Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

🖼️🎞️🔊📄Excited to introduce Composable Diffusion (CoDi), a new generative-AI foundation model that can take any combo of input modalities & generate any combo of output modalities (text, audio, image, video)! Ziyi Yang Chenguang Zhu Mohit Bansal 🧵👇 #CoDi

Zineng Tang

1,642 subscribers

105,290 görüntüleme • 3 yıl önce •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

🔥Excited to introduce CoDi-2! It follows complex multimodal-interleaved in-context instructions to generate any modalities (text, vision, audio) in zero/few-shot interactive way! Ziyi Yang Yang Liu Chenguang Zhu Mohit Bansal 🧵👇

🔥Excited to introduce CoDi-2! It follows complex multimodal-interleaved in-context instructions to generate any modalities (text, vision, audio) in zero/few-shot interactive way! Ziyi Yang Yang Liu Chenguang Zhu Mohit Bansal 🧵👇

Zineng Tang

97,568 görüntüleme • 2 yıl önce

Announcing Genmo Video, a generative media platform with a new text-to-video model that can generate immersive live artwork from any prompt or any image. What will you create? 🎨▶️ Free public access: Discord: 👇1/n

Announcing Genmo Video, a generative media platform with a new text-to-video model that can generate immersive live artwork from any prompt or any image. What will you create? 🎨▶️ Free public access: Discord: 👇1/n

Genmo

94,704 görüntüleme • 3 yıl önce

We asked Logan Kilpatrick what stood out most from Google I/O. His answer: Gemini Omni, Google's new multimodal AI model. "The model can take in any input and produce any output. Text, audio, video, image." "You get a bunch of really interesting capability transfer when you bring it all into a single model." Right now the killer use case is video editing. "It's like having a VFX studio on demand."

We asked Logan Kilpatrick what stood out most from Google I/O. His answer: Gemini Omni, Google's new multimodal AI model. "The model can take in any input and produce any output. Text, audio, video, image." "You get a bunch of really interesting capability transfer when you bring it all into a single model." Right now the killer use case is video editing. "It's like having a VFX studio on demand."

MTS

18,884 görüntüleme • 2 ay önce

TokenFlow: Consistent Diffusion Features for Consistent Video Editing paper page: The generative AI revolution has recently expanded to videos. Nevertheless, current state-of-the-art video models are still lagging behind image models in terms of visual quality and user control over the generated content. In this work, we present a framework that harnesses the power of a text-to-image diffusion model for the task of text-driven video editing. Specifically, given a source video and a target text-prompt, our method generates a high-quality video that adheres to the target text, while preserving the spatial layout and motion of the input video. Our method is based on a key observation that consistency in the edited video can be obtained by enforcing consistency in the diffusion feature space. We achieve this by explicitly propagating diffusion features based on inter-frame correspondences, readily available in the model. Thus, our framework does not require any training or fine-tuning, and can work in conjunction with any off-the-shelf text-to-image editing method. We demonstrate state-of-the-art editing results on a variety of real-world videos.

TokenFlow: Consistent Diffusion Features for Consistent Video Editing paper page: The generative AI revolution has recently expanded to videos. Nevertheless, current state-of-the-art video models are still lagging behind image models in terms of visual quality and user control over the generated content. In this work, we present a framework that harnesses the power of a text-to-image diffusion model for the task of text-driven video editing. Specifically, given a source video and a target text-prompt, our method generates a high-quality video that adheres to the target text, while preserving the spatial layout and motion of the input video. Our method is based on a key observation that consistency in the edited video can be obtained by enforcing consistency in the diffusion feature space. We achieve this by explicitly propagating diffusion features based on inter-frame correspondences, readily available in the model. Thus, our framework does not require any training or fine-tuning, and can work in conjunction with any off-the-shelf text-to-image editing method. We demonstrate state-of-the-art editing results on a variety of real-world videos.

