正在加载视频...

视频加载失败

返回首页

Make Pixels Dance: High-Dynamic Video Generation paper page: Creating high-dynamic videos such as motion-rich actions and sophisticated visual effects poses a significant challenge in the field of artificial intelligence. Unfortunately, current state-of-the-art video generation methods, primarily focusing on text-to-video generation, tend to produce video clips with minimal motions despite...

_akhaliq's profile picture

AK

503,030 subscribers

101,655 次观看 • 2 年前 •via X (Twitter)

科学技术教育
LIVE

Anya Rossi• Live Now

Private livecam show

3 条评论

Yan Zeng 的头像
Yan Zeng2 年前

Thanks! Project website: <- More cases, like this ->

Yan Zeng 的头像
Yan Zeng2 年前

Remix | PixelDance（with music😆）

Ajeya 的头像
Ajeya2 年前

Impressive research! The PixelDance approach seems to be a promising step towards overcoming the challenge of generating high-dynamic videos in AI.

相关视频

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
0:30

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 次观看 • 1 年前

Collaborative Video Diffusion Consistent Multi-video Generation with Camera Control Research on video generation has recently made tremendous progress, enabling high-quality videos to be generated from text prompts or images. Adding control to the video generation
2:16

Collaborative Video Diffusion Consistent Multi-video Generation with Camera Control Research on video generation has recently made tremendous progress, enabling high-quality videos to be generated from text prompts or images. Adding control to the video generation

AK

29,262 次观看 • 2 年前

Today we’re sharing two new advances in our generative AI research: Emu Video & Emu Edit. Details ➡️ These new models deliver exciting results in high quality, diffusion-based text-to-video generation & controlled image editing w/ text instructions. 🧵
0:33

Today we’re sharing two new advances in our generative AI research: Emu Video & Emu Edit. Details ➡️ These new models deliver exciting results in high quality, diffusion-based text-to-video generation & controlled image editing w/ text instructions. 🧵

AI at Meta

798,183 次观看 • 2 年前

We introduce W.A.L.T, a diffusion model for photorealistic video generation. Our model is a transformer trained on image and video generation in a shared latent space. 🧵👇
0:43

We introduce W.A.L.T, a diffusion model for photorealistic video generation. Our model is a transformer trained on image and video generation in a shared latent space. 🧵👇

Agrim Gupta

431,113 次观看 • 2 年前

We have released an update for both text to video and image to video generation with Gen-2, bringing major improvements to both the fidelity and consistency of video results. Try it now at
1:15

We have released an update for both text to video and image to video generation with Gen-2, bringing major improvements to both the fidelity and consistency of video results. Try it now at

Runway

601,381 次观看 • 2 年前

Struggling with slow inference of diffusion and flow models? Check out the video below—I’ve been using our new FastGen library to achieve 7-28x acceleration for text-2-image and {text,image,video}-2-video generation without sacrificing visual fidelity!
2:20

Struggling with slow inference of diffusion and flow models? Check out the video below—I’ve been using our new FastGen library to achieve 7-28x acceleration for text-2-image and {text,image,video}-2-video generation without sacrificing visual fidelity!

Julius Berner

13,604 次观看 • 4 个月前

DisCo: Disentangled Control for Referring Human Dance Generation in Real World paper page: Generative AI has made significant strides in computer vision, particularly in image/video synthesis conditioned on text descriptions. Despite the advancements, it remains challenging especially in the generation of human-centric content such as dance synthesis. Existing dance synthesis methods struggle with the gap between synthesized content and real-world dance scenarios. In this paper, we define a new problem setting: Referring Human Dance Generation, which focuses on real-world dance scenarios with three important properties: (i) Faithfulness: the synthesis should retain the appearance of both human subject foreground and background from the reference image, and precisely follow the target pose; (ii) Generalizability: the model should generalize to unseen human subjects, backgrounds, and poses; (iii) Compositionality: it should allow for composition of seen/unseen subjects, backgrounds, and poses from different sources. To address these challenges, we introduce a novel approach, DISCO, which includes a novel model architecture with disentangled control to improve the faithfulness and compositionality of dance synthesis, and an effective human attribute pre-training for better generalizability to unseen humans. Extensive qualitative and quantitative results demonstrate that DISCO can generate high-quality human dance images and videos with diverse appearances and flexible motions.
0:29

