正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Dimension-Reduction Attack! Video Generative Models are Experts on Controllable Image Synthesis

AK

447,416 subscribers

28,101 次观看 • 1 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

2 条评论

AK 的头像

AK1 年前

discuss with author:

AK 的头像

AK1 年前

app:

相关视频

(1/n) Time to unify your favorite visual generative models, VLMs, and simulators for controllable visual generation—Introducing a Product of Experts (PoE) framework for inference-time knowledge composition from heterogeneous models.

(1/n) Time to unify your favorite visual generative models, VLMs, and simulators for controllable visual generation—Introducing a Product of Experts (PoE) framework for inference-time knowledge composition from heterogeneous models.

Yunzhi Zhang

49,009 次观看 • 1 年前

Generative Novel View Synthesis with 3D-Aware Diffusion Models abs: project page:

Generative Novel View Synthesis with 3D-Aware Diffusion Models abs: project page:

AK

304,708 次观看 • 3 年前

🚀 Introducing InterDyn — our newly accepted CVPR work that explores controllable synthesis of interactive dynamics! Building upon powerful video diffusion models, InterDyn infers future motion and interactions directly from an input image and a dynamic control signal (e.g., a moving hand mask). Check out how we push the boundaries of intuitive physics with video generative models. Project page: Arxiv: #GenAI #AIGC #VideoGen #ML #ComputerVision #CVPR2025 🧵1/6

🚀 Introducing InterDyn — our newly accepted CVPR work that explores controllable synthesis of interactive dynamics! Building upon powerful video diffusion models, InterDyn infers future motion and interactions directly from an input image and a dynamic control signal (e.g., a moving hand mask). Check out how we push the boundaries of intuitive physics with video generative models. Project page: Arxiv: #GenAI #AIGC #VideoGen #ML #ComputerVision #CVPR2025 🧵1/6

Haven (Haiwen) Feng

44,898 次观看 • 1 年前

Google presents VLOGGER Multimodal Diffusion for Embodied Avatar Synthesis We propose VLOGGER, a method for audio-driven human video generation from a single input image of a person, which builds on the success of recent generative diffusion models. Our method consists of

AK

66,375 次观看 • 2 年前

VSTAR Generative Temporal Nursing for Longer Dynamic Video Synthesis Despite tremendous progress in the field of text-to-video (T2V) synthesis, open-sourced T2V diffusion models struggle to generate longer videos with dynamically varying and evolving content. They tend to

VSTAR Generative Temporal Nursing for Longer Dynamic Video Synthesis Despite tremendous progress in the field of text-to-video (T2V) synthesis, open-sourced T2V diffusion models struggle to generate longer videos with dynamically varying and evolving content. They tend to

AK

36,982 次观看 • 2 年前

Unlocking a few more secret weapons for creators. This week in AI image has been CRAZY 🔥 All image models on invideo paid plans are unlimited for 365 days. Limited time only. RT + Comment ‘IMAGE’ to win the highest generative plan on invideo. Keep DMs open.

Unlocking a few more secret weapons for creators. This week in AI image has been CRAZY 🔥 All image models on invideo paid plans are unlimited for 365 days. Limited time only. RT + Comment ‘IMAGE’ to win the highest generative plan on invideo. Keep DMs open.

Invideo

10,697 次观看 • 8 个月前

📊 VBench: Comprehensive Benchmark Suite for Video Generative Models 🎞️ 🏛️ Hierarchical and Disentangled Dimensions 👁️ Human-Alignment in Each Dimension 🌟 Valuable and Multi-Perspective Insights Website: Code:

📊 VBench: Comprehensive Benchmark Suite for Video Generative Models 🎞️ 🏛️ Hierarchical and Disentangled Dimensions 👁️ Human-Alignment in Each Dimension 🌟 Valuable and Multi-Perspective Insights Website: Code:

Ziqi Huang

19,008 次观看 • 2 年前

This is what generative models are for

This is what generative models are for

BURKOV

213,871 次观看 • 1 年前

Compute is the backbone of the AI-driven future. OptimAI Compute Engine would enable scalable, high-performance workloads across image and video models, supporting: • Text-to-image generation • Image editing and inpainting • 2K / 4K / 8K super-resolution • Brand-aligned visual synthesis • OCR and image intelligence • Video generation and motion synthesis • Frame interpolation and enhancement • Multimodal model inference Distributed compute built for faster inference, shorter training cycles, and production-grade AI execution.

OptimAI Network

18,830 次观看 • 5 个月前

ARE YOU READY TO PROMPT😱 UNLIMITED. FREE. 70+ MODELS. Till 1 Dec for all new users on any paid plan. How to access: → Go to → Get any paid plan (Plus, Max, or Generative) → Use any model (image or video) via 'Agents & Models" unlimited and free till 1 December RT + comment 'READY' to win our highest generative plan + $1200 credits. Keep DMs open.