AK

143,469 görüntüleme • 3 yıl önce

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:

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

1,024,571 görüntüleme • 2 yıl önce

Meta presents Video Editing via Factorized Diffusion Distillation We introduce Emu Video Edit (EVE), a model that establishes a new state-of-the art in video editing without relying on any supervised video editing data. To develop EVE we separately train an image editing

Meta presents Video Editing via Factorized Diffusion Distillation We introduce Emu Video Edit (EVE), a model that establishes a new state-of-the art in video editing without relying on any supervised video editing data. To develop EVE we separately train an image editing

AK

115,598 görüntüleme • 2 yıl önce

As you know, my explorations of the Gen AI space is ultimately all about creative control. You should be able to shape the generative matter using all your artistic sensibilities and your aesthetic sense. OpenAI's Sora is a huge technological leap, but what excites me the most about it is the modalities where it depends on input other than text alone. Such as video to video. Here's an example of how Sora can change an input video. Base video🧵

As you know, my explorations of the Gen AI space is ultimately all about creative control. You should be able to shape the generative matter using all your artistic sensibilities and your aesthetic sense. OpenAI's Sora is a huge technological leap, but what excites me the most about it is the modalities where it depends on input other than text alone. Such as video to video. Here's an example of how Sora can change an input video. Base video🧵

Martin Nebelong

7,520,229 görüntüleme • 2 yıl önce

As part of Meta Movie Gen, we trained a 13B parameter audio generation model that can take a video + optional text prompts to generate high quality audio — including ambient sound, foley & instrumental background music — all synced to the video. Details ➡️

As part of Meta Movie Gen, we trained a 13B parameter audio generation model that can take a video + optional text prompts to generate high quality audio — including ambient sound, foley & instrumental background music — all synced to the video. Details ➡️

AI at Meta

76,692 görüntüleme • 1 yıl önce

Introducing group chat on Poe: a new way to collaborate with any AI and anyone you know, all in a single conversation. Now available to all users worldwide, groups can interact with any of the 200+ text, image, video, or audio models on Poe, plus any creator-made bots. (1/8)

Introducing group chat on Poe: a new way to collaborate with any AI and anyone you know, all in a single conversation. Now available to all users worldwide, groups can interact with any of the 200+ text, image, video, or audio models on Poe, plus any creator-made bots. (1/8)

Poe

21,828 görüntüleme • 8 ay önce

🎥 Today we’re premiering Meta Movie Gen: the most advanced media foundation models to-date. Developed by AI research teams at Meta, Movie Gen delivers state-of-the-art results across a range of capabilities. We’re excited for the potential of this line of research to usher in entirely new possibilities for casual creators and creative professionals alike. More details and examples of what Movie Gen can do ➡️ 🛠️ Movie Gen models and capabilities Movie Gen Video: 30B parameter transformer model that can generate high-quality and high-definition images and videos from a single text prompt. Movie Gen Audio: A 13B parameter transformer model that can take a video input along with optional text prompts for controllability to generate high-fidelity audio synced to the video. It can generate ambient sound, instrumental background music and foley sound — delivering state-of-the-art results in audio quality, video-to-audio alignment and text-to-audio alignment. Precise video editing: Using a generated or existing video and accompanying text instructions as an input it can perform localized edits such as adding, removing or replacing elements — or global changes like background or style changes. Personalized videos: Using an image of a person and a text prompt, the model can generate a video with state-of-the-art results on character preservation and natural movement in video. We’re continuing to work closely with creative professionals from across the field to integrate their feedback as we work towards a potential release. We look forward to sharing more on this work and the creative possibilities it will enable in the future.

🎥 Today we’re premiering Meta Movie Gen: the most advanced media foundation models to-date. Developed by AI research teams at Meta, Movie Gen delivers state-of-the-art results across a range of capabilities. We’re excited for the potential of this line of research to usher in entirely new possibilities for casual creators and creative professionals alike. More details and examples of what Movie Gen can do ➡️ 🛠️ Movie Gen models and capabilities Movie Gen Video: 30B parameter transformer model that can generate high-quality and high-definition images and videos from a single text prompt. Movie Gen Audio: A 13B parameter transformer model that can take a video input along with optional text prompts for controllability to generate high-fidelity audio synced to the video. It can generate ambient sound, instrumental background music and foley sound — delivering state-of-the-art results in audio quality, video-to-audio alignment and text-to-audio alignment. Precise video editing: Using a generated or existing video and accompanying text instructions as an input it can perform localized edits such as adding, removing or replacing elements — or global changes like background or style changes. Personalized videos: Using an image of a person and a text prompt, the model can generate a video with state-of-the-art results on character preservation and natural movement in video. We’re continuing to work closely with creative professionals from across the field to integrate their feedback as we work towards a potential release. We look forward to sharing more on this work and the creative possibilities it will enable in the future.

