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.

2D or 3D ? It’s wild to be able to create such precise 3D models with a 2D visual using Tripo or Meshy. They aren’t 100% perfect, but I’m going to refine them in Blender with the help of Claude.

Anima

20,620 subscribers

26,466 views • 5 days ago •via X (Twitter)

Arts Science & Technology

Anya Rossi• Live Now

Private livecam show

14 Comments

Bombard5 days ago

it's incredible! Once the agent can slice a model as well it will be from your mind to the physical world with the push of a button.

Torean “_TrojanMorse” Joel5 days ago

Have you used Meshy more or less often than Tripo? Been looking at it along with Hi3D. I noticed the auto rigging seems to be good on Tripo from testing. The blender shout is a good one as I have been setting up the system at home and got some good result. I have opted to use it for static models as well and iterate cleanup with it and it works well with the workflow of mind.

Frank Houbre5 days ago

Hey 👋 are you rigging the cleaned-up models in Blender to animate them, or using them as staging references for the video pass? Having Claude help with the Blender cleanup is a fun twist on the Tripo and Meshy route.

ChaseInTech4 days ago

Really cool art style

pens4 days ago

Ahh more vending machine art !✨

Andy Garcia4 days ago

Love it

vikas5 days ago

try making iti n parts do this use tripo smart mesh then segment it use triangle topology at gen then take the different parts apart take shot of them from different angles use gpt to fix the flaws then gen seperate and then combine them back to the original

Rodion Kazennov | Nefayran5 days ago

If refining means cutting faces: a limited dissolve keeps each surviving vertex's UV and interpolates the rest, so on my textured mesh the painted edges slid inside every merged region. Sampling the original's texture onto the reduced mesh by nearest point fixed it.

TBK Joshua4 days ago

Thank god! Finally a post that isn't pretending Kimi did ALL the work. 💀 These 3D model AI models need to be supported and advertised as well! Thank you for not being another kimi shill, as much as I like kimi I know they aren't here yet no matter how much they pretend to be.

K.4 days ago

what do u fix wich blender on this character for exemple ?

luuztuuth5 days ago

Very impressive.

iwwon5 days ago

Tripo is better I believe. Wdyt ?

Zerefs cosmos4 days ago

I like the 3d but the 2D just gives me like please make a manga vibe out of this

MASA5 days ago

2D carries way more weight. How messy did the topology turn out around the claw?

Related Videos

What if your AI character could move beyond the screen? Create unique characters with SeaArt. Transform them into high-detail 3D models with Tripo. From 2D imagination to 3D creation, bring your characters closer to life. SeaArt × Tripo Create beyond the screen.

What if your AI character could move beyond the screen? Create unique characters with SeaArt. Transform them into high-detail 3D models with Tripo. From 2D imagination to 3D creation, bring your characters closer to life. SeaArt × Tripo Create beyond the screen.

SeaArt.Ai🐋

43,734 views • 3 months ago

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!

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

112,498 views • 1 year ago

Combining 2D and 3D in After Effects. In Foldspace, not every surface needs to be bent. Keep one flat for 2D artwork, and let the others exist in 3D space. This allows you to combine 2D and 3D objects in a single animation with no masks or tricks needed.

Combining 2D and 3D in After Effects. In Foldspace, not every surface needs to be bent. Keep one flat for 2D artwork, and let the others exist in 3D space. This allows you to combine 2D and 3D objects in a single animation with no masks or tricks needed.

Motion Princess

22,007 views • 7 months ago

This was way too easy... I created a cute 3D character in minutes instead of hours using this combo: Unbound + Tripo I’m not a 3D artist, but this made the whole process feel simple, playful, and actually accessible. Unbound helped me shape the character idea, then Tripo turned it into a 3D model without the usual complicated workflow If you are a 3D artist or you are just starting, try Unbound. It’s free, open for everyone to experiment with, and a fun way to create characters, creatures, and 3D models without feeling overwhelmed I had so much fun using it today, and I think many visual creators are going to love it. Link in the first comment 👇🏻

This was way too easy... I created a cute 3D character in minutes instead of hours using this combo: Unbound + Tripo I’m not a 3D artist, but this made the whole process feel simple, playful, and actually accessible. Unbound helped me shape the character idea, then Tripo turned it into a 3D model without the usual complicated workflow If you are a 3D artist or you are just starting, try Unbound. It’s free, open for everyone to experiment with, and a fun way to create characters, creatures, and 3D models without feeling overwhelmed I had so much fun using it today, and I think many visual creators are going to love it. Link in the first comment 👇🏻

Amira Zairi

186,621 views • 6 months ago

I made a cute 3D wizard in minutes... for free The combo was simple: Unbound + Tripo. Unbound helped me shape the character idea, then Tripo turned it into a 3D model without the usual heavy workflow. The whole process felt fast, playful, and easy to experiment with If you’re a 3D artist, a visual creator, or just starting to explore 3D, try Unbound while it’s still free for a limited time. You can use it to create characters, creatures, and 3D models without feeling overwhelmed I'm sure many visual creators are going to love this Link in the first comment 👇🏻

