Loading video...

Video Failed to Load

Go Home

managed to drive the Flex Avatar GS models with my webcam, also computed custom avatars (created with FLUX KLEIN) and added a feature to compute a 3D avatar from the webcam and it makes me happy :) I'll try to add morph, shaders, WebGL renderer etc. but this is...

nicoptere's profile picture

Nicolas Barradeau

5,891 subscribers

11,505 views • 1 month ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Yesterday, I created to make it as easy as possible to create your custom avatar. Give it a try, and show me what you come up with.
0:59

Yesterday, I created to make it as easy as possible to create your custom avatar. Give it a try, and show me what you come up with.

Shayan

52,752 views • 3 years ago

Mirage just dropped Avatar X, a new model for AI avatars. It creates avatars that actually look, sound and react like you, with lifelike micro-expressions and body language. Avatar X shines on identity preservation for both vertical and horizontal video, capturing subtle expressions and naturally handling moments like laughing. And unlike other avatar models, the quality stays sharp and consistent from the first frame to the last. This is getting way too real. Try it here →
0:27

Mirage just dropped Avatar X, a new model for AI avatars. It creates avatars that actually look, sound and react like you, with lifelike micro-expressions and body language. Avatar X shines on identity preservation for both vertical and horizontal video, capturing subtle expressions and naturally handling moments like laughing. And unlike other avatar models, the quality stays sharp and consistent from the first frame to the last. This is getting way too real. Try it here →

Angry Tom

12,075 views • 18 days ago

It's notoriously harduous to add custom shading models to #UnrealEngine . I was fiddling with this approach to a stylized paint style yesterday night and quite happy with the progress so far. The textures are generated in Adobe Substance 3D #SubstanceDesigner
0:43

It's notoriously harduous to add custom shading models to #UnrealEngine . I was fiddling with this approach to a stylized paint style yesterday night and quite happy with the progress so far. The textures are generated in Adobe Substance 3D #SubstanceDesigner

Elbriga - making Ballistic.exe

78,906 views • 3 years ago

Yes, this works with any avatar. But it doesnt look correct with most avatars. Especially very tall or short ones. Even my avatar has a lot of clipping issues 😭 But yeah!! im working on getting the busted cutscene system to work with any R15 avatar!
1:57

Yes, this works with any avatar. But it doesnt look correct with most avatars. Especially very tall or short ones. Even my avatar has a lot of clipping issues 😭 But yeah!! im working on getting the busted cutscene system to work with any R15 avatar!

tabby 🔜 RDC26

19,714 views • 22 days ago

The Avatar Manager gets a major revamp! ✅ Check it out 🎨 Redesigned UI/UX for the whole avatar manager 📝 New avatar info such as collection name, rarity, TSB tier and size 🏆 Now you will see what avatars have perks enabled, such as earning extra rewards on events or unlocking access to exclusive experiences ➡️ Quick access to each avatar collection page in our marketplace 👾 20+ new free custom avatars added ⁉️ New “Randomize” button to get a fully randomized custom avatar 🔍 Improved filters and search options to easily find your avatar
1:05

The Avatar Manager gets a major revamp! ✅ Check it out 🎨 Redesigned UI/UX for the whole avatar manager 📝 New avatar info such as collection name, rarity, TSB tier and size 🏆 Now you will see what avatars have perks enabled, such as earning extra rewards on events or unlocking access to exclusive experiences ➡️ Quick access to each avatar collection page in our marketplace 👾 20+ new free custom avatars added ⁉️ New “Randomize” button to get a fully randomized custom avatar 🔍 Improved filters and search options to easily find your avatar

The Sandbox

19,768 views • 2 years ago

SuperGrok is insanely powerful. Use the file chat feature and talk to your code in real time. Coded this 3D model of helmet for a game asset using threejs and webgl with Grok 4. The file chat allowed me to add lighting and color controls just like that. It felt surreal. Try it now.
0:46

SuperGrok is insanely powerful. Use the file chat feature and talk to your code in real time. Coded this 3D model of helmet for a game asset using threejs and webgl with Grok 4. The file chat allowed me to add lighting and color controls just like that. It felt surreal. Try it now.

Prashant

1,273,920 views • 11 months ago

Say hello 👋 to our Instant Avatar (Avatar 2.0) - the most advanced avatar technology in the market. Users can now create their own custom avatars in under 5 minutes ⏰ with just a phone or laptop. Oh, and did we mention it was FREE?! 🎉 Get started:
0:29

Say hello 👋 to our Instant Avatar (Avatar 2.0) - the most advanced avatar technology in the market. Users can now create their own custom avatars in under 5 minutes ⏰ with just a phone or laptop. Oh, and did we mention it was FREE?! 🎉 Get started:

HeyGen

72,555 views • 2 years ago

It's finally here! My Cate Kitty Avatar! Inspiration from Cate Meowdy! You can also try it for free with the public version! But yes for 15$! Customize how you like! I'll also be including my new made discord too, which will be important for future avatars to come! Links below!
1:38