AI at Meta

2,265,265 görüntüleme • 1 yıl önce

🚀 Today Photoroom is announcing the next generation of AI photo-editing features. 🚀 We’re dropping 5 new AI features, including a text-to-image model, generative fill, and our new-and-improved AI backgrounds, plus launching the world’s first foundation model trained specifically for product photography. 🖼️ AI Images: Use AI to generate high-quality images from scratch. Create anything you can imagine, at the click of a button. 💗 AI Expand: Use generative AI to realistically expand the scene around your image. 🎑 AI Backgrounds: Generate stunningly realistic AI backgrounds for product photos. ⏳ AI Fill: Take total control of your AI images, by customizing an item or area of the picture. 🔄 Auto-rotate: Correct your camera angle with AI for more professional results. 🔎 AI Upscale: Get better quality images by enhancing the resolution of your images. If our 6x feature drop wasn’t enough, we also just closed our series B funding round, to the tune of $43 million 🎤 #Photoroom #generativeAI #AI #productphotography #ecommerce

🚀 Today Photoroom is announcing the next generation of AI photo-editing features. 🚀 We’re dropping 5 new AI features, including a text-to-image model, generative fill, and our new-and-improved AI backgrounds, plus launching the world’s first foundation model trained specifically for product photography. 🖼️ AI Images: Use AI to generate high-quality images from scratch. Create anything you can imagine, at the click of a button. 💗 AI Expand: Use generative AI to realistically expand the scene around your image. 🎑 AI Backgrounds: Generate stunningly realistic AI backgrounds for product photos. ⏳ AI Fill: Take total control of your AI images, by customizing an item or area of the picture. 🔄 Auto-rotate: Correct your camera angle with AI for more professional results. 🔎 AI Upscale: Get better quality images by enhancing the resolution of your images. If our 6x feature drop wasn’t enough, we also just closed our series B funding round, to the tune of $43 million 🎤 #Photoroom #generativeAI #AI #productphotography #ecommerce

Photoroom

22,236 görüntüleme • 2 yıl önce

TurboEdit Instant text-based image editing discuss: We address the challenges of precise image inversion and disentangled image editing in the context of few-step diffusion models. We introduce an encoder based iterative inversion technique. The inversion network is conditioned on the input image and the reconstructed image from the previous step, allowing for correction of the next reconstruction towards the input image. We demonstrate that disentangled controls can be easily achieved in the few-step diffusion model by conditioning on an (automatically generated) detailed text prompt. To manipulate the inverted image, we freeze the noise maps and modify one attribute in the text prompt (either manually or via instruction based editing driven by an LLM), resulting in the generation of a new image similar to the input image with only one attribute changed. It can further control the editing strength and accept instructive text prompt. Our approach facilitates realistic text-guided image edits in real-time, requiring only 8 number of functional evaluations (NFEs) in inversion (one-time cost) and 4 NFEs per edit. Our method is not only fast, but also significantly outperforms state-of-the-art multi-step diffusion editing techniques.

TurboEdit Instant text-based image editing discuss: We address the challenges of precise image inversion and disentangled image editing in the context of few-step diffusion models. We introduce an encoder based iterative inversion technique. The inversion network is conditioned on the input image and the reconstructed image from the previous step, allowing for correction of the next reconstruction towards the input image. We demonstrate that disentangled controls can be easily achieved in the few-step diffusion model by conditioning on an (automatically generated) detailed text prompt. To manipulate the inverted image, we freeze the noise maps and modify one attribute in the text prompt (either manually or via instruction based editing driven by an LLM), resulting in the generation of a new image similar to the input image with only one attribute changed. It can further control the editing strength and accept instructive text prompt. Our approach facilitates realistic text-guided image edits in real-time, requiring only 8 number of functional evaluations (NFEs) in inversion (one-time cost) and 4 NFEs per edit. Our method is not only fast, but also significantly outperforms state-of-the-art multi-step diffusion editing techniques.