DisCo: Disentangled Control for Referring Human Dance Generation in Real World paper page: Generative AI has made significant strides in computer vision, particularly in image/video synthesis conditioned on text descriptions. Despite the advancements, it remains challenging especially in the generation of human-centric content such as dance synthesis. Existing dance synthesis methods struggle with the gap between synthesized content and real-world dance scenarios. In this paper, we define a new problem setting: Referring Human Dance Generation, which focuses on real-world dance scenarios with three important properties: (i) Faithfulness: the synthesis should retain the appearance of both human subject foreground and background from the reference image, and precisely follow the target pose; (ii) Generalizability: the model should generalize to unseen human subjects, backgrounds, and poses; (iii) Compositionality: it should allow for composition of seen/unseen subjects, backgrounds, and poses from different sources. To address these challenges, we introduce a novel approach, DISCO, which includes a novel model architecture with disentangled control to improve the faithfulness and compositionality of dance synthesis, and an effective human attribute pre-training for better generalizability to unseen humans. Extensive qualitative and quantitative results demonstrate that DISCO can generate high-quality human dance images and videos with diverse appearances and flexible motions.

AK

161,453 次观看 • 2 年前

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.
0:51

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

366,858 次观看 • 1 年前

Gen-3 Alpha Text to Video is now available to everyone. A new frontier for high-fidelity, fast and controllable video generation. Try it now at
2:22

Gen-3 Alpha Text to Video is now available to everyone. A new frontier for high-fidelity, fast and controllable video generation. Try it now at

Runway

4,065,561 次观看 • 1 年前

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.
1:43

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

40,467 次观看 • 1 年前

Introducing Dream Machine - a next generation video model for creating high quality, realistic shots from text instructions and images using AI. It’s available to everyone today! Try for free here #LumaDreamMachine
0:33

Introducing Dream Machine - a next generation video model for creating high quality, realistic shots from text instructions and images using AI. It’s available to everyone today! Try for free here #LumaDreamMachine

Luma

2,476,770 次观看 • 2 年前

As detailed in the Meta Movie Gen technical report, today we’re open sourcing Movie Gen Bench: two new media generation benchmarks that we hope will help to enable the AI research community to progress work on more capable audio and video generation models. Movie Gen Video Bench is the largest and most comprehensive benchmark ever released for evaluating text-to-video generation. It includes a collection of 1,000+ prompts that cover concepts ranging from detailed human activity to animals, physics, unusual subjects and more — with broad coverage across different motion levels. Movie Gen Audio Bench is a first-of-its-kind benchmark aimed at evaluating video-to-audio and (text+video)-to-audio generation. It includes 527 generated videos and associated sound effects and music prompts covering a diverse set of ambient environments and sound effects. To enable fair and easy comparison to our models for future works, these new benchmarks include non cherry-picked generated videos and audio from Movie Gen. In releasing these new benchmarks we hope to promote fair & extensive evaluations in media generation research to enable greater progress in this field.
0:23

As detailed in the Meta Movie Gen technical report, today we’re open sourcing Movie Gen Bench: two new media generation benchmarks that we hope will help to enable the AI research community to progress work on more capable audio and video generation models. Movie Gen Video Bench is the largest and most comprehensive benchmark ever released for evaluating text-to-video generation. It includes a collection of 1,000+ prompts that cover concepts ranging from detailed human activity to animals, physics, unusual subjects and more — with broad coverage across different motion levels. Movie Gen Audio Bench is a first-of-its-kind benchmark aimed at evaluating video-to-audio and (text+video)-to-audio generation. It includes 527 generated videos and associated sound effects and music prompts covering a diverse set of ambient environments and sound effects. To enable fair and easy comparison to our models for future works, these new benchmarks include non cherry-picked generated videos and audio from Movie Gen. In releasing these new benchmarks we hope to promote fair & extensive evaluations in media generation research to enable greater progress in this field.