It's finally here! My Cate Kitty Avatar! Inspiration from Cate Meowdy! You can also try it for free with the public version! But yes for 15$! Customize how you like! I'll also be including my new made discord too, which will be important for future avatars to come! Links below!

akittu

16,676 views • 1 year ago

TIPS: Instrument mocap is a complicated task. It's more than just attaching the prop to your avatar model. #XRAnimator simplifies the process with specialized props that do the adjustments automatically. All you need is a webcam to be a 3D VTuber musician🎵📷
0:37

TIPS: Instrument mocap is a complicated task. It's more than just attaching the prop to your avatar model. #XRAnimator simplifies the process with specialized props that do the adjustments automatically. All you need is a webcam to be a 3D VTuber musician🎵📷

Butz Yung

71,946 views • 6 months ago

Today I created Tetris: but it has an unnecessary learning curve and makes my arm really tired 🟦🥵 Built with Three.js and MediaPipe hand-tracking. This runs on the web and uses a regular laptop / webcam. Let me know if you want to play, and I'll fight some bugs and ship! ⛴️
0:44

Today I created Tetris: but it has an unnecessary learning curve and makes my arm really tired 🟦🥵 Built with Three.js and MediaPipe hand-tracking. This runs on the web and uses a regular laptop / webcam. Let me know if you want to play, and I'll fight some bugs and ship! ⛴️

AA

20,114 views • 1 year ago

From live video to 3D avatar in seconds. This #SIGGRAPH2025 paper from Adobe Research reconstructs a realistic head avatar on the fly, with no pre-cached data, and adapts seamlessly to facial motion for VR, animation, and online communication. 🔗
0:23

From live video to 3D avatar in seconds. This #SIGGRAPH2025 paper from Adobe Research reconstructs a realistic head avatar on the fly, with no pre-cached data, and adapts seamlessly to facial motion for VR, animation, and online communication. 🔗

Adobe Research

29,112 views • 1 year ago

The free UE5 AVATAR project launches today for testing! Experience real-time rendering with cinematic animation quality—create personalized avatars, design outfits, and soon, enjoy full support for importing and exporting 3D models, custom items, and scenes. Right now, you can connect it with free AI motion capture. Comment to get the software!
2:23

The free UE5 AVATAR project launches today for testing! Experience real-time rendering with cinematic animation quality—create personalized avatars, design outfits, and soon, enjoy full support for importing and exporting 3D models, custom items, and scenes. Right now, you can connect it with free AI motion capture. Comment to get the software!

CYANPUPPETS

34,005 views • 1 year ago

After spending some time in the Virgin Islands, I was inspired to create a WebGPU-based water shader with TSL and compute shaders 🌊 Lots left to do, but it's finally starting to look decent! #threejs #webgl #webgpu #shaders
0:51

After spending some time in the Virgin Islands, I was inspired to create a WebGPU-based water shader with TSL and compute shaders 🌊 Lots left to do, but it's finally starting to look decent! #threejs #webgl #webgpu #shaders

Dan Greenheck

28,002 views • 8 months ago

now working in glorious WebGL! added the morph target and wasted a lot of time trying to *ahem* _improve_ the avatar generation ; I noticed the tooth & back were poorly reconstructed so I tried to synthesize and use multiple views & inject them at fitting time, not my finest idea
1:11

now working in glorious WebGL! added the morph target and wasted a lot of time trying to *ahem* _improve_ the avatar generation ; I noticed the tooth & back were poorly reconstructed so I tried to synthesize and use multiple views & inject them at fitting time, not my finest idea

Nicolas Barradeau

11,397 views • 1 month ago

New Puplic Lycanroc Drone Avatar A new public SDL drone avatar has been released. A Lycanroc drone avatar. The avatar has the following options: - Colour can be changed - Hypnovisor with effect Textured and modified by Roc Unit L-049 . We hope you all like this new avatar and have fun with it. The avatar is Adviable on our SDL avatar World. Links to it in the comments. A quest version of the avatar will be released in the coming days.
1:07

New Puplic Lycanroc Drone Avatar A new public SDL drone avatar has been released. A Lycanroc drone avatar. The avatar has the following options: - Colour can be changed - Hypnovisor with effect Textured and modified by Roc Unit L-049 . We hope you all like this new avatar and have fun with it. The avatar is Adviable on our SDL avatar World. Links to it in the comments. A quest version of the avatar will be released in the coming days.

SDL

19,056 views • 8 months ago

Who is ready to eat noodles with me? Seedance 2.0 on WeryAI try it here : Prompt Create a UGC ad using my avatar face. Basically I put noodles pack as a reference product created with GPT Image and my reference image, asked it to create an ad for me. Tada
0:42

Who is ready to eat noodles with me? Seedance 2.0 on WeryAI try it here : Prompt Create a UGC ad using my avatar face. Basically I put noodles pack as a reference product created with GPT Image and my reference image, asked it to create an ad for me. Tada

Sharon Riley

13,360 views • 3 months ago

Was doing an experiment with my HTC Cosmos Elite and decided to do a random video of the current progress of the squish dragon avatar. The avatar is far from being finished.
0:23

Was doing an experiment with my HTC Cosmos Elite and decided to do a random video of the current progress of the squish dragon avatar. The avatar is far from being finished.

