Loading video...

Video Failed to Load

Go Home

We’re introducing imagination models: a new foundation model architecture that unlocks learning from internet-scale video. Our first imagination model, Photon-1, learned to use a computer by watching 18 years of screen recording video without action labels.

induction_labs's profile picture

Induction Labs

4,188 subscribers

585,816 views • 18 days ago •via X (Twitter)

Science & TechnologyEducation
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Today, we are releasing Stable Video Diffusion, our first foundation model for generative AI video based on the image model, Stable Diffusion. As part of this research preview, the code, weights, and research paper are now available. Additionally, today you can sign up for our waitlist to access a new upcoming web experience featuring a Text-To-Video interface. To access the model & sign up for our waitlist, visit our website here:
0:20

Today, we are releasing Stable Video Diffusion, our first foundation model for generative AI video based on the image model, Stable Diffusion. As part of this research preview, the code, weights, and research paper are now available. Additionally, today you can sign up for our waitlist to access a new upcoming web experience featuring a Text-To-Video interface. To access the model & sign up for our waitlist, visit our website here:

Stability AI

1,024,577 views • 2 years ago

Introducing screengrasp - The new SOTA agent click position model - beating Anthropic Computer Use, OmniParser and Molmo by a wide margin. - Simplified API access to the best click models on the market. 🔁Retweet and DM for free API credits. More details 👇
0:18

Introducing screengrasp - The new SOTA agent click position model - beating Anthropic Computer Use, OmniParser and Molmo by a wide margin. - Simplified API access to the best click models on the market. 🔁Retweet and DM for free API credits. More details 👇

Florian S

54,319 views • 1 year ago

My 3D Model of Malevola from Dispatch is finally finished! This was a super fun project, I learned how to use hair curves for the first time and also 3D printed the full model! Have a look at the full process video! #blender #b3d #dispatch
0:12

My 3D Model of Malevola from Dispatch is finally finished! This was a super fun project, I learned how to use hair curves for the first time and also 3D printed the full model! Have a look at the full process video! #blender #b3d #dispatch

Niall

15,127 views • 6 months ago

introducing FLUX 3. beyond video, this is the first model to support interactions with the real world through a new action-prediction system. available now on Krea, more modalities coming soon.
0:19

introducing FLUX 3. beyond video, this is the first model to support interactions with the real world through a new action-prediction system. available now on Krea, more modalities coming soon.

Krea

31,208 views • 6 days ago

MIMO: Advanced Video-to-Video Model by Alibaba This is insane! With this v2v model, we can take a video of ourselves and use it to animate any character we create, all while keeping the original background from the video. It's like we're putting ourselves into any other new worlds! 6 Example:
0:10

MIMO: Advanced Video-to-Video Model by Alibaba This is insane! With this v2v model, we can take a video of ourselves and use it to animate any character we create, all while keeping the original background from the video. It's like we're putting ourselves into any other new worlds! 6 Example:

el.cine

118,771 views • 1 year ago

Today we're releasing the Segment Anything Model (SAM) — a step toward the first foundation model for image segmentation. SAM is capable of one-click segmentation of any object from any photo or video + zero-shot transfer to other segmentation tasks ➡️
0:15

Today we're releasing the Segment Anything Model (SAM) — a step toward the first foundation model for image segmentation. SAM is capable of one-click segmentation of any object from any photo or video + zero-shot transfer to other segmentation tasks ➡️

AI at Meta

3,570,843 views • 3 years ago

NVIDIA just released a very impressive text-to-video paper. Video Latent Diffusion Models (Video LDMs) use a diffusion model in a compressed latent space to generate high-resolution videos. Here's a brief overview of how it works: 1. Pre-train image LDM on a dataset of images. 2. Turn the image LDM into a Video LDM by adding temporal layers to model video frames. 3. Fine-tune the Video LDM on encoded video sequences to create a video generator. 4. Temporally align diffusion model upsamplers to generate high-resolution videos. 5. Validate Video LDM on real driving videos of 512x1024 resolution, achieving state-of-the-art performance. 6. Apply the approach in creative content creation with text-to-video modeling. Paper: Project:
0:14

NVIDIA just released a very impressive text-to-video paper. Video Latent Diffusion Models (Video LDMs) use a diffusion model in a compressed latent space to generate high-resolution videos. Here's a brief overview of how it works: 1. Pre-train image LDM on a dataset of images. 2. Turn the image LDM into a Video LDM by adding temporal layers to model video frames. 3. Fine-tune the Video LDM on encoded video sequences to create a video generator. 4. Temporally align diffusion model upsamplers to generate high-resolution videos. 5. Validate Video LDM on real driving videos of 512x1024 resolution, achieving state-of-the-art performance. 6. Apply the approach in creative content creation with text-to-video modeling. Paper: Project:

