3D — Watch your words take shape. Turn a simple prompt into fully textured 3D characters and props. 📸 Image to 3D — Add depth to your visuals. Transform concept art or reference images into dimensional 3D models. 🖼️ Text to Image — Visualize ideas early. Turn descriptions into concept imagery before converting them into 3D. Built for endless storytelling. Give your imagination some dimension. Available in all tiers. Find it under Wonder Tools. 👉 Get started: 💡 Learn more:

Introducing Wonder 3D, a new generative AI model in Flow Studio for fast and detailed 3D asset creation. 💬 Text to 3D — Watch your words take shape. Turn a simple prompt into fully textured 3D characters and props. 📸 Image to 3D — Add depth to your visuals. Transform concept art or reference images into dimensional 3D models. 🖼️ Text to Image — Visualize ideas early. Turn descriptions into concept imagery before converting them into 3D. Built for endless storytelling. Give your imagination some dimension. Available in all tiers. Find it under Wonder Tools. 👉 Get started: 💡 Learn more:

Autodesk Flow Studio

107,724 views • 4 months ago

🌟Transform an image into a 3D model in just 5 easy steps! 1️⃣Visit the Hunyuan 3D website and log in: 2️⃣Navigate to the "3D Creation" page 3️⃣Choose the "Image to 3D" feature 🎨 4️⃣Upload your image and click "Generate Immediately" 5️⃣Wait a moment , and voilà—your stunning 3D model is ready! ⏳✨ Watch our tutorial video to get started! 😸🎥

🌟Transform an image into a 3D model in just 5 easy steps! 1️⃣Visit the Hunyuan 3D website and log in: 2️⃣Navigate to the "3D Creation" page 3️⃣Choose the "Image to 3D" feature 🎨 4️⃣Upload your image and click "Generate Immediately" 5️⃣Wait a moment , and voilà—your stunning 3D model is ready! ⏳✨ Watch our tutorial video to get started! 😸🎥

Hunyuan

101,468 views • 1 year ago

Check out CAT3D! Image(s)-to-3D in 1 minute! Given any number of real or generated images, CAT3D uses a multi-view diffusion prior to create consistent novel views. These views are used to reconstruct a 3D scene using NeRF/3DGS.

Check out CAT3D! Image(s)-to-3D in 1 minute! Given any number of real or generated images, CAT3D uses a multi-view diffusion prior to create consistent novel views. These views are used to reconstruct a 3D scene using NeRF/3DGS.

Philipp Henzler

12,737 views • 2 years ago