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。

I finally released my new video on YouTube about Diffusion Models / Score-Based Generative Models. Literally planned this for a year and put so much work in. I think this approach to diffusion models is so intuitive and highly recommend giving that a go! Video is 38min long, so... show more

dome | Outlier

3,060 subscribers

54,560 次观看 • 1 年前 •via X (Twitter)

科学技术音乐教育

Anya Rossi• Live Now

Private livecam show

10 条评论

1LittleCoder💻 的头像

1LittleCoder💻1 年前

That's a crazy timeline. Respect!

dome | Outlier 的头像

dome | Outlier1 年前

Thank you haha

Robin Rombach 的头像

Robin Rombach1 年前

Nice, richtig gut 😍

dome | Outlier 的头像

dome | Outlier1 年前

Nächstes video dann über Flow Matching. Ich werd auf dich zurückkommen mit paar Fragen :c

Ryan Tabrizi 的头像

Ryan Tabrizi1 年前

Learned a lot following your derivations. Thanks!

dome | Outlier 的头像

dome | Outlier1 年前

So awesome to hear. One small addition, the solution to this is not just Sliced Score Matching. It‘s what Pascal Vincent came up with when he combined Score Matching & Denoising Autoencoders -> Denoising Score Matching So basically two solutions to this problem, and mostly DSM is used :) Super happy the video was helpful

Ariel N. Lee 的头像

Ariel N. Lee1 年前

This is awesome

Ashutosh Narang 的头像

Ashutosh Narang1 年前

@jeremyphoward Watching it today, thank you

The Variational Book 的头像

The Variational Book1 年前

@dome_271 looks great, what did you use to make the video? Seems like would be right up your alley

dome | Outlier 的头像

dome | Outlier1 年前

Manim and Premiere Pro :c

相关视频

Diffusion clicked for me when I read about score-based models, a line of work pioneered by Stefano Ermon (et al.) at Stanford. So it was a full-circle moment to collab with him and Inception on a video about training & sampling techniques for making diffusion LLMs faster.

Diffusion clicked for me when I read about score-based models, a line of work pioneered by Stefano Ermon (et al.) at Stanford. So it was a full-circle moment to collab with him and Inception on a video about training & sampling techniques for making diffusion LLMs faster.

Julia Turc

27,125 次观看 • 4 个月前

Dreamix: Video Diffusion Models are General Video Editors abs: project page: present diffusion-based method that is able to perform text-based motion and appearance editing of general videos

Dreamix: Video Diffusion Models are General Video Editors abs: project page: present diffusion-based method that is able to perform text-based motion and appearance editing of general videos

AK

398,160 次观看 • 3 年前

Announcing Diffusion Forcing Transformer (DFoT), our new video diffusion algorithm that generates ultra-long videos of 800+ frames. DFoT enables History Guidance, a simple add-on to any existing video diffusion models for a quality boost. Website: (1/7)

Announcing Diffusion Forcing Transformer (DFoT), our new video diffusion algorithm that generates ultra-long videos of 800+ frames. DFoT enables History Guidance, a simple add-on to any existing video diffusion models for a quality boost. Website: (1/7)

Boyuan Chen

175,996 次观看 • 1 年前

This is the first time in a long while that I’ve let myself think about this again and rewatch this video since the first time. It hurt so much I could barely handle it…. Thank you so much Seungkwan and 17, i love you guys so much

This is the first time in a long while that I’ve let myself think about this again and rewatch this video since the first time. It hurt so much I could barely handle it…. Thank you so much Seungkwan and 17, i love you guys so much

🐻🐻‍❄️

99,886 次观看 • 5 个月前

Nvidia presents Align Your Steps Optimizing Sampling Schedules in Diffusion Models Diffusion models (DMs) have established themselves as the state-of-the-art generative modeling approach in the visual domain and beyond. A crucial drawback of DMs is their slow sampling speed,

Nvidia presents Align Your Steps Optimizing Sampling Schedules in Diffusion Models Diffusion models (DMs) have established themselves as the state-of-the-art generative modeling approach in the visual domain and beyond. A crucial drawback of DMs is their slow sampling speed,

AK

32,888 次观看 • 2 年前

working towards action-conditioned video diffusion models for now this is just cs2 gameplay, and i parse the keypresses from the .dem game file next steps will be to work on a scalable data loader then coding the model

working towards action-conditioned video diffusion models for now this is just cs2 gameplay, and i parse the keypresses from the .dem game file next steps will be to work on a scalable data loader then coding the model

Arnie Ramesh

31,090 次观看 • 4 个月前

Excited to share our interview with Sander Dieleman! This is Part 3 in our History of Diffusion series. We talk about diffusion as spectral autoregression, diffusion language models, flow matching, and much more. Enjoy!

