Загрузка видео...

Не удалось загрузить видео

На главную

I made a tool called Diffusion Explorer that lets you to train and visualize simple 2D diffusion and flow models live in the browser. You can draw your own distributions and observe how the generated samples converge during training. Try it live 👇

alec_helbling's profile picture

Alec Helbling

10,350 subscribers

73,076 просмотров • 1 год назад •via X (Twitter)

Наука и технологииОбразование
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

I made a tool that lets you find the treasure in your computer. It's called Windows Explorer 2
0:12

I made a tool that lets you find the treasure in your computer. It's called Windows Explorer 2

torcado

119,582 просмотров • 8 месяцев назад

The Dream 7B (diffusion reasoning language model) is OUT! 🚨 I built a demo so you can test it out (and check the diffusion process live) 𖣯🔍
0:10

The Dream 7B (diffusion reasoning language model) is OUT! 🚨 I built a demo so you can test it out (and check the diffusion process live) 𖣯🔍

apolinario 🌐

35,257 просмотров • 1 год назад

I've been putting together an interactive tool called DiffusionLab for explaining the geometric intuition behind diffusion and flow based generative models. Sampling is actually being done in the browser using Tensorflow.js! It is still in the very early stages.
0:11

I've been putting together an interactive tool called DiffusionLab for explaining the geometric intuition behind diffusion and flow based generative models. Sampling is actually being done in the browser using Tensorflow.js! It is still in the very early stages.

Alec Helbling

104,645 просмотров • 1 год назад

You can build your own AI-apps powered by OpenAI and Stable Diffusion. **Even if you don't know how to code** Using no-code, build your own text and image generation apps with: - Bubble - OpenAI - Stable Diffusion Learn how:
0:12

You can build your own AI-apps powered by OpenAI and Stable Diffusion. **Even if you don't know how to code** Using no-code, build your own text and image generation apps with: - Bubble - OpenAI - Stable Diffusion Learn how:

Seth Kramer

6,893,639 просмотров • 3 лет назад

I made 3 models for discord streams. I plan to draw more. If you like it, I can send you 2d models by e-mail and show you how to use them in the discord :D #art #artwork #forsaken #forsakenroblox #azure #1x1x1x1
0:10

I made 3 models for discord streams. I plan to draw more. If you like it, I can send you 2d models by e-mail and show you how to use them in the discord :D #art #artwork #forsaken #forsakenroblox #azure #1x1x1x1

🔞Crocan🔞

17,342 просмотров • 1 год назад

LLaDA (the first Large Language Diffusion Model) is *just* out 💥 and I've built a demo, try out now 👨‍💻 It's mesmerizing to watch the diffusion process 🌀, and it being a diffusion model gives you superpowers like "the 4th word has to be pineapple" 🦸 Demo and weights 👇
0:17

LLaDA (the first Large Language Diffusion Model) is *just* out 💥 and I've built a demo, try out now 👨‍💻 It's mesmerizing to watch the diffusion process 🌀, and it being a diffusion model gives you superpowers like "the 4th word has to be pineapple" 🦸 Demo and weights 👇

apolinario (poli)

82,599 просмотров • 1 год назад

Excited to share this simple tool I made ✨ Explore, remix, and animate hundreds of 3D shapes. Or bring your own vector to life. All in your browser. Try beta now →
0:19

Excited to share this simple tool I made ✨ Explore, remix, and animate hundreds of 3D shapes. Or bring your own vector to life. All in your browser. Try beta now →

Augis

57,915 просмотров • 1 год назад

Excited to introduce Diffusion Augmented Agents (DAAGs)✨. We give an agent control of a diffusion model, so it can create its own *synthetic experience*.🪄 The result is a lifelong agent that can learn new reward detectors and policies, much more efficiently. Here's how. 👇
0:18