AI at Meta

156,240 次观看 • 1 年前

Glad to share Seaweed-7B, a cost-effective foundation model for video generation. Our tech report highlights the key designs that significantly improve compute efficiency and performance given limited resources, achieving comparable quality against other industry-level models. To unleash the power of the foundation model, Seaweed-7B further enables a wide range of downstream applications including image-to-video generation, human video generation, subject-consistent video generation, video-audio joint generation, long video generation and storytelling, real-time generation, super-resolution generation, camera controlled generation. Check out our webpage and report for more details: Webpage: Paper: It's a wonderful journey of the last year. Thanks to all teammates for their contributions, sincerely.
1:30

Glad to share Seaweed-7B, a cost-effective foundation model for video generation. Our tech report highlights the key designs that significantly improve compute efficiency and performance given limited resources, achieving comparable quality against other industry-level models. To unleash the power of the foundation model, Seaweed-7B further enables a wide range of downstream applications including image-to-video generation, human video generation, subject-consistent video generation, video-audio joint generation, long video generation and storytelling, real-time generation, super-resolution generation, camera controlled generation. Check out our webpage and report for more details: Webpage: Paper: It's a wonderful journey of the last year. Thanks to all teammates for their contributions, sincerely.

Ceyuan Yang

77,423 次观看 • 1 年前

SceneScape: Text-Driven Consistent Scene Generation abs: project page: text-driven perpetual view generation -- synthesizing long videos of arbitrary scenes solely from an input text describing the scene and camera poses
0:48

SceneScape: Text-Driven Consistent Scene Generation abs: project page: text-driven perpetual view generation -- synthesizing long videos of arbitrary scenes solely from an input text describing the scene and camera poses

AK

73,258 次观看 • 3 年前

Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution paper page: Text-based diffusion models have exhibited remarkable success in generation and editing, showing great promise for enhancing visual content with their generative prior. However, applying these models to video super-resolution remains challenging due to the high demands for output fidelity and temporal consistency, which is complicated by the inherent randomness in diffusion models. Our study introduces Upscale-A-Video, a text-guided latent diffusion framework for video upscaling. This framework ensures temporal coherence through two key mechanisms: locally, it integrates temporal layers into U-Net and VAE-Decoder, maintaining consistency within short sequences; globally, without training, a flow-guided recurrent latent propagation module is introduced to enhance overall video stability by propagating and fusing latent across the entire sequences. Thanks to the diffusion paradigm, our model also offers greater flexibility by allowing text prompts to guide texture creation and adjustable noise levels to balance restoration and generation, enabling a trade-off between fidelity and quality. Extensive experiments show that Upscale-A-Video surpasses existing methods in both synthetic and real-world benchmarks, as well as in AI-generated videos, showcasing impressive visual realism and temporal consistency.
1:45

Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution paper page: Text-based diffusion models have exhibited remarkable success in generation and editing, showing great promise for enhancing visual content with their generative prior. However, applying these models to video super-resolution remains challenging due to the high demands for output fidelity and temporal consistency, which is complicated by the inherent randomness in diffusion models. Our study introduces Upscale-A-Video, a text-guided latent diffusion framework for video upscaling. This framework ensures temporal coherence through two key mechanisms: locally, it integrates temporal layers into U-Net and VAE-Decoder, maintaining consistency within short sequences; globally, without training, a flow-guided recurrent latent propagation module is introduced to enhance overall video stability by propagating and fusing latent across the entire sequences. Thanks to the diffusion paradigm, our model also offers greater flexibility by allowing text prompts to guide texture creation and adjustable noise levels to balance restoration and generation, enabling a trade-off between fidelity and quality. Extensive experiments show that Upscale-A-Video surpasses existing methods in both synthetic and real-world benchmarks, as well as in AI-generated videos, showcasing impressive visual realism and temporal consistency.

