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.

Today we open-source LingBot-Video — the first MoE-based video foundation model built for embodied intelligence. 🔹30B params, only 3B active at inference. 🔹Augmented with 70K hours of embodied data on top of large-scale internet video pretraining. 🔹Already outperforming Wan2.6, Seedance 1.5 Pro, and Cosmos3 Super on RBench. 🧵👇

Robbyant

2,927 subscribers

1,181,420 views • 1 month ago •via X (Twitter)

Science & Technology Education

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

LingBot-Video is out on Hugging Face MoE-based video foundation model built for embodied intelligence 30B params, only 3B active at inference Augmented with 70K hours of embodied data on top of large-scale internet video pretraining

LingBot-Video is out on Hugging Face MoE-based video foundation model built for embodied intelligence 30B params, only 3B active at inference Augmented with 70K hours of embodied data on top of large-scale internet video pretraining

AK

40,846 views • 1 month ago

We're releasing HY-Embodied-0.5, a family of foundation models for real-world embodied agents. The 2B model is now open source. It strengthens spatial-temporal perception and embodied reasoning for prediction, interaction, and planning. 🤖 The suite includes: 🔹 2B for edge deployment 🔹 32B for complex reasoning Key innovations: 🔹 Mixture-of-Transformers (MoT) architecture for modality-specific computation 🔹 Latent tokens for improved perceptual representation 🔹 Self-evolving post-training 🔹 On-policy distillation from large to small models Across 22 benchmarks, the 2B model outperforms similarly sized SOTA systems on 16 tasks. The 32B model approaches frontier-level performance. 🔗 GitHub: 🤗 Hugging Face:

We're releasing HY-Embodied-0.5, a family of foundation models for real-world embodied agents. The 2B model is now open source. It strengthens spatial-temporal perception and embodied reasoning for prediction, interaction, and planning. 🤖 The suite includes: 🔹 2B for edge deployment 🔹 32B for complex reasoning Key innovations: 🔹 Mixture-of-Transformers (MoT) architecture for modality-specific computation 🔹 Latent tokens for improved perceptual representation 🔹 Self-evolving post-training 🔹 On-policy distillation from large to small models Across 22 benchmarks, the 2B model outperforms similarly sized SOTA systems on 16 tasks. The 32B model approaches frontier-level performance. 🔗 GitHub: 🤗 Hugging Face:

Tencent Hy

34,317 views • 4 months ago

Marey Realism 1.5 by Moonvalley is now live in ComfyUI API nodes! First video model trained only on 100% licensed 1080P footages — pro quality, production-ready, and commercially safe. Now available: 🔹 Text-to-Video 🔹 Image-to-Video 🕙 Pose and Motion Transfer nodes coming soon 🧵👇

Marey Realism 1.5 by Moonvalley is now live in ComfyUI API nodes! First video model trained only on 100% licensed 1080P footages — pro quality, production-ready, and commercially safe. Now available: 🔹 Text-to-Video 🔹 Image-to-Video 🕙 Pose and Motion Transfer nodes coming soon 🧵👇

ComfyUI

14,606 views • 1 year ago

Meet LongCat-Video-Avatar 1.5🐱—our upgraded, open-source digital human framework. Built for real production, not just short demos. What's New: 🔹 Upgraded Audio Encoder: Replaces Wav2Vec2 with Whisper-Large, yielding significantly smoother and more natural lip dynamics. 🔹 Production-Ready Stability: Achieves accurate lip-synchronization, full-body temporal stability, and robust long-video generation with strict identity consistency. 🔹 Stylized Domain Generalization: Robustly generalizes to anime, animals, and complex real-world conditions such as multi-person interactions and object handling. 🔹 Efficient 8-Step Inference: Advanced step distillation accelerates inference to 8 NFE, balancing cost-effective serving with exceptional visual fidelity. 📊 LongCat-Video-Avatar 1.5 performs strongly in realism, naturalness, and stability, outperforming leading open-source models and closed systems. 🐱 Avatar 1.5 framework is now open source: 🔗 Weights & Code: 🔗 HuggingFace: 🔗 Tech Report: 🔗 Project Page:

Meituan LongCat

31,400 views • 3 months ago

🤖Robots that think ahead and act in real time. LingBot-VA 2.0 — the first embodied-native foundation model. Not fine-tuned from a video generator. Built from scratch for the physical world. ✅ 93.6% success on bimanual tasks ⚡ 150 Hz single-GPU inference 🎯 20 demos to generalize. This is what happens when you stop adapting and start building natively. 🧵👇

🤖Robots that think ahead and act in real time. LingBot-VA 2.0 — the first embodied-native foundation model. Not fine-tuned from a video generator. Built from scratch for the physical world. ✅ 93.6% success on bimanual tasks ⚡ 150 Hz single-GPU inference 🎯 20 demos to generalize. This is what happens when you stop adapting and start building natively. 🧵👇

Robbyant

888,616 views • 1 month ago

Very excited to share our first public release after I joined Robbyant! We present Lingbot-Depth 👀 — a state-of-the-art depth foundation model trained with RGB-D MAE on millions of real & simulated RGBD pairs. 🔹 Camera depths as natural masks for RGB-D MAE modeling 🔹 Large-scale real + sim RGBD data curation pipeline What surprised us most: ✨ Significant improvement on transparent, reflective surfaces, and thin structures — traditionally the hardest cases for depth models. 👇These are some of hard causal-capture images we tested on. The results are pretty good! #DepthEstimation #FoundationModels #EmbodiedAI #3DVision #Robotics #RobbyAnt

Very excited to share our first public release after I joined Robbyant! We present Lingbot-Depth 👀 — a state-of-the-art depth foundation model trained with RGB-D MAE on millions of real & simulated RGBD pairs. 🔹 Camera depths as natural masks for RGB-D MAE modeling 🔹 Large-scale real + sim RGBD data curation pipeline What surprised us most: ✨ Significant improvement on transparent, reflective surfaces, and thin structures — traditionally the hardest cases for depth models. 👇These are some of hard causal-capture images we tested on. The results are pretty good! #DepthEstimation #FoundationModels #EmbodiedAI #3DVision #Robotics #RobbyAnt

Yinghao Xu

22,664 views • 6 months ago

🤖 LingBot-VLA 2.0 is now open-source — our next-gen embodied foundation model. 🔷 60,000 hours of high-quality pretraining data — combining curated robotic demonstrations and egocentric human operation videos 🔷 20 robot configurations across 17 brands — Astribot, Leju, Unitree, Franka, Fourier, Realman, and more 🔷 Whole-body DoF: heads, waists, dexterous hands, and mobile bases — enabling far more complex task scenarios 🔷 Inference under 130ms on RTX 4090 — developer events launching soon #EmbodiedAI #Robotics #OpenSource #VLA

🤖 LingBot-VLA 2.0 is now open-source — our next-gen embodied foundation model. 🔷 60,000 hours of high-quality pretraining data — combining curated robotic demonstrations and egocentric human operation videos 🔷 20 robot configurations across 17 brands — Astribot, Leju, Unitree, Franka, Fourier, Realman, and more 🔷 Whole-body DoF: heads, waists, dexterous hands, and mobile bases — enabling far more complex task scenarios 🔷 Inference under 130ms on RTX 4090 — developer events launching soon #EmbodiedAI #Robotics #OpenSource #VLA

Robbyant

731,613 views • 1 month ago

🔥 Very excited to share that we’re releasing LingBot-World 🌍 Robbyant — an open-source frontier world model! We’re pushing the limits of: 🔹 High-Fidelity Simulation & Precise Control 🔹 Long-Horizon Consistency & Memory 🔹 Modeling Physical & Game Worlds The most surprising part? The emergence of sophisticated behaviors that go beyond simple video generation. 👇I’m obsessed with this dragon demo 🐉. It can rollout for 1 min while maintaining crisp visual dynamics and consistent memory!

🔥 Very excited to share that we’re releasing LingBot-World 🌍 Robbyant — an open-source frontier world model! We’re pushing the limits of: 🔹 High-Fidelity Simulation & Precise Control 🔹 Long-Horizon Consistency & Memory 🔹 Modeling Physical & Game Worlds The most surprising part? The emergence of sophisticated behaviors that go beyond simple video generation. 👇I’m obsessed with this dragon demo 🐉. It can rollout for 1 min while maintaining crisp visual dynamics and consistent memory!