Excited to introduce Diffusion Augmented Agents (DAAGs)✨. We give an agent control of a diffusion model, so it can create its own *synthetic experience*.🪄 The result is a lifelong agent that can learn new reward detectors and policies, much more efficiently. Here's how. 👇

Norman Di Palo

12,874 просмотров • 1 год назад

Stochastic and deterministic sampling strategies for diffusion models produce strikingly different trajectories, but both ultimately achieve the same aim. I had a great time presenting our work, Diffusion Explorer, this week at IEEE VIS in Vienna.
0:14

Stochastic and deterministic sampling strategies for diffusion models produce strikingly different trajectories, but both ultimately achieve the same aim. I had a great time presenting our work, Diffusion Explorer, this week at IEEE VIS in Vienna.

Alec Helbling

279,017 просмотров • 7 месяцев назад

Langevin Monte Carlo allows you to draw samples from a probability distribution using its log gradient ∇ log p(x). By performing a sort of gradient ascent with noise you can navigate around the distribution. Langevin MC is heavily related to modern diffusion models.
0:19

Langevin Monte Carlo allows you to draw samples from a probability distribution using its log gradient ∇ log p(x). By performing a sort of gradient ascent with noise you can navigate around the distribution. Langevin MC is heavily related to modern diffusion models.

Alec Helbling

96,842 просмотров • 1 год назад

Genspark AI has released AI Browser. You can now have a super AI agent in your browser to automate browsing, planning, and interacting with the web for you. 5 powerful use cases + how to try👇: 1. Summarize my X feed and create a podcast about it
0:19

Genspark AI has released AI Browser. You can now have a super AI agent in your browser to automate browsing, planning, and interacting with the web for you. 5 powerful use cases + how to try👇: 1. Summarize my X feed and create a podcast about it

Alvaro Cintas

117,491 просмотров • 8 месяцев назад

When we began testing #GeminiOmni I wanted to see the accuracy of the edits. So I made a tool directly in Google Flow. DIFF TOOL allows you to compare images/videos in realtime or export videos in sync. Try it out or remix it to make it your own.
0:12

When we began testing #GeminiOmni I wanted to see the accuracy of the edits. So I made a tool directly in Google Flow. DIFF TOOL allows you to compare images/videos in realtime or export videos in sync. Try it out or remix it to make it your own.

Nick Matarese

46,981 просмотров • 26 дней назад

Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models "Block diffusion sequentially generates blocks of tokens by performing diffusion within each block and conditioning on previous blocks. By combining strength from autoregressive and diffusion models, block diffusion overcomes the limitations of both approaches by supporting variable-length, higher-quality generation and improving inference efficiency with KV caching and parallel sampling."
0:19

Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models "Block diffusion sequentially generates blocks of tokens by performing diffusion within each block and conditioning on previous blocks. By combining strength from autoregressive and diffusion models, block diffusion overcomes the limitations of both approaches by supporting variable-length, higher-quality generation and improving inference efficiency with KV caching and parallel sampling."

Tanishq Mathew Abraham, Ph.D.

21,813 просмотров • 1 год назад

Billboard character textures are now live in browser monkey ball. You can find the template download and upload your own in the multiplayer settings. Huge thank you to The BombSquad for this awesome PR!
0:17

Billboard character textures are now live in browser monkey ball. You can find the template download and upload your own in the multiplayer settings. Huge thank you to The BombSquad for this awesome PR!