I made a cute 3D wizard in minutes... for free The combo was simple: Unbound + Tripo. Unbound helped me shape the character idea, then Tripo turned it into a 3D model without the usual heavy workflow. The whole process felt fast, playful, and easy to experiment with If you’re a 3D artist, a visual creator, or just starting to explore 3D, try Unbound while it’s still free for a limited time. You can use it to create characters, creatures, and 3D models without feeling overwhelmed I'm sure many visual creators are going to love this Link in the first comment 👇🏻

Amira Zairi

18,116 views • 6 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

41,747 views • 2 years ago

I got a lot of questions yesterday on how this made and if it was 3D or 2D so I decided to make a small breakdown video to explain. It was created using Non-Photorealistic Shaders and adapting a 2D animation workflow into 3D within Blender itself.

I got a lot of questions yesterday on how this made and if it was 3D or 2D so I decided to make a small breakdown video to explain. It was created using Non-Photorealistic Shaders and adapting a 2D animation workflow into 3D within Blender itself.

BNBaku

80,329 views • 2 years 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 👇

"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

279,116 views • 1 year ago

NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360° Views github:

NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360° Views github:

AK

142,744 views • 3 years ago

you can now use Krea with any 2D, 3D, animation, vector, or painting software in the world Photoshop, Blender, Figma...

you can now use Krea with any 2D, 3D, animation, vector, or painting software in the world Photoshop, Blender, Figma...

titus

262,702 views • 2 years ago

✨ Commissions OPEN for 3D Models ✨ ⚜️Create 3D models with rich detail and refined visual effects. ⚜️More info: ⚜️Looking forward to hearing from you❤ ✨Let’s bring your 2D characters to life in 3D✨ #3DCG #Commission #Vtuber #warudo #VGenOpen

✨ Commissions OPEN for 3D Models ✨ ⚜️Create 3D models with rich detail and refined visual effects. ⚜️More info: ⚜️Looking forward to hearing from you❤ ✨Let’s bring your 2D characters to life in 3D✨ #3DCG #Commission #Vtuber #warudo #VGenOpen

Blaird_COMMOPEN

16,985 views • 9 months ago

We just open-sourced 1,300+ 3D models. All 39 GB are free to download on Hugging Face. > made with Hitem3D, Meshy, Rodin, Tripo, Claude Opus 5.5 3D and GPT-6 Astra 3D, which all run on Scenario > includes the input images, prompts and settings that made them > GLBs up to 8K textures, native Blender files from Opus and Astra, CC BY 4.0

We just open-sourced 1,300+ 3D models. All 39 GB are free to download on Hugging Face. > made with Hitem3D, Meshy, Rodin, Tripo, Claude Opus 5.5 3D and GPT-6 Astra 3D, which all run on Scenario > includes the input images, prompts and settings that made them > GLBs up to 8K textures, native Blender files from Opus and Astra, CC BY 4.0

Emm | scenario.com

74,702 views • 5 days ago

Initially, I had Claude make this animation in 2D. It wrote the piano score and drew every frame in JavaScript. I gave this 2D version as reference to another Claude. Because the whole film was code, Claude was able to use its exact choreography and make the 3D one in Blender.

Initially, I had Claude make this animation in 2D. It wrote the piano score and drew every frame in JavaScript. I gave this 2D version as reference to another Claude. Because the whole film was code, Claude was able to use its exact choreography and make the 3D one in Blender.

Kevin Ngo

39,237 views • 20 days ago

Text-to-3D Generation with Bidirectional Diffusion using both 2D and 3D priors paper page: Most 3D generation research focuses on up-projecting 2D foundation models into the 3D space, either by minimizing 2D Score Distillation Sampling (SDS) loss or fine-tuning on multi-view datasets. Without explicit 3D priors, these methods often lead to geometric anomalies and multi-view inconsistency. Recently, researchers have attempted to improve the genuineness of 3D objects by directly training on 3D datasets, albeit at the cost of low-quality texture generation due to the limited texture diversity in 3D datasets. To harness the advantages of both approaches, we propose Bidirectional Diffusion(BiDiff), a unified framework that incorporates both a 3D and a 2D diffusion process, to preserve both 3D fidelity and 2D texture richness, respectively. Moreover, as a simple combination may yield inconsistent generation results, we further bridge them with novel bidirectional guidance. In addition, our method can be used as an initialization of optimization-based models to further improve the quality of 3D model and efficiency of optimization, reducing the generation process from 3.4 hours to 20 minutes. Experimental results have shown that our model achieves high-quality, diverse, and scalable 3D generation.

