Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

🔥Introducing Open-Sora Plan v1.3! We introduce the🚀Skiparse 3D attention and 🚄WFVAE, significantly reducing the training cost of the model. This video is an alternate ending we created for #BlackMythWukong , generated by our v1.3. Welcome to star!🌟

Bin Lin

1,275 subscribers

23,891 Aufrufe • vor 1 Jahr •via X (Twitter)

#BlackMythWukong

Anya Rossi• Live Now

Private livecam show

7 Kommentare

Profilbild von Bin Lin

Bin Linvor 1 Jahr

By the way, the #Allegro was built on our v1.2 version. I’m glad to see more and more companies fine-tuning and commercializing models based on our Open-Sora Plan. The significance of open-source is becoming increasingly tangible.♥️

Profilbild von Bin Lin

Bin Linvor 1 Jahr

Carefully! The video includes audio but Chinese version.

Profilbild von UNPLUGGED PERFORMANCE

UNPLUGGED PERFORMANCEvor 1 Jahr

Upgrade your Tesla with UP-03 Forged Wheels from Unplugged Performance! Unmatched strength, lightweight design, and track-proven durability—perfect for Model S, 3, X, and Y. Ready to ship with a lifetime warranty. #Tesla #UP03 #UnpluggedPerformance

Profilbild von Ray

Rayvor 1 Jahr

cool

Profilbild von Lyman

Lymanvor 1 Jahr

nice work

Profilbild von davis

davisvor 1 Jahr

老哥，videobench在hf 上挂了，可以帮忙在后台更新一下吗

Profilbild von Josh Garbutt

Josh Garbuttvor 1 Jahr

Hi Bin, Love the work you're doing!!! I'm actually partnered with a company based in the California who is looking for Gen AI specialists with experience in Character generation Would be great to speak more on this and see if youre interested?

Ähnliche Videos

Welcome to Ignition This is the final phase before we transition to a Proof of Contribution rewards model powered by an ERC-20C token Introducing Ignition Rewards 👇

Welcome to Ignition This is the final phase before we transition to a Proof of Contribution rewards model powered by an ERC-20C token Introducing Ignition Rewards 👇

Fishing Frenzy

21,110 Aufrufe • vor 10 Monaten

🌟 Introducing Falcon 180B: The World's Most Powerful Open LLM! 🚀 At #TII, we are continuing to push the boundaries of generative AI with our open access Falcon 180B AI model which has already soared to the top of the Hugging Face Leaderboard.

🌟 Introducing Falcon 180B: The World's Most Powerful Open LLM! 🚀 At #TII, we are continuing to push the boundaries of generative AI with our open access Falcon 180B AI model which has already soared to the top of the Hugging Face Leaderboard.

Technology Innovation Institute

1,296,194 Aufrufe • vor 2 Jahren

Virtual try-on is the future of retail. Soon, we won’t even remember a time when we shopped without it. With Doji I created a fashion campaign with my favorite new products with myself as the model, an AI generated digital twin, and brought it to life additional AI video tools. Open to see more experiments and use cases for this technology:

Virtual try-on is the future of retail. Soon, we won’t even remember a time when we shopped without it. With Doji I created a fashion campaign with my favorite new products with myself as the model, an AI generated digital twin, and brought it to life additional AI video tools. Open to see more experiments and use cases for this technology:

Paige Piskin XR

52,666 Aufrufe • vor 1 Jahr

This is probably the best AI generated video I saw. This video cost 8500$ worth of credits to make. It was created by Varun Mayya's team.

This is probably the best AI generated video I saw. This video cost 8500$ worth of credits to make. It was created by Varun Mayya's team.

Elias

23,449 Aufrufe • vor 1 Monat

This video was generated by Sora. That's the new model by OpenAI. The most advanced text-to-video tool created so far. I'll share the videos here. Absolutely insane. Prompt: This close-up shot of a Victoria crowned pigeon showcases its striking blue plumage and red chest. Its crest is made of delicate, lacy feathers, while its eye is a striking red color. The bird’s head is tilted slightly to the side, giving the impression of it looking regal and majestic. The background is blurred, drawing attention to the bird’s striking appearance.

