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.

I dramatically shifted my stream's perspective from 2D to 3D. Chat thought we were starting the stream in our standard 2D overlay, until I zoomed out to reveal my new 3D vtuber model.

shindigs

52,897 subscribers

89,867 views • 1 year ago •via X (Twitter)

Comedy Arts Gaming

Anya Rossi• Live Now

Private livecam show

11 Comments

shindigs1 year ago

3D model by @stupah

shindigs1 year ago

Concept art by @imcertly

shindigs1 year ago

@imcertly stream bg by @feya_kun

Study Bunny Games2 years ago

Learn Japanese through "mild immersion" in a game Like this? Repost and follow us!

Mei 💝🦊1 year ago

So freaking cool. 3D is so fun so much you can do.

Jets 🔗 Vershion1 year ago

Dude hell yeah!!!

Tom Farro 💀🤌 Skeletom1 year ago

Great stream! Our cat, Olivia, really enjoyed the spinning fish. The rest was pretty neat, too.

🏁 Ashton Marten | アシュトン♥マーチン 🍒1 year ago

IM SO SAD I DIDNT GET TO SEE THIS LIVE

pekoe 🌱🌧 vtuber1 year ago

THIS WAS SO COOL I WAS SO GLAD I WAS ABLE TO CATCH IT LIVE!!!!!!

Skab1 year ago

Huh, can't help but notice you didn't include the part where you break it down like rent is due, very curious Shin

Rogueshadow671 year ago

And then...he did the dance #17

Related Videos

I showed chat a sneak peak of my 2.0 VTuber model today... this 3D gremlin is going back to 2D and getting TALLER!!! watch out!!!!!!

I showed chat a sneak peak of my 2.0 VTuber model today... this 3D gremlin is going back to 2D and getting TALLER!!! watch out!!!!!!

Bella Pawesborne 🐾💛

12,772 views • 2 months ago

Starting with a 3D model? Bad idea right 🤔 ⁺˚*•̩̩͙✩•̩̩͙*˚⁺‧͙⁺˚*•̩̩͙✩•̩̩͙*˚⁺‧͙⁺˚*•̩̩͙✩•̩̩͙*˚⁺‧͙⁺˚*•̩̩͙✩•̩̩͙*˚⁺‧͙⁺˚*•̩̩͙✩•̩̩͙*˚⁺‧͙ I made this to reveal my model on TikTok and thought I'd post it here as well c: (link on my carrd) I have my reasons for choosing 3D over 2D but I'd like to save that story for my debut ^^

Starting with a 3D model? Bad idea right 🤔 ⁺˚•̩̩͙✩•̩̩͙˚⁺‧͙⁺˚•̩̩͙✩•̩̩͙˚⁺‧͙⁺˚•̩̩͙✩•̩̩͙˚⁺‧͙⁺˚•̩̩͙✩•̩̩͙˚⁺‧͙⁺˚•̩̩͙✩•̩̩͙˚⁺‧͙ I made this to reveal my model on TikTok and thought I'd post it here as well c: (link on my carrd) I have my reasons for choosing 3D over 2D but I'd like to save that story for my debut ^^

Bijou Vos 💎 Diamond Fox ⟡ comms soon!

140,532 views • 2 years ago

🥳 NEW TUTORIAL 🥳 2D look is making a big come back and I love it! In this video I give you my tips to achieve convincing 2D look for your 3D animation using #Blender obviously 🤗 👉 #b3D #animation #p2dessign #2D #3D #anime

🥳 NEW TUTORIAL 🥳 2D look is making a big come back and I love it! In this video I give you my tips to achieve convincing 2D look for your 3D animation using #Blender obviously 🤗 👉 #b3D #animation #p2dessign #2D #3D #anime

Pierrick Picaut

71,568 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

i bought a iphone just to add tracking to my model 💀 2d live pixel texture face on a 3d body made in the #GodotEngine

i bought a iphone just to add tracking to my model 💀 2d live pixel texture face on a 3d body made in the #GodotEngine

byte 🕹️ nme64 | DEBUT: TBA

50,954 views • 2 years ago

I did something cool today during a Picarto drawing stream. I had both my 3d AND my 2D vtuber avatars running at the same time. The result was rally cute.🐰🐰

I did something cool today during a Picarto drawing stream. I had both my 3d AND my 2D vtuber avatars running at the same time. The result was rally cute.🐰🐰

𝕋𝕙𝕖 𝔽𝕠𝕣𝕘𝕖 ☠

18,145 views • 2 years ago

My game's weirdest feature explained in 5 words or less - Change from 3D to 2D

My game's weirdest feature explained in 5 words or less - Change from 3D to 2D

Horizonite

348,997 views • 7 months ago

My stream's animation budget got cut, so I had to remake my stream purely as a storyboard. We were able to afford higher animation quality due to the support from chat.

My stream's animation budget got cut, so I had to remake my stream purely as a storyboard. We were able to afford higher animation quality due to the support from chat.

shindigs

41,146 views • 1 month ago

One thing I really envy about 2D vtubers is how their models sway so beautifully! :D So, like a normal person, I built my own system to replicate a similar effect for our 3D customizable vtuber model!💜 It looks kind of uncanny to see a 3D model moving like a Live2D one hehe✨

One thing I really envy about 2D vtubers is how their models sway so beautifully! :D So, like a normal person, I built my own system to replicate a similar effect for our 3D customizable vtuber model!💜 It looks kind of uncanny to see a 3D model moving like a Live2D one hehe✨

Pastell & Palette🤍 3D Customizable Model!