Twilight

55,066 просмотров • 3 месяцев назад

Diffusion models are sensitive to small changes in the input noise. We introduce Alias-Free Latent Diffusion Models (𝗔𝗙-𝗟𝗗𝗠) at #CVPR2025. It achieves shift-equivariance and generates consistent outputs. Project: arXiv:
0:10

Diffusion models are sensitive to small changes in the input noise. We introduce Alias-Free Latent Diffusion Models (𝗔𝗙-𝗟𝗗𝗠) at #CVPR2025. It achieves shift-equivariance and generates consistent outputs. Project: arXiv:

Xingang Pan

42,538 просмотров • 1 год назад

1/ Happy to share UniDisc - Unified Multimodal Discrete Diffusion – We train a 1.5 billion parameter transformer model from scratch on 250 million image/caption pairs using a **discrete diffusion objective**. Our model has all the benefits of diffusion models but now in multimodal space! - flexible compute-quality tradeoff, zero-shot inpainting and editing, better control via classifier-free guidance and lower latency! We open source everything - our code, weights and the training dataset.
0:10

1/ Happy to share UniDisc - Unified Multimodal Discrete Diffusion – We train a 1.5 billion parameter transformer model from scratch on 250 million image/caption pairs using a **discrete diffusion objective**. Our model has all the benefits of diffusion models but now in multimodal space! - flexible compute-quality tradeoff, zero-shot inpainting and editing, better control via classifier-free guidance and lower latency! We open source everything - our code, weights and the training dataset.

Mihir Prabhudesai

104,862 просмотров • 1 год назад

Congrats to Mario 👏 for the accept of his ICLR paper on "Diffusion Graph Nets", predicting complex distributions of flow states on unstructured meshes Highly efficient, works even if the training data has only a fraction of the flow statistics.
0:14

Congrats to Mario 👏 for the accept of his ICLR paper on "Diffusion Graph Nets", predicting complex distributions of flow states on unstructured meshes Highly efficient, works even if the training data has only a fraction of the flow statistics.

Thuerey Group at TUM

24,996 просмотров • 1 год назад

Chop the gradients ✂️! We found that truncating decoder gradients in latent video diffusion to a fixed window allows us to finetune on videos with pixel-wise perceptual losses without running out of memory. Pixel losses have been essential for image generation and reconstruction, but until now, they haven't scaled to long-duration, high-resolution video diffusion due to recursive activation accumulation in causal decoders, leading to OOM during training 💥📉. Project: Video diffusion models can do a lot more 🚀 when you can backprop the decoder! Post-process neural rendered scenes, super-resolve videos, harmonize lighting in controlled synthetic driving scenes, and inpaint videos — all in a single step ⚡ with a quick finetune from a standard diffusion model.
0:19

Chop the gradients ✂️! We found that truncating decoder gradients in latent video diffusion to a fixed window allows us to finetune on videos with pixel-wise perceptual losses without running out of memory. Pixel losses have been essential for image generation and reconstruction, but until now, they haven't scaled to long-duration, high-resolution video diffusion due to recursive activation accumulation in causal decoders, leading to OOM during training 💥📉. Project: Video diffusion models can do a lot more 🚀 when you can backprop the decoder! Post-process neural rendered scenes, super-resolve videos, harmonize lighting in controlled synthetic driving scenes, and inpaint videos — all in a single step ⚡ with a quick finetune from a standard diffusion model.

Felix Heide

28,282 просмотров • 2 месяцев назад

Inspired by Andrej Karpathy's microgpt, I built microgpt.js: a JavaScript port that runs entirely in your browser! It's an exact numerical implementation, so the randomness and outputs match bit-for-bit! Try it out yourself and train your own GPT by simply opening a webpage! 👇
0:14

Inspired by Andrej Karpathy's microgpt, I built microgpt.js: a JavaScript port that runs entirely in your browser! It's an exact numerical implementation, so the randomness and outputs match bit-for-bit! Try it out yourself and train your own GPT by simply opening a webpage! 👇

Xenova

48,286 просмотров • 4 месяцев назад

If any of you BB nuts are interested in this, I actually made the veto necklace that Taran was wearing in today's live feed update, and you can get your own here: #BB27 #hoffmania
0:12

If any of you BB nuts are interested in this, I actually made the veto necklace that Taran was wearing in today's live feed update, and you can get your own here: #BB27 #hoffmania

Matt Hoffman-Moonves

121,457 просмотров • 9 месяцев назад