Excited to share our interview with Sander Dieleman! This is Part 3 in our History of Diffusion series. We talk about diffusion as spectral autoregression, diffusion language models, flow matching, and much more. Enjoy!

Slater Stich

28,721 次观看 • 1 年前

Synthesizing worlds with video diffusion models is often inconsistent — moving the camera back and forth leads to different scenes. We propose 🌐𝗪𝗼𝗿𝗹𝗱𝗠𝗲𝗺, a memory-based approach that ensures consistent world simulation without relying on explicit 3D reconstruction.

Synthesizing worlds with video diffusion models is often inconsistent — moving the camera back and forth leads to different scenes. We propose 🌐𝗪𝗼𝗿𝗹𝗱𝗠𝗲𝗺, a memory-based approach that ensures consistent world simulation without relying on explicit 3D reconstruction.

Xingang Pan

19,413 次观看 • 1 年前

Ill Try to make a model pack of the npcs soon, since the models uses layered masks I will need to make some custom textures that I will add with the material info so people can use the models better, so for those who want models I will ask patience n.n

Ill Try to make a model pack of the npcs soon, since the models uses layered masks I will need to make some custom textures that I will add with the material info so people can use the models better, so for those who want models I will ask patience n.n

ChicoEevee

31,415 次观看 • 2 个月前

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models paper page: github: Recent advancements in text-to-image generation with diffusion models have yielded remarkable results synthesizing highly realistic and diverse images. However, these models still encounter difficulties when generating images from prompts that demand spatial or common sense reasoning. We propose to equip diffusion models with enhanced reasoning capabilities by using off-the-shelf pretrained large language models (LLMs) in a novel two-stage generation process. First, we adapt an LLM to be a text-guided layout generator through in-context learning. When provided with an image prompt, an LLM outputs a scene layout in the form of bounding boxes along with corresponding individual descriptions. Second, we steer a diffusion model with a novel controller to generate images conditioned on the layout. Both stages utilize frozen pretrained models without any LLM or diffusion model parameter optimization. We validate the superiority of our design by demonstrating its ability to outperform the base diffusion model in accurately generating images according to prompts that necessitate both language and spatial reasoning. Additionally, our method naturally allows dialog-based scene specification and is able to handle prompts in a language that is not well-supported by the underlying diffusion model.

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models paper page: github: Recent advancements in text-to-image generation with diffusion models have yielded remarkable results synthesizing highly realistic and diverse images. However, these models still encounter difficulties when generating images from prompts that demand spatial or common sense reasoning. We propose to equip diffusion models with enhanced reasoning capabilities by using off-the-shelf pretrained large language models (LLMs) in a novel two-stage generation process. First, we adapt an LLM to be a text-guided layout generator through in-context learning. When provided with an image prompt, an LLM outputs a scene layout in the form of bounding boxes along with corresponding individual descriptions. Second, we steer a diffusion model with a novel controller to generate images conditioned on the layout. Both stages utilize frozen pretrained models without any LLM or diffusion model parameter optimization. We validate the superiority of our design by demonstrating its ability to outperform the base diffusion model in accurately generating images according to prompts that necessitate both language and spatial reasoning. Additionally, our method naturally allows dialog-based scene specification and is able to handle prompts in a language that is not well-supported by the underlying diffusion model.

AK

83,657 次观看 • 2 年前

Glad that our work “Inference-Time Enhancement of Generative Robot Policies via Predictive World Modeling”, led by Han Qi, has been accepted to IEEE Robotics and Automation Letters! 🎉 We propose Generative Predictive Control (GPC): sample action proposals from a pretrained diffusion policy (“look back”), roll them out with a diffusion-based action-conditioned video world model (“look forward”), then rank or optimize the actions using either a learned reward model or VLM preferences. Conceptually, this is trajectory optimization / MPC with hybrid sampling + gradient optimization, interpreted through modern diffusion priors and video world models. Interestingly, we first posted the paper on arXiv in Feb 2025, when action-conditioned video world models for planning were still rare—now this direction is rapidly gaining traction. Still many open questions, e.g., • how to avoid local minima in planning • what representations work best for world models • how to balance physics priors vs. data-driven learning Paper:

Glad that our work “Inference-Time Enhancement of Generative Robot Policies via Predictive World Modeling”, led by Han Qi, has been accepted to IEEE Robotics and Automation Letters! 🎉 We propose Generative Predictive Control (GPC): sample action proposals from a pretrained diffusion policy (“look back”), roll them out with a diffusion-based action-conditioned video world model (“look forward”), then rank or optimize the actions using either a learned reward model or VLM preferences. Conceptually, this is trajectory optimization / MPC with hybrid sampling + gradient optimization, interpreted through modern diffusion priors and video world models. Interestingly, we first posted the paper on arXiv in Feb 2025, when action-conditioned video world models for planning were still rare—now this direction is rapidly gaining traction. Still many open questions, e.g., • how to avoid local minima in planning • what representations work best for world models • how to balance physics priors vs. data-driven learning Paper:

Heng Yang

18,994 次观看 • 3 个月前

Procedural models are so fun to work with! You can have so much control over your own models and creations. 💜 Let me know if I should turn this into a plugin... 👀 #RobloxDev #Roblox

Procedural models are so fun to work with! You can have so much control over your own models and creations. 💜 Let me know if I should turn this into a plugin... 👀 #RobloxDev #Roblox

obviouslypurple

150,141 次观看 • 28 天前

We are thrilled to announce "Layered Diffusion Brushes": a real-time training-free image editor powered by diffusion models. 🎨✨ This is new work from my PhD student Peyman Gholami Peyman Gholami. Explore the interactive demo and check out more videos at:

We are thrilled to announce "Layered Diffusion Brushes": a real-time training-free image editor powered by diffusion models. 🎨✨ This is new work from my PhD student Peyman Gholami Peyman Gholami. Explore the interactive demo and check out more videos at:

Robert Xiao

14,330 次观看 • 2 年前

I finally found the time and courage to spend a few minutes on what I really think. After the announcement of the end of #Destiny2 I laid bare what I feel. The video is long, so you’ll find the full version on my #YouTube channel. (The video is in Italian) This is for you, Guardians. Thank you for everything, and thank you, Destiny. A Light that tears through the darkness. I love you. Full Video: #Destiny2Creator #Twitch #TwitchItalia

I finally found the time and courage to spend a few minutes on what I really think. After the announcement of the end of #Destiny2 I laid bare what I feel. The video is long, so you’ll find the full version on my #YouTube channel. (The video is in Italian) This is for you, Guardians. Thank you for everything, and thank you, Destiny. A Light that tears through the darkness. I love you. Full Video: #Destiny2Creator #Twitch #TwitchItalia

IFreddo

10,526 次观看 • 1 个月前

History-Guided Video Diffusion TL;DR: Diffuse long videos by performing guidance over different histories, enabled by Diffusion Forcing Transformer, a simple finetunable add-on to any existing sequence diffusion models.

History-Guided Video Diffusion TL;DR: Diffuse long videos by performing guidance over different histories, enabled by Diffusion Forcing Transformer, a simple finetunable add-on to any existing sequence diffusion models.

AK

20,914 次观看 • 1 年前

Took some time off but I’m excited to be back and find out that we reached 3k!!! I’m so happy for that thank you so so much for this 🥰🥰🥰 (a video that I took on my little vacation😜)

Took some time off but I’m excited to be back and find out that we reached 3k!!! I’m so happy for that thank you so so much for this 🥰🥰🥰 (a video that I took on my little vacation😜)

Vals Soles

15,125 次观看 • 2 年前

My craft is so different, even my biggest inspirations and role models don’t even know where to put me as I respectfully say that. It’s a gift and a curse.

My craft is so different, even my biggest inspirations and role models don’t even know where to put me as I respectfully say that. It’s a gift and a curse.

🦇 beastboi.🦇

12,095 次观看 • 4 个月前

I highly recommend Tesla investors watch this video. First time I go directly to video in my research since I had to cover too much context.

I highly recommend Tesla investors watch this video. First time I go directly to video in my research since I had to cover too much context.

AJ Investment Research

224,080 次观看 • 1 年前

Diffusion models generate high-quality images but require hundreds of forward passes. MIT CSAIL and Adobe Research introduce Distribution Matching Distillation (DMD), a distillation approach that converts costly multi-step diffusion models into fast one-step generators. A thread 🧵

Diffusion models generate high-quality images but require hundreds of forward passes. MIT CSAIL and Adobe Research introduce Distribution Matching Distillation (DMD), a distillation approach that converts costly multi-step diffusion models into fast one-step generators. A thread 🧵

MIT CSAIL

34,383 次观看 • 2 年前

Been thinking about what this paper really means. "Video diffusion" and "World Models" are becoming synonymous. Neural Computers are basically video diffusion world models for terminal envs and GUI. Lots of talk last week about automating Manim videos. In theory, we should be able to train these world models on a 10000 hours of diverse manim videos and "see where it goes" If a NC can generate outputs to terminal commands, it should be able to generate videos like this directly from prompt too. Without writing code.

Been thinking about what this paper really means. "Video diffusion" and "World Models" are becoming synonymous. Neural Computers are basically video diffusion world models for terminal envs and GUI. Lots of talk last week about automating Manim videos. In theory, we should be able to train these world models on a 10000 hours of diverse manim videos and "see where it goes" If a NC can generate outputs to terminal commands, it should be able to generate videos like this directly from prompt too. Without writing code.

AVB

119,949 次观看 • 2 个月前