Irix

83,789 views • 2 years ago

Want to create an avatar from a single image? FlexAvatar is a transformer model that creates full 360°, high-quality, and expressive 3D head avatar from just a single portrait image in minutes. Real-time Demo: FlexAvatar's lightweight architecture allows both animation and rendering in real-time, enabling interactive user experiences. To create a new 3D head avatar, only one image is required, e.g., from a webcam. The final avatar is ready after 2 minutes. Architecture: Under the hood, FlexAvatar adopts a transformer-based encoder-decoder design. The encoder maps the input image onto a latent avatar space, while the decoder produces 3D Gaussian attribute maps by incorporating the animation signal via cross-attention. The model learns all facial animations directly from the data without relying on pre-built 3D face models. This equips the avatars with realistic facial expressions. The internal avatar latent space can be conveniently used to integrate additional observations of a person via fitting. This enables use-cases where more than one image of a person is available, e.g., from a phone scan of the person. We train jointly on 2D monocular videos and multi-view data. However, in monocular videos, the animation signal leaks the target viewpoint, causing the model to produce incomplete 3D heads. We call this phenomenon entanglement of driving signal and target viewpoint. To prevent entanglement, we introduce bias sinks. These are learnable tokens that indicate whether a training sample stems from a monocular or a multi-view dataset. During training, the model learns to produce incomplete 3D heads only when the monocular token is present. During inference, FlexAvatar then always uses the multi-view token for which the model has learned to produce complete 3D heads. This simple design allows to combine the generalizability from monocular data with the quality of multi-view data. FlexAvatar summary: - Input: Single-image, phone scan, or monocular video - Output: Full 360° head avatar - Expressive animations - Real-time rendering and animation - Generalization to any portrait - Create a new avatar in 2 minutes - Use bias sinks to combine 2D and 3D data 🏠 🌍 🎥 Great work by Tobias Kirschstein and Simon Giebenhain!
0:30

Want to create an avatar from a single image? FlexAvatar is a transformer model that creates full 360°, high-quality, and expressive 3D head avatar from just a single portrait image in minutes. Real-time Demo: FlexAvatar's lightweight architecture allows both animation and rendering in real-time, enabling interactive user experiences. To create a new 3D head avatar, only one image is required, e.g., from a webcam. The final avatar is ready after 2 minutes. Architecture: Under the hood, FlexAvatar adopts a transformer-based encoder-decoder design. The encoder maps the input image onto a latent avatar space, while the decoder produces 3D Gaussian attribute maps by incorporating the animation signal via cross-attention. The model learns all facial animations directly from the data without relying on pre-built 3D face models. This equips the avatars with realistic facial expressions. The internal avatar latent space can be conveniently used to integrate additional observations of a person via fitting. This enables use-cases where more than one image of a person is available, e.g., from a phone scan of the person. We train jointly on 2D monocular videos and multi-view data. However, in monocular videos, the animation signal leaks the target viewpoint, causing the model to produce incomplete 3D heads. We call this phenomenon entanglement of driving signal and target viewpoint. To prevent entanglement, we introduce bias sinks. These are learnable tokens that indicate whether a training sample stems from a monocular or a multi-view dataset. During training, the model learns to produce incomplete 3D heads only when the monocular token is present. During inference, FlexAvatar then always uses the multi-view token for which the model has learned to produce complete 3D heads. This simple design allows to combine the generalizability from monocular data with the quality of multi-view data. FlexAvatar summary: - Input: Single-image, phone scan, or monocular video - Output: Full 360° head avatar - Expressive animations - Real-time rendering and animation - Generalization to any portrait - Create a new avatar in 2 minutes - Use bias sinks to combine 2D and 3D data 🏠 🌍 🎥 Great work by Tobias Kirschstein and Simon Giebenhain!

Matthias Niessner

96,186 views • 8 months ago

Hey! I'm open for avatar re-texture work for VRChat! Want an avatar you will love and be proud to wear? Then I'm the fox to help you with that! Quality work and service. Accepting any avatar models! Fill this out to get a quote:
0:54

Hey! I'm open for avatar re-texture work for VRChat! Want an avatar you will love and be proud to wear? Then I'm the fox to help you with that! Quality work and service. Accepting any avatar models! Fill this out to get a quote:

Alpha WereFox

16,603 views • 11 months ago

The free AVATAR project is expected to launch for testing this week, offering cinematic-quality real-time rendering. You can create personalized characters and even connect with free AI motion capture to produce high-quality real-time animation using a 1080P webcam.
1:09

The free AVATAR project is expected to launch for testing this week, offering cinematic-quality real-time rendering. You can create personalized characters and even connect with free AI motion capture to produce high-quality real-time animation using a 1080P webcam.

CYANPUPPETS

41,033 views • 1 year ago