Yinghao Xu

41,657 views • 6 months ago

Sundar Pichai (Sundar Pichai), Google CEO, on: 🔹Race to AGI 🔹Agents 🔹AI & Information Diet 🔹Open Source 🔹Cybersecurity 🔹US vs China Intro AI agents replacing parts of the internet AI agents deciding our information diet Will agents kill the “raw internet”? AI cyberattacks and Google’s defense strategy Should dangerous cyber AI models be held back? The threshold for releasing powerful AI Why Google hasn't open-sourced a large model The broken business model with open-source AI American companies using Chinese AI The risk of building on China’s AI ecosystem Why Google cares so much about cheap, fast AI models Sundar on self-improving AI and the race to AGI Google’s compute situation Google has more AI demand than compute Google’s biggest compute bottleneck

Sundar Pichai (Sundar Pichai), Google CEO, on: 🔹Race to AGI 🔹Agents 🔹AI & Information Diet 🔹Open Source 🔹Cybersecurity 🔹US vs China Intro AI agents replacing parts of the internet AI agents deciding our information diet Will agents kill the “raw internet”? AI cyberattacks and Google’s defense strategy Should dangerous cyber AI models be held back? The threshold for releasing powerful AI Why Google hasn't open-sourced a large model The broken business model with open-source AI American companies using Chinese AI The risk of building on China’s AI ecosystem Why Google cares so much about cheap, fast AI models Sundar on self-improving AI and the race to AGI Google’s compute situation Google has more AI demand than compute Google’s biggest compute bottleneck

Matthew Berman

306,650 views • 3 months ago

Hear it directly from our CTO, @leehomyc🌀 Video AI today has three problems: it’s slow, expensive, and centralized. Everlyn solves all three: 🔹 Model: Everlyn-1 runs in ~25s at ~$0.04 per video. 🔹 Agents: Everworld gives you photorealistic twins you can own. 🔹 Protocol: Lyn secures everything on-chain with proof and provenance. This isn’t just video generation. It’s the agentic layer for the next Internet.

Hear it directly from our CTO, @leehomyc🌀 Video AI today has three problems: it’s slow, expensive, and centralized. Everlyn solves all three: 🔹 Model: Everlyn-1 runs in ~25s at ~$0.04 per video. 🔹 Agents: Everworld gives you photorealistic twins you can own. 🔹 Protocol: Lyn secures everything on-chain with proof and provenance. This isn’t just video generation. It’s the agentic layer for the next Internet.

Everlyn

131,619 views • 11 months ago

Today we are introducing Dyna-2, a world-action model pre-trained on one million hours of human video. At this scale, for the first time, we discovered several new scaling laws: • world-action models exhibit scaling law on human data across four orders of magnitude, from 1000 to 1,000,000 hours, • this human data scaling law implied a scaling law on never seen robot data, • both data and objective matter; world modeling and scaling on video data are essential for cross-embodiment scaling transfer to emerge 🧵

Today we are introducing Dyna-2, a world-action model pre-trained on one million hours of human video. At this scale, for the first time, we discovered several new scaling laws: • world-action models exhibit scaling law on human data across four orders of magnitude, from 1000 to 1,000,000 hours, • this human data scaling law implied a scaling law on never seen robot data, • both data and objective matter; world modeling and scaling on video data are essential for cross-embodiment scaling transfer to emerge 🧵

Dyna Robotics

1,747,032 views • 14 days ago

Meta announces Movie Gen A Cast of Media Foundation Models We present Movie Gen, a cast of foundation models that generates high-quality, 1080p HD videos with different aspect ratios and synchronized audio. We also show additional capabilities such as precise instruction-based video editing and generation of personalized videos based on a user’s image. Our models set a new state-of-the-art on multiple tasks: text-to-video synthesis, video personalization, video editing, video-to-audio generation, and text-to-audio generation. Our largest video generation model is a 30B parameter transformer trained with a maximum context length of 73K video tokens, corresponding to a generated video of 16 seconds at 16 frames-per-second. We show multiple technical innovations and simplifications on the architecture, latent spaces, training objectives and recipes, data curation, evaluation protocols, parallelization techniques, and inference optimizations that allow us to reap the benefits of scaling pre-training data, model size, and training compute for training large scale media generation models. We hope this paper helps the research community to accelerate progress and innovation in media generation models