This video was generated by Sora. That's the new model by OpenAI. The most advanced text-to-video tool created so far. I'll share the videos here. Absolutely insane. Prompt: This close-up shot of a Victoria crowned pigeon showcases its striking blue plumage and red chest. Its crest is made of delicate, lacy feathers, while its eye is a striking red color. The bird’s head is tilted slightly to the side, giving the impression of it looking regal and majestic. The background is blurred, drawing attention to the bird’s striking appearance.

Eduardo Borges

17,035,603 Aufrufe • vor 2 Jahren

V3D Video Diffusion Models are Effective 3D Generators Automatic 3D generation has recently attracted widespread attention. Recent methods have greatly accelerated the generation speed, but usually produce less-detailed objects due to limited model capacity or 3D data. Motivated by recent advancements in video diffusion models, we introduce V3D, which leverages the world simulation capacity of pre-trained video diffusion models to facilitate 3D generation. To fully unleash the potential of video diffusion to perceive the 3D world, we further introduce geometrical consistency prior and extend the video diffusion model to a multi-view consistent 3D generator. Benefiting from this, the state-of-the-art video diffusion model could be fine-tuned to generate 360degree orbit frames surrounding an object given a single image. With our tailored reconstruction pipelines, we can generate high-quality meshes or 3D Gaussians within 3 minutes. Furthermore, our method can be extended to scene-level novel view synthesis, achieving precise control over the camera path with sparse input views. Extensive experiments demonstrate the superior performance of the proposed approach, especially in terms of generation quality and multi-view consistency

V3D Video Diffusion Models are Effective 3D Generators Automatic 3D generation has recently attracted widespread attention. Recent methods have greatly accelerated the generation speed, but usually produce less-detailed objects due to limited model capacity or 3D data. Motivated by recent advancements in video diffusion models, we introduce V3D, which leverages the world simulation capacity of pre-trained video diffusion models to facilitate 3D generation. To fully unleash the potential of video diffusion to perceive the 3D world, we further introduce geometrical consistency prior and extend the video diffusion model to a multi-view consistent 3D generator. Benefiting from this, the state-of-the-art video diffusion model could be fine-tuned to generate 360degree orbit frames surrounding an object given a single image. With our tailored reconstruction pipelines, we can generate high-quality meshes or 3D Gaussians within 3 minutes. Furthermore, our method can be extended to scene-level novel view synthesis, achieving precise control over the camera path with sparse input views. Extensive experiments demonstrate the superior performance of the proposed approach, especially in terms of generation quality and multi-view consistency

AK

31,997 Aufrufe • vor 2 Jahren

🌟WELCOME OUR 2025 NATIONAL CHAMPIONS!🌟 We are proud to introduce these incredible Champions to our network. Their stories show the impact your donations have on kids in your community. Watch the video to learn about this inspiring group of National Champions! #changekidshealth

🌟WELCOME OUR 2025 NATIONAL CHAMPIONS!🌟 We are proud to introduce these incredible Champions to our network. Their stories show the impact your donations have on kids in your community. Watch the video to learn about this inspiring group of National Champions! #changekidshealth

Extra Life

11,212 Aufrufe • vor 1 Jahr

Only Reform UK is taking the cost of living seriously as an issue. This is our plan to cut your energy bills if we win the next election. 👇

Only Reform UK is taking the cost of living seriously as an issue. This is our plan to cut your energy bills if we win the next election. 👇

Reform UK

12,137 Aufrufe • vor 4 Monaten

Exciting News from Open-Sora! 🚀 They've just made the ENTIRE suite of their video-generation model open source! Dive into the world of cutting-edge AI with access to model weights, comprehensive training source code, and detailed architecture insights. Start building your dream video-generation model today! Check it out 👉

Exciting News from Open-Sora! 🚀 They've just made the ENTIRE suite of their video-generation model open source! Dive into the world of cutting-edge AI with access to model weights, comprehensive training source code, and detailed architecture insights. Start building your dream video-generation model today! Check it out 👉