AK

32,840 次观看 • 2 年前

📽️ Video generation is now live on Venice for all users Bring your imagination to life with state-of-the-art video generation models on Venice, including industry-leading models Sora 2 and Veo3.1
0:47

📽️ Video generation is now live on Venice for all users Bring your imagination to life with state-of-the-art video generation models on Venice, including industry-leading models Sora 2 and Veo3.1

Venice

80,293 次观看 • 7 个月前

New #NVIDIA Paper We introduce Motive, a motion-centric, gradient-based data attribution method that traces which training videos help or hurt video generation. By isolating temporal dynamics from static appearance, Motive identifies which training videos shape motion in video generation. 🔗 1/10
1:15

New #NVIDIA Paper We introduce Motive, a motion-centric, gradient-based data attribution method that traces which training videos help or hurt video generation. By isolating temporal dynamics from static appearance, Motive identifies which training videos shape motion in video generation. 🔗 1/10

Xindi Wu

110,606 次观看 • 4 个月前

Video generation of humans with control over body pose and facial expressions is crucial for a plethora of applications. Towards this goal, we introduce a new interspatial attention (ISA) mechanism as a scalable building block for DiT–based video generation models #SIGGRAPH2025
0:32

Video generation of humans with control over body pose and facial expressions is crucial for a plethora of applications. Towards this goal, we introduce a new interspatial attention (ISA) mechanism as a scalable building block for DiT–based video generation models #SIGGRAPH2025

Gordon Wetzstein

28,407 次观看 • 1 年前

Can we simplify video generation by decomposing it into interleaved text-video co-generation? Would explicit, repeated thinking in language improve generation in pixels? We introduce TV2TV: a unified model that jointly learns - language modeling (next-token prediction) - video flow matching (next-frame prediction) At inference, TV2TV dynamically alternates between textual thinking and video generation. Model generations below: interleaved text plans and video slices (~1–2s) are co-generated over time, conditioned on a single frame per sport. 📖
0:36

Can we simplify video generation by decomposing it into interleaved text-video co-generation? Would explicit, repeated thinking in language improve generation in pixels? We introduce TV2TV: a unified model that jointly learns - language modeling (next-token prediction) - video flow matching (next-frame prediction) At inference, TV2TV dynamically alternates between textual thinking and video generation. Model generations below: interleaved text plans and video slices (~1–2s) are co-generated over time, conditioned on a single frame per sport. 📖

Xiaochuang Han

29,080 次观看 • 6 个月前

Ovi is out on Hugging Face Twin Backbone Cross-Modal Fusion for Audio-Video Generation Ovi is a veo-3 like, video+audio generation model that simultaneously generates both video and audio content from text or text+image inputs. Video+Audio Generation: Generate synchronized video and audio content simultaneously Flexible Input: Supports text-only or text+image conditioning 5-second Videos: Generates 5-second videos at 24 FPS, area of 720×720, at various aspect ratios (9:16, 16:9, 1:1, etc)
2:08

Ovi is out on Hugging Face Twin Backbone Cross-Modal Fusion for Audio-Video Generation Ovi is a veo-3 like, video+audio generation model that simultaneously generates both video and audio content from text or text+image inputs. Video+Audio Generation: Generate synchronized video and audio content simultaneously Flexible Input: Supports text-only or text+image conditioning 5-second Videos: Generates 5-second videos at 24 FPS, area of 720×720, at various aspect ratios (9:16, 16:9, 1:1, etc)

AK

23,082 次观看 • 8 个月前