Lior Alexander

158,565 views • 3 years ago

📢Introducing Generated Reality📢 A world model for XR that turns your tracked hand and head poses into an interactive, generative video experience. Take world models to the next level by interacting with the world using your own body! 🔗 1/4
0:15

📢Introducing Generated Reality📢 A world model for XR that turns your tracked hand and head poses into an interactive, generative video experience. Take world models to the next level by interacting with the world using your own body! 🔗 1/4

Gordon Wetzstein

20,045 views • 5 months ago

We are pleased to announce the availability of Stable Video 4D, our very first video-to-video generation model that allows users to upload a single video and receive dynamic novel-view videos of eight new angles, delivering a new level of versatility and creativity. In conjunction with this announcement, we are releasing a comprehensive technical report detailing the methodologies, challenges, and breakthroughs achieved during the development of this model. Learn more about this release and access the report here:
0:13

We are pleased to announce the availability of Stable Video 4D, our very first video-to-video generation model that allows users to upload a single video and receive dynamic novel-view videos of eight new angles, delivering a new level of versatility and creativity. In conjunction with this announcement, we are releasing a comprehensive technical report detailing the methodologies, challenges, and breakthroughs achieved during the development of this model. Learn more about this release and access the report here:

Stability AI

131,173 views • 2 years ago

This is a video from when we rented a studio and invited a lighting director to hold a live-action lighting workshop for our staff for DS2. The model was Shioli Kutsuna. Two and a half years ago🙏😍🫶🎬
0:15

This is a video from when we rented a studio and invited a lighting director to hold a live-action lighting workshop for our staff for DS2. The model was Shioli Kutsuna. Two and a half years ago🙏😍🫶🎬

HIDEO_KOJIMA

276,820 views • 1 year ago

BREAKING: Chinese cybersecurity company just found a way around one of AI's most expensive problems. Meta built an AI model called SAM that could outline any object in a photo. The catch: it needed millions of hand-labeled images to learn how. 360 AI Research's new ECCV 2026 paper, MoSA teaches AI to recognize objects by watching video move. No human labels. 10,000 hours of unlabeled video. 21 million+ self-generated labels. Zero humans in the loop. Learn more 🧵👇
0:16

BREAKING: Chinese cybersecurity company just found a way around one of AI's most expensive problems. Meta built an AI model called SAM that could outline any object in a photo. The catch: it needed millions of hand-labeled images to learn how. 360 AI Research's new ECCV 2026 paper, MoSA teaches AI to recognize objects by watching video move. No human labels. 10,000 hours of unlabeled video. 21 million+ self-generated labels. Zero humans in the loop. Learn more 🧵👇

Shruti

115,394 views • 27 days ago

1/ Gemini 2.5 is here, and it’s our most intelligent AI model ever. Our first 2.5 model, Gemini 2.5 Pro Experimental is a state-of-the-art thinking model, leading in a wide range of benchmarks – with impressive improvements in enhanced reasoning and coding and now #1 on Arena by a significant margin. With a model this intelligent, we wanted to get it to people as quickly as possible. Find it on Google AI Studio and in the Google Gemini for Gemini Advanced users now – and in Vertex in the coming weeks. This is the start of a new era of thinking models – and we can’t wait to see where things go from here.
0:14

1/ Gemini 2.5 is here, and it’s our most intelligent AI model ever. Our first 2.5 model, Gemini 2.5 Pro Experimental is a state-of-the-art thinking model, leading in a wide range of benchmarks – with impressive improvements in enhanced reasoning and coding and now #1 on Arena by a significant margin. With a model this intelligent, we wanted to get it to people as quickly as possible. Find it on Google AI Studio and in the Google Gemini for Gemini Advanced users now – and in Vertex in the coming weeks. This is the start of a new era of thinking models – and we can’t wait to see where things go from here.

Sundar Pichai

864,496 views • 1 year ago

The new Victoria VR website is live. We continue to evolve our journey with AI. Victoria VR is more than a virtual world, it’s an AI-driven platform where creation is powered by intelligence itself. Imagine writing a single sentence and watching it become a living world. AI generates the architecture. AI populates it with avatars. AI gives them memory, logic, and awareness. This is creation redefined, where generative AI meets virtual reality, and imagination meets execution. Welcome to the foundation layer of the immersive internet. Discover the new Victoria VR: Victoria VR, a world where anything is possible.
0:12

The new Victoria VR website is live. We continue to evolve our journey with AI. Victoria VR is more than a virtual world, it’s an AI-driven platform where creation is powered by intelligence itself. Imagine writing a single sentence and watching it become a living world. AI generates the architecture. AI populates it with avatars. AI gives them memory, logic, and awareness. This is creation redefined, where generative AI meets virtual reality, and imagination meets execution. Welcome to the foundation layer of the immersive internet. Discover the new Victoria VR: Victoria VR, a world where anything is possible.