35,144 views • 24 days ago

Polishing my shader to auto-convert 2D images to 3D (Texture + 3D entirely created from scratch in 5 minutes) #Midjourney #AIart #AIイラスト #gamedev #StableDiffussion

Polishing my shader to auto-convert 2D images to 3D (Texture + 3D entirely created from scratch in 5 minutes) #Midjourney #AIart #AIイラスト #gamedev #StableDiffussion

Cristian Peñas ░░░░░░░░

469,546 views • 3 years ago

I made a stream overlay that lets Twitch chat draw my new vtuber into existence. Each time they tap a section on the screen, they sketch out more of the vtuber. After being fully colored, the model pops out of the paper and comes to life.

I made a stream overlay that lets Twitch chat draw my new vtuber into existence. Each time they tap a section on the screen, they sketch out more of the vtuber. After being fully colored, the model pops out of the paper and comes to life.

shindigs

612,726 views • 2 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

41,729 views • 1 year ago

My submission for #SCA26 ! Wanted to 3D model instead of 2D art for this special occasion :0 #SkyVisualArts #thatskygame

My submission for #SCA26 ! Wanted to 3D model instead of 2D art for this special occasion :0 #SkyVisualArts #thatskygame

Deltabyss

11,740 views • 3 months ago

3D VRChat Model showcase for 𝐃𝐞𝐥𝐢𝑅𝑖𝑛 🪢🩷 ✨ I loved bringing this model to life! The design is stunning 😍💙 Huge credit to: 🎨 Original design by Nix Byakko ⏾ 🖌️ 2D Model Art by miiikaccino ✧˖° #Vtuber #b3d

3D VRChat Model showcase for 𝐃𝐞𝐥𝐢𝑅𝑖𝑛 🪢🩷 ✨ I loved bringing this model to life! The design is stunning 😍💙 Huge credit to: 🎨 Original design by Nix Byakko ⏾ 🖌️ 2D Model Art by miiikaccino ✧˖° #Vtuber #b3d

QuantumL34p

12,741 views • 4 months ago

Excited to announce our new preprint! We developed a method to automatically extract standard 2D views from 3D echocardiography volumes. This method allows for novel approach to echo acquisition: Instead of moving the probe across patients chest in the search of standard views, a sonographer would only have to place the probe in the apical position to capture the whole snapshot of the heart, which is then decomposed into all standard views with the similar quality to the views obtained in the traditional pipeline. That way we benefit from the speed of 3D acquisition while allowing clinicians to preserve their familiar 2D interpretation workflow.

Excited to announce our new preprint! We developed a method to automatically extract standard 2D views from 3D echocardiography volumes. This method allows for novel approach to echo acquisition: Instead of moving the probe across patients chest in the search of standard views, a sonographer would only have to place the probe in the apical position to capture the whole snapshot of the heart, which is then decomposed into all standard views with the similar quality to the views obtained in the traditional pipeline. That way we benefit from the speed of 3D acquisition while allowing clinicians to preserve their familiar 2D interpretation workflow.

Milos Vukadinovic

11,193 views • 4 months ago

I want to do my absolute best to provide something similar to a live2D customizable model but for 3D!🩷 2D models are so amazing. They have so many clothing sliders, and now, 3D can too!✨Now, our clothes can have even more customization possibilities! -^u^-

I want to do my absolute best to provide something similar to a live2D customizable model but for 3D!🩷 2D models are so amazing. They have so many clothing sliders, and now, 3D can too!✨Now, our clothes can have even more customization possibilities! -^u^-

Pastell & Palette🤍 3D Customizable Model!

27,584 views • 4 months ago

Proud to share the original 3D model I created for HalO!🫶 #3D #3DCG #Vtuber #버튜버

Proud to share the original 3D model I created for HalO!🫶 #3D #3DCG #Vtuber #버튜버

DDDako🐙3D Modeler

46,873 views • 1 year ago

Bring the 2d timing chart to 3d!! I finally recorded a demo of this addon, available on my gumroad page :) Thanks for your support 🙏

Bring the 2d timing chart to 3d!! I finally recorded a demo of this addon, available on my gumroad page :) Thanks for your support 🙏

Dedouze 🧢 Andry

73,077 views • 10 months ago

Day 33 of vibe coding a game+engine using Cursor So I approached character animation from a different perspective this time. Instead of 3D -> 2D I went for native 2D via image to video method. This gives us much richer animations that the limited ones we get with 3D! Eliza is really cute with these! The downside is the time it takes to get them all done, even with Cursor skills/automation. Which ones did you like more? Check the previous posts for the 3D ones!

Day 33 of vibe coding a game+engine using Cursor So I approached character animation from a different perspective this time. Instead of 3D -> 2D I went for native 2D via image to video method. This gives us much richer animations that the limited ones we get with 3D! Eliza is really cute with these! The downside is the time it takes to get them all done, even with Cursor skills/automation. Which ones did you like more? Check the previous posts for the 3D ones!

Startracker 🔺

33,327 views • 5 months ago

✨Introducing Neuralangelo✨ A new #AI model to turn 2D video from any device -- cell phone to drone capture -- into 3D structures with intricate details. New from #NVIDIAResearch #CVPR2023 Read more:

✨Introducing Neuralangelo✨ A new #AI model to turn 2D video from any device -- cell phone to drone capture -- into 3D structures with intricate details. New from #NVIDIAResearch #CVPR2023 Read more:

NVIDIA AI Developer

497,945 views • 3 years ago