Text-to-3D Generation with Bidirectional Diffusion using both 2D and 3D priors paper page: Most 3D generation research focuses on up-projecting 2D foundation models into the 3D space, either by minimizing 2D Score Distillation Sampling (SDS) loss or fine-tuning on multi-view datasets. Without explicit 3D priors, these methods often lead to geometric anomalies and multi-view inconsistency. Recently, researchers have attempted to improve the genuineness of 3D objects by directly training on 3D datasets, albeit at the cost of low-quality texture generation due to the limited texture diversity in 3D datasets. To harness the advantages of both approaches, we propose Bidirectional Diffusion(BiDiff), a unified framework that incorporates both a 3D and a 2D diffusion process, to preserve both 3D fidelity and 2D texture richness, respectively. Moreover, as a simple combination may yield inconsistent generation results, we further bridge them with novel bidirectional guidance. In addition, our method can be used as an initialization of optimization-based models to further improve the quality of 3D model and efficiency of optimization, reducing the generation process from 3.4 hours to 20 minutes. Experimental results have shown that our model achieves high-quality, diverse, and scalable 3D generation.

AK

38,853 views • 2 years ago

Semantically annotating 3D gaussian splats on the fly using gemini 3.1 + sparkjs 1. Load any 3D scene and hit scan 2. Get 2D detections from VLM 3. Cluster outputs & project into 3D world space 4. Save as a persistent 3D semantic layer Inspired by Alexander Chen's experiments with gemini visual intelligence. Just had to try to lift it from 2D to 3D!

Semantically annotating 3D gaussian splats on the fly using gemini 3.1 + sparkjs 1. Load any 3D scene and hit scan 2. Get 2D detections from VLM 3. Cluster outputs & project into 3D world space 4. Save as a persistent 3D semantic layer Inspired by Alexander Chen's experiments with gemini visual intelligence. Just had to try to lift it from 2D to 3D!

Bilawal Sidhu

56,910 views • 5 months ago

From 2D to 3D to video with speech using the tools I have developed. So 100% local and open-source. LTX.io #b3d

From 2D to 3D to video with speech using the tools I have developed. So 100% local and open-source. LTX.io #b3d

tintwotin

11,179 views • 3 months ago

Using MeshyAI alongside Blender with Codex/Astra for 3D game creation is such an unlock for higher-fidelity characters (the models aren't great at procedurally creating characters in my experience) My workflow starts by generating high-res image refs (in t-pose and nothing else in background) of target characters in Codex/GPT Image 2 (or finding some online) The model then handles image-to-3d via Meshy REST API, as well as rigging + animating the models and integrating them into target game (the latter piece is where frontier models really stand out) I always have the agent create a local studio page so I can view and interact with the generated models! Tl;dr: Bowser T-pose image → 4 Blender reference images → Meshy image-to-3D → Blender cleanup (3M → 35K triangles) → Meshy auto-rigging → walk/run animations → interactive Three.js viewer

Using MeshyAI alongside Blender with Codex/Astra for 3D game creation is such an unlock for higher-fidelity characters (the models aren't great at procedurally creating characters in my experience) My workflow starts by generating high-res image refs (in t-pose and nothing else in background) of target characters in Codex/GPT Image 2 (or finding some online) The model then handles image-to-3d via Meshy REST API, as well as rigging + animating the models and integrating them into target game (the latter piece is where frontier models really stand out) I always have the agent create a local studio page so I can view and interact with the generated models! Tl;dr: Bowser T-pose image → 4 Blender reference images → Meshy image-to-3D → Blender cleanup (3M → 35K triangles) → Meshy auto-rigging → walk/run animations → interactive Three.js viewer

Rishi

69,345 views • 1 month ago

Transform your ideas into 3D with ease! 🎨✨ Tripo AI uses AI to help you create 3D models in no time. is this the future of 3d design? 🚀 Check it out: #Threejs #WebGL #AI

Transform your ideas into 3D with ease! 🎨✨ Tripo AI uses AI to help you create 3D models in no time. is this the future of 3d design? 🚀 Check it out: #Threejs #WebGL #AI

Three.js Resources

58,819 views • 1 year ago

Worked with incredible local life drawing models to populate our indie project Gesture VR Life Drawing with some fantastic new poses! Draw them in 2D or 3D in our virtual studio! Support us on Quest 2 here: or help us spread the word by RTing ♥️✏️

Worked with incredible local life drawing models to populate our indie project Gesture VR Life Drawing with some fantastic new poses! Draw them in 2D or 3D in our virtual studio! Support us on Quest 2 here: or help us spread the word by RTing ♥️✏️

Nick Ladd

14,039 views • 3 years ago

Running some more tests with Adobe’s new 3D model viewer, Gaussian Splatting generator, and AI image generator, 'Substance 3D Viewer.' It’s still in beta, but it’s already pretty awesome and very easy to use! 🔥 Check out what I was able to create. The models in this video were made with Tripo AI using text-to-3D, and the animations were brought to life using Hailuo and Luma Dream. This tech just keeps getting more useful! #AIArt #3DModeling #Substance3DViewer

Running some more tests with Adobe’s new 3D model viewer, Gaussian Splatting generator, and AI image generator, 'Substance 3D Viewer.' It’s still in beta, but it’s already pretty awesome and very easy to use! 🔥 Check out what I was able to create. The models in this video were made with Tripo AI using text-to-3D, and the animations were brought to life using Hailuo and Luma Dream. This tech just keeps getting more useful! #AIArt #3DModeling #Substance3DViewer

Martin Nebelong

87,635 views • 2 years ago