Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Meta presents Adaptive Caching for Faster Video Generation with Diffusion Transformers

_akhaliq's profile picture

AK

524,814 subscribers

53,129 Aufrufe • vor 2 Jahren •via X (Twitter)

BildungWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

8 Kommentare

Profilbild von AK
AKvor 2 Jahren

discuss:

Profilbild von Prashant
Prashantvor 2 Jahren

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

Profilbild von Wu Han Solo 
Wu Han Solo vor 2 Jahren

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

Profilbild von Rehan Sheikh
Rehan Sheikhvor 2 Jahren

Would be interesting to see results with Mochi 1?

Profilbild von Madan Khadka
Madan Khadkavor 2 Jahren

Lfg amazing 🔥🔥

Profilbild von Shoyo Hinata
Shoyo Hinatavor 2 Jahren

Meta ftw!

Profilbild von Tosh 🏴‍☠️
Tosh 🏴‍☠️vor 2 Jahren

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

Profilbild von 🦋an
🦋anvor 1 Jahr

What do we need faster video generation for?

Ähnliche 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 Aufrufe • vor 10 Monaten

SCoPE Sightline-Coordinate Positional Encoding for Video Diffusion Transformers model:
2:00

SCoPE Sightline-Coordinate Positional Encoding for Video Diffusion Transformers model:

AK

24,274 Aufrufe • vor 2 Monaten

🚨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

63,130 Aufrufe • vor 3 Monaten

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 Aufrufe • vor 2 Jahren

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

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

Chubby♨️

12,843 Aufrufe • vor 1 Jahr

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 Aufrufe • vor 10 Monaten

"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

38,833 Aufrufe • vor 1 Jahr

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

123,055 Aufrufe • vor 1 Jahr

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

NeuralRemaster Phase-Preserving Diffusion for Structure-Aligned Generation

AK

39,909 Aufrufe • vor 10 Monaten

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

ActionMesh Animated 3D Mesh Generation with Temporal 3D Diffusion

AK

12,347 Aufrufe • vor 8 Monaten

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 Aufrufe • vor 2 Jahren

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

431,392 Aufrufe • vor 2 Jahren

Microsoft presents World-R1 Reinforcing 3D Constraints for Text-to-Video Generation paper:
1:11

Microsoft presents World-R1 Reinforcing 3D Constraints for Text-to-Video Generation paper:

AK

24,625 Aufrufe • vor 6 Monaten