Meta announces Movie Gen A Cast of Media Foundation Models We present Movie Gen, a cast of foundation models that generates high-quality, 1080p HD videos with different aspect ratios and synchronized audio. We also show additional capabilities such as precise instruction-based video editing and generation of personalized videos based on a user’s image. Our models set a new state-of-the-art on multiple tasks: text-to-video synthesis, video personalization, video editing, video-to-audio generation, and text-to-audio generation. Our largest video generation model is a 30B parameter transformer trained with a maximum context length of 73K video tokens, corresponding to a generated video of 16 seconds at 16 frames-per-second. We show multiple technical innovations and simplifications on the architecture, latent spaces, training objectives and recipes, data curation, evaluation protocols, parallelization techniques, and inference optimizations that allow us to reap the benefits of scaling pre-training data, model size, and training compute for training large scale media generation models. We hope this paper helps the research community to accelerate progress and innovation in media generation models

AK

62,719 views • 1 year ago

Santiago Carmuega (Santiago Carmuega) joins us for a technical deep dive into Dolos, a lightweight Cardano data node alternative built completely in Rust. 🚀 This Developers Office Hour breaks down TxPipe's design philosophy and architecture for optimizing ledger data access: • The Data Node Role: Bypassing heavy consensus validation to optimize for fast, resource-efficient ledger queries. • Rust Infrastructure: Leveraging a modern performance-first tech stack built on top of Cardano open protocols. • Lightweight Use Cases: Overcoming standard node hardware limitations for client-side applications and indexers. Check out the documentation and open-source repositories mentioned in the session: 🔹 Dolos Docs: 🔹 GitHub Repository: 🔹 Subscribe to the calendar:

Santiago Carmuega (Santiago Carmuega) joins us for a technical deep dive into Dolos, a lightweight Cardano data node alternative built completely in Rust. 🚀 This Developers Office Hour breaks down TxPipe's design philosophy and architecture for optimizing ledger data access: • The Data Node Role: Bypassing heavy consensus validation to optimize for fast, resource-efficient ledger queries. • Rust Infrastructure: Leveraging a modern performance-first tech stack built on top of Cardano open protocols. • Lightweight Use Cases: Overcoming standard node hardware limitations for client-side applications and indexers. Check out the documentation and open-source repositories mentioned in the session: 🔹 Dolos Docs: 🔹 GitHub Repository: 🔹 Subscribe to the calendar:

Cardano Community

18,265 views • 2 months ago

Introducing WALL-WM, our open-source World Model for embodied AI and the next piece of our open-source robotics stack. Carving World Action Modeling at the Event Joints Read the blog: Why it matters WALL-WM shifts robot world modeling from fixed-length action chunks to event-grounded video-action pretraining. It learns around events like reaching, contact, grasping, lifting, moving, and placing, so language, vision, and action align more naturally. Why you should care WALL-WM brings together: •Event-grounded VLA pretraining •Prior-aligned video-action architecture •Wan-based video tower + randomly initialized action DiT •Multi-view perception with sight-cone masking, tube patch masking, and Camera RoPE •Event Mode for variable-length execution •Unified Mode with Staircase Decoding •DMuon for large-scale training The goal: help robots learn what physically matters, not just what happens in the next fixed slice of time. Code (coming soon): #opensource #EmbodiedAI

Introducing WALL-WM, our open-source World Model for embodied AI and the next piece of our open-source robotics stack. Carving World Action Modeling at the Event Joints Read the blog: Why it matters WALL-WM shifts robot world modeling from fixed-length action chunks to event-grounded video-action pretraining. It learns around events like reaching, contact, grasping, lifting, moving, and placing, so language, vision, and action align more naturally. Why you should care WALL-WM brings together: •Event-grounded VLA pretraining •Prior-aligned video-action architecture •Wan-based video tower + randomly initialized action DiT •Multi-view perception with sight-cone masking, tube patch masking, and Camera RoPE •Event Mode for variable-length execution •Unified Mode with Staircase Decoding •DMuon for large-scale training The goal: help robots learn what physically matters, not just what happens in the next fixed slice of time. Code (coming soon): #opensource #EmbodiedAI