AK

16,062 görüntüleme • 1 yıl önce

I found an app combo that makes my audio quality basically perfect in every app – OBS, Zoom, whatever. 1. Audio Hijack – lets me add effects to my actual mic input 2. Loopback – turns the output from Audio Hijack into a virtual input device This lets you use the virtual device as your input in any other app. You can even set it as your whole system's default input. Result: Perfect audio at the time of recording, in any app. I went down a rabbit hole to set this up because I was tired of my Loom recordings sounding so much worse than my YouTube videos. But this also solved issues in OBS, which doesn't support all of my audio plugins for some reason. I'm so pleased the result that I had to shoot a little video on it:

I found an app combo that makes my audio quality basically perfect in every app – OBS, Zoom, whatever. 1. Audio Hijack – lets me add effects to my actual mic input 2. Loopback – turns the output from Audio Hijack into a virtual input device This lets you use the virtual device as your input in any other app. You can even set it as your whole system's default input. Result: Perfect audio at the time of recording, in any app. I went down a rabbit hole to set this up because I was tired of my Loom recordings sounding so much worse than my YouTube videos. But this also solved issues in OBS, which doesn't support all of my audio plugins for some reason. I'm so pleased the result that I had to shoot a little video on it:

Thomas Frank

41,604 görüntüleme • 9 ay önce

In Prompt Engineering for Vision Models, taught by Abby Jacques Verre and Caleb Kaiser of Comet , you’ll learn how to prompt and fine-tune vision models for personalized image generation, image editing, object detection and segmentation. The prompts you'll use for vision models could be text, point coordinates, or bounding boxes, depending on the model. You'll also learn to tune hyperparameters to shape the output. Models you'll use include Segment-Anything Model (SAM), OWL-ViT, and Stable Diffusion. You'll also learn to fine-tune Stable Diffusion to generate personalized images (say, an image of a specific person), using a handful of images for training. As an example of a multi-step workflow, you'll use OWL-ViT to detect an object based on a text prompt, then pass the bounding box to SAM to create a segmentation mask, and input that mask into Stable Diffusion to replace the original object with a new one based on a text prompt. Controlling vision models can be tricky; this course will teach prompting and fine-tuning techniques to get precise control over their output. Get started here:

In Prompt Engineering for Vision Models, taught by Abby Jacques Verre and Caleb Kaiser of Comet , you’ll learn how to prompt and fine-tune vision models for personalized image generation, image editing, object detection and segmentation. The prompts you'll use for vision models could be text, point coordinates, or bounding boxes, depending on the model. You'll also learn to tune hyperparameters to shape the output. Models you'll use include Segment-Anything Model (SAM), OWL-ViT, and Stable Diffusion. You'll also learn to fine-tune Stable Diffusion to generate personalized images (say, an image of a specific person), using a handful of images for training. As an example of a multi-step workflow, you'll use OWL-ViT to detect an object based on a text prompt, then pass the bounding box to SAM to create a segmentation mask, and input that mask into Stable Diffusion to replace the original object with a new one based on a text prompt. Controlling vision models can be tricky; this course will teach prompting and fine-tuning techniques to get precise control over their output. Get started here:

Andrew Ng

151,198 görüntüleme • 2 yıl önce

Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation paper page: Recent advances in generative modeling have led to promising progress on synthesizing 3D human motion from text, with methods that can generate character animations from short prompts and specified durations. However, using a single text prompt as input lacks the fine-grained control needed by animators, such as composing multiple actions and defining precise durations for parts of the motion. To address this, we introduce the new problem of timeline control for text-driven motion synthesis, which provides an intuitive, yet fine-grained, input interface for users. Instead of a single prompt, users can specify a multi-track timeline of multiple prompts organized in temporal intervals that may overlap. This enables specifying the exact timings of each action and composing multiple actions in sequence or at overlapping intervals. To generate composite animations from a multi-track timeline, we propose a new test-time denoising method. This method can be integrated with any pre-trained motion diffusion model to synthesize realistic motions that accurately reflect the timeline. At every step of denoising, our method processes each timeline interval (text prompt) individually, subsequently aggregating the predictions with consideration for the specific body parts engaged in each action. Experimental comparisons and ablations validate that our method produces realistic motions that respect the semantics and timing of given text prompts.

Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation paper page: Recent advances in generative modeling have led to promising progress on synthesizing 3D human motion from text, with methods that can generate character animations from short prompts and specified durations. However, using a single text prompt as input lacks the fine-grained control needed by animators, such as composing multiple actions and defining precise durations for parts of the motion. To address this, we introduce the new problem of timeline control for text-driven motion synthesis, which provides an intuitive, yet fine-grained, input interface for users. Instead of a single prompt, users can specify a multi-track timeline of multiple prompts organized in temporal intervals that may overlap. This enables specifying the exact timings of each action and composing multiple actions in sequence or at overlapping intervals. To generate composite animations from a multi-track timeline, we propose a new test-time denoising method. This method can be integrated with any pre-trained motion diffusion model to synthesize realistic motions that accurately reflect the timeline. At every step of denoising, our method processes each timeline interval (text prompt) individually, subsequently aggregating the predictions with consideration for the specific body parts engaged in each action. Experimental comparisons and ablations validate that our method produces realistic motions that respect the semantics and timing of given text prompts.

AK

126,595 görüntüleme • 2 yıl önce

Generative video models are rapidly improving in quality. Meet Replay, a new AI model that can generate stunning videos from text. Replay v0.1 is designed to create ultrasmooth HD videos with a new interface. Available today for everyone. What's New? 1. Replay understands plain English prompts without prompt engineering. Try "rugged surfer" or "mermaid". 2. What's a movie without actors? Replay can crisply render close-ups of people and animals. 3. Free and fast generation from our homepage with no waiting list (link in bio). Behind the scenes, Replay is powered by aligning our new diffusion model for videos with the LLM behind Genmo Chat. We’re so excited to see what you create! Share your creations below👇

Generative video models are rapidly improving in quality. Meet Replay, a new AI model that can generate stunning videos from text. Replay v0.1 is designed to create ultrasmooth HD videos with a new interface. Available today for everyone. What's New? 1. Replay understands plain English prompts without prompt engineering. Try "rugged surfer" or "mermaid". 2. What's a movie without actors? Replay can crisply render close-ups of people and animals. 3. Free and fast generation from our homepage with no waiting list (link in bio). Behind the scenes, Replay is powered by aligning our new diffusion model for videos with the LLM behind Genmo Chat. We’re so excited to see what you create! Share your creations below👇

Genmo

154,603 görüntüleme • 2 yıl önce

"#AI will never create clean meshes" AI 👇 This is the new #AI model from NVIDIA called Meshtron (jeez what a name 😅). It generates meshes of complex 3D objects closely resembling those created by professional artists. It opens the door to a more realistic generation of detailed 3D assets for animation, gaming, and virtual environments. The current version accepts the following control inputs: - Point cloud: Determines the shape of the output mesh. - Face count: Determines the density of the output mesh. - Quad ratio: Switches between quad and triangle tessellation. - Creativity: Can be adjusted to generate extra details in the model. Meshtron can either serve as a stand-alone remesher to improve the quality of existing models, or be used in tandem with a text-to-3D or image-to-3D model to generate artist-grade meshes from scratch.

"#AI will never create clean meshes" AI 👇 This is the new #AI model from NVIDIA called Meshtron (jeez what a name 😅). It generates meshes of complex 3D objects closely resembling those created by professional artists. It opens the door to a more realistic generation of detailed 3D assets for animation, gaming, and virtual environments. The current version accepts the following control inputs: - Point cloud: Determines the shape of the output mesh. - Face count: Determines the density of the output mesh. - Quad ratio: Switches between quad and triangle tessellation. - Creativity: Can be adjusted to generate extra details in the model. Meshtron can either serve as a stand-alone remesher to improve the quality of existing models, or be used in tandem with a text-to-3D or image-to-3D model to generate artist-grade meshes from scratch.