ARE YOU READY TO PROMPT😱 UNLIMITED. FREE. 70+ MODELS. Till 1 Dec for all new users on any paid plan. How to access: → Go to → Get any paid plan (Plus, Max, or Generative) → Use any model (image or video) via 'Agents & Models" unlimited and free till 1 December RT + comment 'READY' to win our highest generative plan + $1200 credits. Keep DMs open.

Invideo

652,823 次观看 • 8 个月前

Image & video synthesis struggle with the scale of truly large 3D scenes. mschneider456 presents a geometry-first approach : - structure first: mesh scaffold defining the scene - then appearance: mesh-conditioned image synthesis Check it out:

Image & video synthesis struggle with the scale of truly large 3D scenes. mschneider456 presents a geometry-first approach : - structure first: mesh scaffold defining the scene - then appearance: mesh-conditioned image synthesis Check it out:

Angela Dai

19,645 次观看 • 4 个月前

Foundation models are powerful machine learning algorithms that sit at the core of many generative AI tools today. How are they built and deployed and how are they changing society? Here’s a quick intro for non-experts:

Foundation models are powerful machine learning algorithms that sit at the core of many generative AI tools today. How are they built and deployed and how are they changing society? Here’s a quick intro for non-experts:

Stanford HAI

20,770 次观看 • 3 年前

Exciting milestones in our generative AI research: Emu Video, which lets you create high quality videos from a text prompt, and Emu Edit, which enables detailed image editing based on your instructions. These new models are built on Emu, our foundation model for image generation and technology from them will underpin new creative features across our apps next year. Try it out: Emu Video: Emu Edit:

Exciting milestones in our generative AI research: Emu Video, which lets you create high quality videos from a text prompt, and Emu Edit, which enables detailed image editing based on your instructions. These new models are built on Emu, our foundation model for image generation and technology from them will underpin new creative features across our apps next year. Try it out: Emu Video: Emu Edit:

Boz

110,733 次观看 • 2 年前

Scaling up GANs for Text-to-Image Synthesis present our 1B-parameter GigaGAN, achieving lower FID than Stable Diffusion v1.5, DALL·E 2, and Parti-750M. It generates 512px outputs at 0.13s, orders of magnitude faster than diffusion and autoregressive models, and inherits the disentangled, continuous, and controllable latent space of GANs abs: project page:

Scaling up GANs for Text-to-Image Synthesis present our 1B-parameter GigaGAN, achieving lower FID than Stable Diffusion v1.5, DALL·E 2, and Parti-750M. It generates 512px outputs at 0.13s, orders of magnitude faster than diffusion and autoregressive models, and inherits the disentangled, continuous, and controllable latent space of GANs abs: project page:

AK

278,115 次观看 • 3 年前

ByteDance just dropped Goku Flow Based Video Generative Foundation Models

ByteDance just dropped Goku Flow Based Video Generative Foundation Models

AK

248,359 次观看 • 1 年前

I am recruiting PhD students for Fall '25 at Cornell! I plan to admit multiple students interested in building more controllable generative models, music technologies (or both!). 🎶 Please apply to Cornell Computer Science.

I am recruiting PhD students for Fall '25 at Cornell! I plan to admit multiple students interested in building more controllable generative models, music technologies (or both!). 🎶 Please apply to Cornell Computer Science.

John Thickstun

27,280 次观看 • 1 年前

Netflix just dropped Go-with-the-Flow Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise

Netflix just dropped Go-with-the-Flow Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise

AK

95,564 次观看 • 1 年前

Google is offering a Generative AI Learning Path with 10 courses for FREE! - Intro to Generative AI - Intro to LLMs - Intro to Image Generation - Encoder-Decoder Architecture - Transformer Models and more A Thread 🧵👇

Google is offering a Generative AI Learning Path with 10 courses for FREE! - Intro to Generative AI - Intro to LLMs - Intro to Image Generation - Encoder-Decoder Architecture - Transformer Models and more A Thread 🧵👇

Afiz ⚡️

249,585 次观看 • 3 年前

New research from BlackForestLabsAI - Unofficial 🥳 Meet Self-Flow: our self-supervised framework for image, audio, video & world models 🤖 Do generative models really need DINO to learn strong representations? We propose teaching them directly via a joint framework instead 🧵

New research from BlackForestLabsAI - Unofficial 🥳 Meet Self-Flow: our self-supervised framework for image, audio, video & world models 🤖 Do generative models really need DINO to learn strong representations? We propose teaching them directly via a joint framework instead 🧵

Hila Chefer

68,697 次观看 • 5 个月前