Victoria VR

176,796 views • 9 months ago

AI just won't stop 🤯 Just this week, 160+ AI models were released from companies like Google, META, Alibaba, more. Here are the 9 incredible AI models you need to know about: 1/ FMA-Net, a new AI model for video deblurring.
0:19

AI just won't stop 🤯 Just this week, 160+ AI models were released from companies like Google, META, Alibaba, more. Here are the 9 incredible AI models you need to know about: 1/ FMA-Net, a new AI model for video deblurring.

Barsee 🐶

566,905 views • 2 years ago

Depth Any Video with Scalable Synthetic Data AI physicists and chemists continue to make strides in depth estimation from video. Check out this new paper featuring some impressive examples. See the thread for more details (unfortunately no code yet). Abstract: Video depth estimation has long been hindered by the scarcity of consistent and scalable ground truth data, leading to inconsistent and unreliable results. In this paper, we introduce Depth Any Video, a model that tackles the challenge through two key innovations. First, we develop a scalable synthetic data pipeline, capturing real-time video depth data from diverse game environments, yielding 40,000 video clips of 5-second duration, each with precise depth annotations. Second, we leverage the powerful priors of generative video diffusion models to handle real-world videos effectively, integrating advanced techniques such as rotary position encoding and flow matching to further enhance flexibility and efficiency. Unlike previous models, which are limited to fixed-length video sequences, our approach introduces a novel mixed-duration training strategy that handles videos of varying lengths and performs robustly across different frame rates 0 - even on single frames. At inference, we propose a depth interpolation method that enables our model to infer high-resolution video depth across sequences of up to 150 frames. Our model outperforms all previous generative depth models in terms of spatial accuracy and temporal consistency.
0:13

Depth Any Video with Scalable Synthetic Data AI physicists and chemists continue to make strides in depth estimation from video. Check out this new paper featuring some impressive examples. See the thread for more details (unfortunately no code yet). Abstract: Video depth estimation has long been hindered by the scarcity of consistent and scalable ground truth data, leading to inconsistent and unreliable results. In this paper, we introduce Depth Any Video, a model that tackles the challenge through two key innovations. First, we develop a scalable synthetic data pipeline, capturing real-time video depth data from diverse game environments, yielding 40,000 video clips of 5-second duration, each with precise depth annotations. Second, we leverage the powerful priors of generative video diffusion models to handle real-world videos effectively, integrating advanced techniques such as rotary position encoding and flow matching to further enhance flexibility and efficiency. Unlike previous models, which are limited to fixed-length video sequences, our approach introduces a novel mixed-duration training strategy that handles videos of varying lengths and performs robustly across different frame rates 0 - even on single frames. At inference, we propose a depth interpolation method that enables our model to infer high-resolution video depth across sequences of up to 150 frames. Our model outperforms all previous generative depth models in terms of spatial accuracy and temporal consistency.

MrNeRF

27,428 views • 1 year ago

NEW SECRET MYSTERY AI VIDEO MODEL ARENA CODE NAME: BOUNCYBOHR Unlike Artificial Analysis, on Arena. AI you can submit your own prompts and this prompt is designed to try and unmask who created the model. Models powered by an LLM (like Seedance 2.0 and Omni) are smart and can see what you are doing. As far as thoughts? Eh? While another screenshot looked like Omni, this does look pretty Seedance to me. Judging by the result, this looks like the rumored new "improved" FAST model and not upgraded full 2.1 model that is supposed to be 25% better. Text To Video close-up cinematic scene from a film, professionally directed, focused, ultrafine details a woman laughs as she whiteboard writes out what model made this video
0:15

NEW SECRET MYSTERY AI VIDEO MODEL ARENA CODE NAME: BOUNCYBOHR Unlike Artificial Analysis, on Arena. AI you can submit your own prompts and this prompt is designed to try and unmask who created the model. Models powered by an LLM (like Seedance 2.0 and Omni) are smart and can see what you are doing. As far as thoughts? Eh? While another screenshot looked like Omni, this does look pretty Seedance to me. Judging by the result, this looks like the rumored new "improved" FAST model and not upgraded full 2.1 model that is supposed to be 25% better. Text To Video close-up cinematic scene from a film, professionally directed, focused, ultrafine details a woman laughs as she whiteboard writes out what model made this video

Brent Lynch

32,504 views • 2 months ago

Our next-gen interactive video model is shaping up to be so exciting. Check out these early outputs. AI-imagined video that you can play like a game feels like a totally new form of media. The YouTube of interactive video must be built to enjoy it 🥰
0:10

