Loading video...

Video Failed to Load

Go Home

Meta presents Adaptive Caching for Faster Video Generation with Diffusion Transformers

_akhaliq's profile picture

AK

503,060 subscribers

53,119 views • 1 year ago •via X (Twitter)

EducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

8 Comments

AK's profile picture
AK1 year ago

discuss:

Prashant's profile picture
Prashant1 year ago

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

Wu Han Solo 's profile picture
Wu Han Solo 1 year ago

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

Rehan Sheikh's profile picture
Rehan Sheikh1 year ago

Would be interesting to see results with Mochi 1?

Madan Khadka's profile picture
Madan Khadka1 year ago

Lfg amazing 🔥🔥

Shoyo Hinata's profile picture
Shoyo Hinata1 year ago

Meta ftw!

Tosh 🏴‍☠️'s profile picture
Tosh 🏴‍☠️1 year ago

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

🦋an's profile picture
🦋an1 year ago

What do we need faster video generation for?

Related Videos

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 views • 6 months ago

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 views • 1 year ago

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 views • 6 months ago

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 views • 1 year ago

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

Nvidia presents Articulated Kinematics Distillation from Video Diffusion Models

AK

39,189 views • 1 year ago

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 views • 1 year ago

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 views • 1 year ago

"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 views • 7 months ago

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

NeuralRemaster Phase-Preserving Diffusion for Structure-Aligned Generation

AK

39,816 views • 6 months ago

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

122,958 views • 1 year ago

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

ActionMesh Animated 3D Mesh Generation with Temporal 3D Diffusion

AK

11,995 views • 4 months ago

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 views • 2 years ago

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 views • 2 years ago

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 views • 7 months ago

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

115,597 views • 2 years ago

More examples of what Meta Movie Gen can do across video generation, precise video editing, personalized video generation and audio generation.
1:08

More examples of what Meta Movie Gen can do across video generation, precise video editing, personalized video generation and audio generation.

AI at Meta

97,025 views • 1 year ago

Speed and quality can finally coexist in diffusion-based language generation. Introducing DiDi-Instruct, a Discrete Diffusion Divergence Instruct method that distills a pre-trained discrete diffusion language model (dLLM) into a few-step student for ultra-fast generation. Built on integral KL-divergence minimization, DiDi-Instruct achieves up to 64× faster decoding, surpasses both its teacher and GPT-2, and cuts training time by 20×. Ultra-Fast Language Generation via Discrete Diffusion Divergence Instruct Paper: Code: Project: Our report: 📬 #PapersAccepted by Jiqizhixin
0:40

Speed and quality can finally coexist in diffusion-based language generation. Introducing DiDi-Instruct, a Discrete Diffusion Divergence Instruct method that distills a pre-trained discrete diffusion language model (dLLM) into a few-step student for ultra-fast generation. Built on integral KL-divergence minimization, DiDi-Instruct achieves up to 64× faster decoding, surpasses both its teacher and GPT-2, and cuts training time by 20×. Ultra-Fast Language Generation via Discrete Diffusion Divergence Instruct Paper: Code: Project: Our report: 📬 #PapersAccepted by Jiqizhixin

机器之心 JIQIZHIXIN

18,126 views • 7 months ago