Yang You

245,742 Aufrufe • vor 2 Jahren

Exciting news just in 🔥! Neuroni AI is thrilled to announce we will be integrating "Sora by OpenAI" for video generation into our ecosystem the moment it becomes available. And guess what? We're offering this incredible tool absolutely FREE for our token holders! Why are we doing this? Because we believe "Sora" represents a groundbreaking leap forward in video development technology, and it aligns perfectly with Neuroni #AI's vision without competing with our development goals. We're passionate about ensuring our community gets first dibs on this advanced technology. Stay tuned for the future of video creation, powered by "#Sora" and brought to you by #Neuroni AI! $ETH #Crypto #AI #OpenAI

Exciting news just in 🔥! Neuroni AI is thrilled to announce we will be integrating "Sora by OpenAI" for video generation into our ecosystem the moment it becomes available. And guess what? We're offering this incredible tool absolutely FREE for our token holders! Why are we doing this? Because we believe "Sora" represents a groundbreaking leap forward in video development technology, and it aligns perfectly with Neuroni #AI's vision without competing with our development goals. We're passionate about ensuring our community gets first dibs on this advanced technology. Stay tuned for the future of video creation, powered by "#Sora" and brought to you by #Neuroni AI! $ETH #Crypto #AI #OpenAI

Neuroni AI

19,004 Aufrufe • vor 2 Jahren

Virgin Galactic is revolutionizing the operating model and economics of human spaceflight. To improve the clarity and quality of information available to our large retail investor base, we made a video presenting our multi-year growth plan and business model. We encourage our investors and fans to watch and hear how we are creating value now, while laying the foundation for substantial growth in the years to come!

Virgin Galactic is revolutionizing the operating model and economics of human spaceflight. To improve the clarity and quality of information available to our large retail investor base, we made a video presenting our multi-year growth plan and business model. We encourage our investors and fans to watch and hear how we are creating value now, while laying the foundation for substantial growth in the years to come!

Virgin Galactic

32,094 Aufrufe • vor 1 Jahr

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

367,000 Aufrufe • vor 1 Jahr

We developed an RL method for fine-tuning our models for precise tasks in just a few hours or even minutes. Instead of training the whole model, we add an “RL token” output to π-0.6, our latest model, which is used by a tiny actor and critic to learn quickly with RL.

We developed an RL method for fine-tuning our models for precise tasks in just a few hours or even minutes. Instead of training the whole model, we add an “RL token” output to π-0.6, our latest model, which is used by a tiny actor and critic to learn quickly with RL.

Physical Intelligence

434,203 Aufrufe • vor 4 Monaten

Google presents Still-Moving Customized Video Generation without Customized Video Data Customizing text-to-image (T2I) models has seen tremendous progress recently, particularly in areas such as personalization, stylization, and conditional generation. However, expanding this progress to video generation is still in its infancy, primarily due to the lack of customized video data. In this work, we introduce Still-Moving, a novel generic framework for customizing a text-to-video (T2V) model, without requiring any customized video data. The framework applies to the prominent T2V design where the video model is built over a text-to-image (T2I) model (e.g., via inflation). We assume access to a customized version of the T2I model, trained only on still image data (e.g., using DreamBooth or StyleDrop). Naively plugging in the weights of the customized T2I model into the T2V model often leads to significant artifacts or insufficient adherence to the customization data. To overcome this issue, we train lightweight Spatial Adapters that adjust the features produced by the injected T2I layers. Importantly, our adapters are trained on "frozen videos" (i.e., repeated images), constructed from image samples generated by the customized T2I model. This training is facilitated by a novel Motion Adapter module, which allows us to train on such static videos while preserving the motion prior of the video model. At test time, we remove the Motion Adapter modules and leave in only the trained Spatial Adapters. This restores the motion prior of the T2V model while adhering to the spatial prior of the customized T2I model. We demonstrate the effectiveness of our approach on diverse tasks including personalized, stylized, and conditional generation. In all evaluated scenarios, our method seamlessly integrates the spatial prior of the customized T2I model with a motion prior supplied by the T2V model.