Gabriele Romagnoli

2,177,047 görüntüleme • 1 yıl önce

The reception since we launched the first unified audio + text + image to video model in production last week has been incredible! We wanted to take a moment and highlight some firsts: - the first omnimodal modal that jointly operates over text, image, and audio. Fun fact: we shipped our first audio-to-video model Character-1 last June! - Character-3 is generating 5 minute uncut clips, and capable of temporally stable longform prediction. - Character-3 handles realistic humans, cartoons, side profiles, dynamic backgrounds, anime, animals, and more. - Character-3 sets a new standard for fast & efficient video diffusion at HD and SD resolutions, leveraging our advancements in realtime video generation. We'll have an announcement soon, but you can read more about an earlier version of this line of work in our paper here:

The reception since we launched the first unified audio + text + image to video model in production last week has been incredible! We wanted to take a moment and highlight some firsts: - the first omnimodal modal that jointly operates over text, image, and audio. Fun fact: we shipped our first audio-to-video model Character-1 last June! - Character-3 is generating 5 minute uncut clips, and capable of temporally stable longform prediction. - Character-3 handles realistic humans, cartoons, side profiles, dynamic backgrounds, anime, animals, and more. - Character-3 sets a new standard for fast & efficient video diffusion at HD and SD resolutions, leveraging our advancements in realtime video generation. We'll have an announcement soon, but you can read more about an earlier version of this line of work in our paper here:

Hedra

180,676 görüntüleme • 1 yıl önce

StyleDrop: Text-to-Image Generation in Any Style introduce StyleDrop, a method that enables the synthesis of images that faithfully follow a specific style using a text-to-image model. The proposed method is extremely versatile and captures nuances and details of a user-provided style, such as color schemes, shading, design patterns, and local and global effects. It efficiently learns a new style by fine-tuning very few trainable parameters (less than 1% of total model parameters) and improving the quality via iterative training with either human or automated feedback. Better yet, StyleDrop is able to deliver impressive results even when the user supplies only a single image that specifies the desired style. An extensive study shows that, for the task of style tuning text-to-image models, StyleDrop implemented on Muse convincingly outperforms other methods, including DreamBooth and textual inversion on Imagen or Stable Diffusion. paper page:

StyleDrop: Text-to-Image Generation in Any Style introduce StyleDrop, a method that enables the synthesis of images that faithfully follow a specific style using a text-to-image model. The proposed method is extremely versatile and captures nuances and details of a user-provided style, such as color schemes, shading, design patterns, and local and global effects. It efficiently learns a new style by fine-tuning very few trainable parameters (less than 1% of total model parameters) and improving the quality via iterative training with either human or automated feedback. Better yet, StyleDrop is able to deliver impressive results even when the user supplies only a single image that specifies the desired style. An extensive study shows that, for the task of style tuning text-to-image models, StyleDrop implemented on Muse convincingly outperforms other methods, including DreamBooth and textual inversion on Imagen or Stable Diffusion. paper page:

AK

56,377 görüntüleme • 3 yıl önce

Google presents Genie Generative Interactive Environments introduce Genie, the first generative interactive environment trained in an unsupervised manner from unlabelled Internet videos. The model can be prompted to generate an endless variety of action-controllable virtual worlds described through text, synthetic images, photographs, and even sketches. At 11B parameters, Genie can be considered a foundation world model. It is comprised of a spatiotemporal video tokenizer, an autoregressive dynamics model, and a simple and scalable latent action model. Genie enables users to act in the generated environments on a frame-by-frame basis despite training without any ground-truth action labels or other domain-specific requirements typically found in the world model literature. Further the resulting learned latent action space facilitates training agents to imitate behaviors from unseen videos, opening the path for training generalist agents of the future.

Google presents Genie Generative Interactive Environments introduce Genie, the first generative interactive environment trained in an unsupervised manner from unlabelled Internet videos. The model can be prompted to generate an endless variety of action-controllable virtual worlds described through text, synthetic images, photographs, and even sketches. At 11B parameters, Genie can be considered a foundation world model. It is comprised of a spatiotemporal video tokenizer, an autoregressive dynamics model, and a simple and scalable latent action model. Genie enables users to act in the generated environments on a frame-by-frame basis despite training without any ground-truth action labels or other domain-specific requirements typically found in the world model literature. Further the resulting learned latent action space facilitates training agents to imitate behaviors from unseen videos, opening the path for training generalist agents of the future.

AK

684,372 görüntüleme • 2 yıl önce