Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Meta presents Adaptive Caching for Faster Video Generation with Diffusion Transformers

_akhaliq's profile picture

AK

503,060 subscribers

53,119 görüntüleme • 1 yıl önce •via X (Twitter)

EğitimBilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

8 Yorum

AK profil fotoğrafı
AK1 yıl önce

discuss:

Prashant profil fotoğrafı
Prashant1 yıl önce

Meta is pushing research at faster pace than anyone else, making open source AI great again

Wu Han Solo  profil fotoğrafı
Wu Han Solo 1 yıl önce

Claude, implement this for Mochi in ComfyUI lol @MushroomFleet am i crazy?? 😝

Rehan Sheikh profil fotoğrafı
Rehan Sheikh1 yıl önce

Would be interesting to see results with Mochi 1?

Madan Khadka profil fotoğrafı
Madan Khadka1 yıl önce

Lfg amazing 🔥🔥

Shoyo Hinata profil fotoğrafı
Shoyo Hinata1 yıl önce

Meta ftw!

Tosh 🏴‍☠️ profil fotoğrafı
Tosh 🏴‍☠️1 yıl önce

I like how Meta used open sora as a baseline looks like they got a 2-4x speedup w/ the adacache

🦋an profil fotoğrafı
🦋an1 yıl önce

What do we need faster video generation for?

Benzer Videolar

Meta presents OneStory Coherent Multi-Shot Video Generation with Adaptive Memory
0:35

Meta presents OneStory Coherent Multi-Shot Video Generation with Adaptive Memory

AK

11,532 görüntüleme • 6 ay önce

🚨Coming to #ICML2026 🇰🇷 Last year, we introduced Block Diffusion LMs, adopted by dLLMs at Google, NVIDIA, Meta, etc. 🚀Today, we introduce Set Diffusion, a faster, more flexible alternative that combines AR and diffusion by interpolating generation orders. 🧵1/8
0:28

🚨Coming to #ICML2026 🇰🇷 Last year, we introduced Block Diffusion LMs, adopted by dLLMs at Google, NVIDIA, Meta, etc. 🚀Today, we introduce Set Diffusion, a faster, more flexible alternative that combines AR and diffusion by interpolating generation orders. 🧵1/8

Marianne Arriola @ICML

46,334 görüntüleme • 3 gün önce

Google presents CAT4D Create Anything in 4D with Multi-View Video Diffusion Models
2:12

Google presents CAT4D Create Anything in 4D with Multi-View Video Diffusion Models

AK

61,949 görüntüleme • 1 yıl önce

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
0:22

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 görüntüleme • 2 yıl önce

BlockVid Block Diffusion for High-Quality and Consistent Minute-Long Video Generation
1:00

BlockVid Block Diffusion for High-Quality and Consistent Minute-Long Video Generation

AK

19,949 görüntüleme • 7 ay önce

SkyReels-A2 just dropped on Hugging Face Compose Anything in Video Diffusion Transformers
0:31

SkyReels-A2 just dropped on Hugging Face Compose Anything in Video Diffusion Transformers

AK

73,605 görüntüleme • 1 yıl önce

Nvidia presents Articulated Kinematics Distillation from Video Diffusion Models
4:11

Nvidia presents Articulated Kinematics Distillation from Video Diffusion Models

AK

39,189 görüntüleme • 1 yıl önce

Voyager Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation
0:30

Voyager Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation

AK

15,840 görüntüleme • 1 yıl önce

AccVideo just dropped on Hugging Face Accelerating Video Diffusion Model with Synthetic Dataset present a efficient distillation method to accelerate video diffusion models with synthetic dataset method is 8.5x faster than HunyuanVideo
1:04

AccVideo just dropped on Hugging Face Accelerating Video Diffusion Model with Synthetic Dataset present a efficient distillation method to accelerate video diffusion models with synthetic dataset method is 8.5x faster than HunyuanVideo

AK

20,633 görüntüleme • 1 yıl önce

"An hour of planning can save you 10 hours of doing." ✨📝 Planned Diffusion 📝 ✨ makes a plan before parallel dLLM generation. Planned Diffusion runs 1.2-1.8× faster than autoregressive and an order of magnitude faster than diffusion, while staying within 0.9–5% AR quality.
0:21

"An hour of planning can save you 10 hours of doing." ✨📝 Planned Diffusion 📝 ✨ makes a plan before parallel dLLM generation. Planned Diffusion runs 1.2-1.8× faster than autoregressive and an order of magnitude faster than diffusion, while staying within 0.9–5% AR quality.

Daniel Israel

38,699 görüntüleme • 8 ay önce

Google presents LightLab Controlling Light Sources in Images with Diffusion Models
2:29

Google presents LightLab Controlling Light Sources in Images with Diffusion Models

AK

122,981 görüntüleme • 1 yıl önce

NeuralRemaster Phase-Preserving Diffusion for Structure-Aligned Generation
3:32

NeuralRemaster Phase-Preserving Diffusion for Structure-Aligned Generation

AK

39,816 görüntüleme • 7 ay önce

ActionMesh Animated 3D Mesh Generation with Temporal 3D Diffusion
0:48

ActionMesh Animated 3D Mesh Generation with Temporal 3D Diffusion

AK

12,327 görüntüleme • 5 ay önce

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

29,278 görüntüleme • 2 yıl önce

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

431,142 görüntüleme • 2 yıl önce

This video explains how diffusion models are overtaking Large Language Models for generation tasks like: 1. Code Generation 2. Image Generation 3. Video Generation 00:00 Agenda 00:20 How are they different from LLMs? 05:09 Internal Mechanism 10:09 How are vectors generated? 12:08 Conclusion 13:02 Opinion Piece AI Engineering Course: #Diffusion #AI #LLMs
15:00

This video explains how diffusion models are overtaking Large Language Models for generation tasks like: 1. Code Generation 2. Image Generation 3. Video Generation 00:00 Agenda 00:20 How are they different from LLMs? 05:09 Internal Mechanism 10:09 How are vectors generated? 12:08 Conclusion 13:02 Opinion Piece AI Engineering Course: #Diffusion #AI #LLMs

Gaurav Sen

27,927 görüntüleme • 8 ay 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
0:24

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