Our next-gen interactive video model is shaping up to be so exciting. Check out these early outputs. AI-imagined video that you can play like a game feels like a totally new form of media. The YouTube of interactive video must be built to enjoy it 🥰

Oliver Cameron

33,399 views • 1 year ago

(1/n) 🚀 With FastVideo, you can now generate a 5-second video in 5 seconds on a single H200 GPU! Introducing FastWan series, a family of fast video generation models trained via a new recipe we term as “sparse distillation”, to speed up video denoising time by 70X! 🖥️ Live demo: (Thanks to @gmicloud for the support!) 🔗 Blog: 🔓 We fully open-source our models, code, and data with Apache-2.0 licenses
0:13

(1/n) 🚀 With FastVideo, you can now generate a 5-second video in 5 seconds on a single H200 GPU! Introducing FastWan series, a family of fast video generation models trained via a new recipe we term as “sparse distillation”, to speed up video denoising time by 70X! 🖥️ Live demo: (Thanks to @gmicloud for the support!) 🔗 Blog: 🔓 We fully open-source our models, code, and data with Apache-2.0 licenses

Hao AI Lab

78,660 views • 1 year ago

A viral paper "Language Model Represents Space and Time" recently claims that LLMs learn "world models". As much as I like Max Tegmark's works, I disagree with their definition of world model. World model is a core concept in AI agent and decision making. It is our mental simulation of how the world works given interventions (or lack thereof). A world model captures causality and intuitive physics, telling the agent what is likely and what is impossible. It can and should be used for counterfactual reasoning, i.e. "what ifs": what would happen if I knock over a cup of water? Where would I have been if I had not taken that bus? Yann LeCun Yann LeCun says it well in his position paper ( I quote: "Using such world models, animals can learn new skills with very few trials. They can predict the consequences of their actions, they can reason, plan, explore, and imagine new solutions to problems. Importantly, they can also avoid making dangerous mistakes when facing an unknown situation." The first use of the term World Model in deep policy learning is attributed to hardmaru & Jürgen Schmidhuber: In their seminal paper, an agent masters shooting skills in the popular game Doom (demo below) by learning in imagination, using an internal world model as a "physics simulator". To put in a simple Python math formula, world model learns a function F(s[0:t-1], a) -> s[t:], which takes as input the observed past and current action, and outputs plausible future states. Now the definition of World Model in Tegmark's paper seems to be about predicting GPS coordinates and time eras. I see this as just a classification task with no causal learning and simulation going on. You cannot make meaningful interventions against that model, nor can you optimize any decision making in a closed feedback loop. As for the "space & time neurons", I think they are most similar to the "sentiment neuron" that OpenAI published in 2017: Predicting GPS is conceptually no different from predicting sentiment in my opinion. I don't think their experimental results are wrong - just that their conclusion is on shaky grounds. I welcome any debate! Paper link:
0:15

A viral paper "Language Model Represents Space and Time" recently claims that LLMs learn "world models". As much as I like Max Tegmark's works, I disagree with their definition of world model. World model is a core concept in AI agent and decision making. It is our mental simulation of how the world works given interventions (or lack thereof). A world model captures causality and intuitive physics, telling the agent what is likely and what is impossible. It can and should be used for counterfactual reasoning, i.e. "what ifs": what would happen if I knock over a cup of water? Where would I have been if I had not taken that bus? Yann LeCun Yann LeCun says it well in his position paper ( I quote: "Using such world models, animals can learn new skills with very few trials. They can predict the consequences of their actions, they can reason, plan, explore, and imagine new solutions to problems. Importantly, they can also avoid making dangerous mistakes when facing an unknown situation." The first use of the term World Model in deep policy learning is attributed to hardmaru & Jürgen Schmidhuber: In their seminal paper, an agent masters shooting skills in the popular game Doom (demo below) by learning in imagination, using an internal world model as a "physics simulator". To put in a simple Python math formula, world model learns a function F(s[0:t-1], a) -> s[t:], which takes as input the observed past and current action, and outputs plausible future states. Now the definition of World Model in Tegmark's paper seems to be about predicting GPS coordinates and time eras. I see this as just a classification task with no causal learning and simulation going on. You cannot make meaningful interventions against that model, nor can you optimize any decision making in a closed feedback loop. As for the "space & time neurons", I think they are most similar to the "sentiment neuron" that OpenAI published in 2017: Predicting GPS is conceptually no different from predicting sentiment in my opinion. I don't think their experimental results are wrong - just that their conclusion is on shaky grounds. I welcome any debate! Paper link:

Jim Fan

594,014 views • 2 years ago