Google presents Still-Moving Customized Video Generation without Customized Video Data Customizing text-to-image (T2I) models has seen tremendous progress recently, particularly in areas such as personalization, stylization, and conditional generation. However, expanding this progress to video generation is still in its infancy, primarily due to the lack of customized video data. In this work, we introduce Still-Moving, a novel generic framework for customizing a text-to-video (T2V) model, without requiring any customized video data. The framework applies to the prominent T2V design where the video model is built over a text-to-image (T2I) model (e.g., via inflation). We assume access to a customized version of the T2I model, trained only on still image data (e.g., using DreamBooth or StyleDrop). Naively plugging in the weights of the customized T2I model into the T2V model often leads to significant artifacts or insufficient adherence to the customization data. To overcome this issue, we train lightweight Spatial Adapters that adjust the features produced by the injected T2I layers. Importantly, our adapters are trained on "frozen videos" (i.e., repeated images), constructed from image samples generated by the customized T2I model. This training is facilitated by a novel Motion Adapter module, which allows us to train on such static videos while preserving the motion prior of the video model. At test time, we remove the Motion Adapter modules and leave in only the trained Spatial Adapters. This restores the motion prior of the T2V model while adhering to the spatial prior of the customized T2I model. We demonstrate the effectiveness of our approach on diverse tasks including personalized, stylized, and conditional generation. In all evaluated scenarios, our method seamlessly integrates the spatial prior of the customized T2I model with a motion prior supplied by the T2V model.

AK

40,474 Aufrufe • vor 2 Jahren

4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models Contributions: • We introduce 4D LangSplat for open-vocabulary 4D spatial-temporal queries. To the best of our knowledge, we are the first to construct 4D language fields with object textual captions generated by MLLMs. • To model smooth transitions across states for objects in 4D scenes, we propose a status deformable network to capture continuous temporal changes. • Experiential results show that our method attains state-of-the-art performance for both time-agnostic and time-sensitive open-vocabulary queries.

4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models Contributions: • We introduce 4D LangSplat for open-vocabulary 4D spatial-temporal queries. To the best of our knowledge, we are the first to construct 4D language fields with object textual captions generated by MLLMs. • To model smooth transitions across states for objects in 4D scenes, we propose a status deformable network to capture continuous temporal changes. • Experiential results show that our method attains state-of-the-art performance for both time-agnostic and time-sensitive open-vocabulary queries.

MrNeRF

10,953 Aufrufe • vor 1 Jahr

Jensen Huang open-sourced NVIDIA's flagship AI model, its weights, its data, AND how they created it. "We open sourced the models," Huang says. "We open sourced the weights." "We open sourced the data." "We open sourced how we created it." Four layers of openness in one model release. "Open source is fundamentally necessary for many industries to join the AI revolution." "NVIDIA has the scale and the motivation to build and continue to build these AI models for as long as we shall live." The chip seller benefits when every model is open. NVIDIA is the chip seller. P.S. I made a playbook breaking down 100+ most powerful decision making mental models used by history's greatest thinkers. 5,000+ downloads. 113 five-star reviews. Grab a free copy here: If you're new here, follow GeniusThinking for content on the greatest minds in economics, psychology, and history. — Jensen Huang ( NVIDIA ), NVIDIA CEO, on Lex Fridman's ( Lex Fridman ) podcast

Jensen Huang open-sourced NVIDIA's flagship AI model, its weights, its data, AND how they created it. "We open sourced the models," Huang says. "We open sourced the weights." "We open sourced the data." "We open sourced how we created it." Four layers of openness in one model release. "Open source is fundamentally necessary for many industries to join the AI revolution." "NVIDIA has the scale and the motivation to build and continue to build these AI models for as long as we shall live." The chip seller benefits when every model is open. NVIDIA is the chip seller. P.S. I made a playbook breaking down 100+ most powerful decision making mental models used by history's greatest thinkers. 5,000+ downloads. 113 five-star reviews. Grab a free copy here: If you're new here, follow GeniusThinking for content on the greatest minds in economics, psychology, and history. — Jensen Huang ( NVIDIA ), NVIDIA CEO, on Lex Fridman's ( Lex Fridman ) podcast

GeniusThinking

14,769 Aufrufe • vor 1 Monat

The U.N.’s goal of reducing carbon emissions to “net zero” by 2050 is ambitious. But is it plausible? Our video explores the history (and possible futures) of how we power the world.

The U.N.’s goal of reducing carbon emissions to “net zero” by 2050 is ambitious. But is it plausible? Our video explores the history (and possible futures) of how we power the world.

Kite & Key Media

478,697 Aufrufe • vor 9 Monaten