X Square Robot

41,801 views • 2 months ago

🚀 We’re excited to announce LingBot-VA, a new state-of-the-art robot policy model from Robbyant ! LingBot-VA is built on a causal, autoregressive video-action world model for generalist robot control. Highlights: (1) First unified autoregressive video-action world model for robot control (2) Low-latency inference with a new asynchronous execution pipeline (3) SOTA on RoboTwin (92.9%, firstever > 90%) and LIBERO (98.5%) (4) +20% over π0.5 on challenging real-world long-horizon & high-precision tasks

🚀 We’re excited to announce LingBot-VA, a new state-of-the-art robot policy model from Robbyant ! LingBot-VA is built on a causal, autoregressive video-action world model for generalist robot control. Highlights: (1) First unified autoregressive video-action world model for robot control (2) Low-latency inference with a new asynchronous execution pipeline (3) SOTA on RoboTwin (92.9%, firstever > 90%) and LIBERO (98.5%) (4) +20% over π0.5 on challenging real-world long-horizon & high-precision tasks

Yinghao Xu

46,962 views • 6 months ago

FRIEDBERG: VIDEO DATA WILL POWER THE NEXT GENERATION OF AI Friedberg broke down the scale shift coming to artificial intelligence, arguing that text based models like GPT are just the beginning, and that the real revolution will come from video-trained systems: “The internet and all these LLMs are language models trained on text from the internet, around 50 billion words total, maybe one to five terabytes of data in their training sets. But if you look at the video data out there, there are hundreds of billions of hours, much of it on YouTube. By some estimates, there’s a thousand exabytes of video data on the internet, about a billion times more than text data. I think we just saw that play out with the new video model that launched yesterday. Google has all this YouTube data, whether or not they’re using it to train, I don’t know. I’ve heard from insiders they’re not allowed to yet and would have to redo the terms of service.” Source: AIFinInsights david friedberg

FRIEDBERG: VIDEO DATA WILL POWER THE NEXT GENERATION OF AI Friedberg broke down the scale shift coming to artificial intelligence, arguing that text based models like GPT are just the beginning, and that the real revolution will come from video-trained systems: “The internet and all these LLMs are language models trained on text from the internet, around 50 billion words total, maybe one to five terabytes of data in their training sets. But if you look at the video data out there, there are hundreds of billions of hours, much of it on YouTube. By some estimates, there’s a thousand exabytes of video data on the internet, about a billion times more than text data. I think we just saw that play out with the new video model that launched yesterday. Google has all this YouTube data, whether or not they’re using it to train, I don’t know. I’ve heard from insiders they’re not allowed to yet and would have to redo the terms of service.” Source: AIFinInsights david friedberg

Mario Nawfal

15,855 views • 8 months ago

New research with Tsinghua University: Spatial-TTT. A framework for streaming visual-based spatial intelligence with test-time training (TTT). Spatial-TTT adapts fast weights to capture and organize spatial evidence from long video streams, enabling models to build structured 3D spatial memory over time. Highlights: 🔹Efficient streaming memory. Fast weights act as compact spatial memory with sublinear memory growth over 7000+ frames and more than 40% lower compute. 🔹Spatial-predictive mechanism. TTT layers with 3D spatiotemporal convolution capture geometric correspondence and temporal continuity. 🔹SOTA results on long-horizon video spatial understanding (VSI-Bench). The paper ranked #1 on Hugging Face Daily Papers on March 13. Project page: GitHub: Paper: Model & Data:

New research with Tsinghua University: Spatial-TTT. A framework for streaming visual-based spatial intelligence with test-time training (TTT). Spatial-TTT adapts fast weights to capture and organize spatial evidence from long video streams, enabling models to build structured 3D spatial memory over time. Highlights: 🔹Efficient streaming memory. Fast weights act as compact spatial memory with sublinear memory growth over 7000+ frames and more than 40% lower compute. 🔹Spatial-predictive mechanism. TTT layers with 3D spatiotemporal convolution capture geometric correspondence and temporal continuity. 🔹SOTA results on long-horizon video spatial understanding (VSI-Bench). The paper ranked #1 on Hugging Face Daily Papers on March 13. Project page: GitHub: Paper: Model & Data:

Tencent Hy

20,792 views • 5 months ago

Tencent presents GameGen-O Open-world Video Game Generation We introduce GameGen-O, the first diffusion transformer model tailored for the generation of open-world video games. This model facilitates high-quality, open-domain generation by simulating a wide array of game engine features, such as innovative characters, dynamic environments, complex actions, and diverse events. Additionally, it provides interactive controllability, thus allowing for the gameplay simulation. The development of GameGen-O involves a comprehensive data collection and processing effort from scratch. We collect and build the first Open-World Video Game Dataset (OGameData), amassed extensive data from over a hundred of next-generation open-world games, employing a proprietary data pipeline for efficient sorting, scoring, filtering, and decoupled captioning. This robust and extensive OGameData forms the foundation of our model's training process. GameGen-O undergoes a two-stage training process, consisting of foundation model pretraining and instruction tuning. In the first phase, the model is pre-trained on the OGameData via the text-to-video and video continuation, endowing GameGen-O with the capability for open-domain video game generation. In the second phase, the pre-trained model is frozen, and we fine-tuned using a trainable InstructNet, which enables the production of subsequent frames based on multimodal structural instructions. This whole training process imparts the model with the ability to generate and interactively control content. In summary, GameGen-O represents a notable initial step forward in the realm of open-world video game generation via generative models. It underscores the potential of generative models to serve as an alternative to rendering techniques, which can efficiently combine creative generation with interactive capabilities.

Tencent presents GameGen-O Open-world Video Game Generation We introduce GameGen-O, the first diffusion transformer model tailored for the generation of open-world video games. This model facilitates high-quality, open-domain generation by simulating a wide array of game engine features, such as innovative characters, dynamic environments, complex actions, and diverse events. Additionally, it provides interactive controllability, thus allowing for the gameplay simulation. The development of GameGen-O involves a comprehensive data collection and processing effort from scratch. We collect and build the first Open-World Video Game Dataset (OGameData), amassed extensive data from over a hundred of next-generation open-world games, employing a proprietary data pipeline for efficient sorting, scoring, filtering, and decoupled captioning. This robust and extensive OGameData forms the foundation of our model's training process. GameGen-O undergoes a two-stage training process, consisting of foundation model pretraining and instruction tuning. In the first phase, the model is pre-trained on the OGameData via the text-to-video and video continuation, endowing GameGen-O with the capability for open-domain video game generation. In the second phase, the pre-trained model is frozen, and we fine-tuned using a trainable InstructNet, which enables the production of subsequent frames based on multimodal structural instructions. This whole training process imparts the model with the ability to generate and interactively control content. In summary, GameGen-O represents a notable initial step forward in the realm of open-world video game generation via generative models. It underscores the potential of generative models to serve as an alternative to rendering techniques, which can efficiently combine creative generation with interactive capabilities.

AK

367,128 views • 1 year ago

Figure announces Project Go-Big: Internet-Scale Humanoid Pretraining and Direct Human-to-Robot Transfer The company has achieved a new milestone for the Helix AI model: after training exclusively on egocentric human data, Figure robots can now navigate real-world spaces from natural language commands such as “Go water the plants.” This also enabled a unified Helix model that can output both manipulation and navigation commands to the continuous control system. This ties into the Brookfield partnership that they announced yesterday. Brookfield is a global asset manager overseeing $1 trillion in assets, including 100,000 residential units, 500M square feet of commercial office space, and 160M square feet of logistics space. Using human video capture in a variety of Brookfield environments, Figure will amass critical pretraining data at scale, allowing them to explore the full potential of internet-scale embodied datasets for locomotion and manipulation.

Figure announces Project Go-Big: Internet-Scale Humanoid Pretraining and Direct Human-to-Robot Transfer The company has achieved a new milestone for the Helix AI model: after training exclusively on egocentric human data, Figure robots can now navigate real-world spaces from natural language commands such as “Go water the plants.” This also enabled a unified Helix model that can output both manipulation and navigation commands to the continuous control system. This ties into the Brookfield partnership that they announced yesterday. Brookfield is a global asset manager overseeing $1 trillion in assets, including 100,000 residential units, 500M square feet of commercial office space, and 160M square feet of logistics space. Using human video capture in a variety of Brookfield environments, Figure will amass critical pretraining data at scale, allowing them to explore the full potential of internet-scale embodied datasets for locomotion and manipulation.

The Humanoid Hub

32,879 views • 11 months ago