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。

Introducing darkspark, a gui for your neural network. It traces your pytorch code and brings up a visual representation for you to interact with. We have a hosted gallery of popular model architectures pre-traced and ready to explore. Here’s stable-diffusion-v1.5

Rudy Gilman

3,144 subscribers

16,783 次观看 • 1 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

10 条评论

Rudy Gilman 的头像

Rudy Gilman1 年前

We’re also capturing activations during the trace. Check out the simple color and line detectors in the first layer of convnext_zepto from the timm library

Rudy Gilman 的头像

Rudy Gilman1 年前

It’s like openai’s Microscope tool but for your own models. See if you can identify these later features from timm’s contrastively-trained vit_base_patch16_siglip_224

Rudy Gilman 的头像

Rudy Gilman1 年前

We can also explore the attention patterns. The siglip model from above has a head that appears to move information around hamburgers

Rudy Gilman 的头像

Rudy Gilman1 年前

We’ve got all the models from the timm library as well as many others from huggingface’s transformers and diffusers libraries already hosted.

Rudy Gilman 的头像

Rudy Gilman1 年前

The github repo isn’t yet ready for public release but you can explore all the pre-traced models at Works best with a large screen.

Rudy Gilman 的头像

Rudy Gilman1 年前

Or start with a few neurons from DINO-v2

JohnMark Taylor 的头像

JohnMark Taylor1 年前

Very cool—I wrote a package (TorchLens) that does visuals for DNNs but without the interactivity. Lemme know if you ever want to compare notes!

Rudy Gilman 的头像

Rudy Gilman1 年前

yes torchlens was an inspiration for me!

sway 的头像

sway1 年前

sd1.5 having 7.7b params seems very wrong

Rudy Gilman 的头像

Rudy Gilman1 年前

why?

相关视频

We created a series of simplified notebooks that cover essential aspects of Stable Diffusion, using the vanilla Stable Diffusion 2.1 base to utilise it as a face-editing model for building your own face app 🧵(1/3) Github :

We created a series of simplified notebooks that cover essential aspects of Stable Diffusion, using the vanilla Stable Diffusion 2.1 base to utilise it as a face-editing model for building your own face app 🧵(1/3) Github :

OutofAi

45,864 次观看 • 2 年前

Today, we are releasing Stable Video Diffusion, our first foundation model for generative AI video based on the image model, Stable Diffusion. As part of this research preview, the code, weights, and research paper are now available. Additionally, today you can sign up for our waitlist to access a new upcoming web experience featuring a Text-To-Video interface. To access the model & sign up for our waitlist, visit our website here:

Today, we are releasing Stable Video Diffusion, our first foundation model for generative AI video based on the image model, Stable Diffusion. As part of this research preview, the code, weights, and research paper are now available. Additionally, today you can sign up for our waitlist to access a new upcoming web experience featuring a Text-To-Video interface. To access the model & sign up for our waitlist, visit our website here:

Stability AI

1,024,598 次观看 • 2 年前

MVDiffusion: How to take a pre-trained text2image model for a perspective view (e.g., Stable Diffusion) and retrain to generate multiple consistent views (e.g., a panorama). Project site: Hugging Face demo: Code out in a month.

MVDiffusion: How to take a pre-trained text2image model for a perspective view (e.g., Stable Diffusion) and retrain to generate multiple consistent views (e.g., a panorama). Project site: Hugging Face demo: Code out in a month.

Yasutaka Furukawa

33,456 次观看 • 3 年前

The latest Visual Studio Code release brings auto model selection (preview) - a way to have the best model picked for you based on current capacity and performance. Currently being rolled out to all GitHub Copilot users in Visual Studio Code starting with individuals. Learn more:

The latest Visual Studio Code release brings auto model selection (preview) - a way to have the best model picked for you based on current capacity and performance. Currently being rolled out to all GitHub Copilot users in Visual Studio Code starting with individuals. Learn more:

Visual Studio Code

67,659 次观看 • 11 个月前

introducing Moodboard Gallery. we added thousands of new moodboards in our gallery for you to explore and generate using Krea 2. we're also previewing "random" and "auto" – two new modes to select moodboards automatically for your generations.

introducing Moodboard Gallery. we added thousands of new moodboards in our gallery for you to explore and generate using Krea 2. we're also previewing "random" and "auto" – two new modes to select moodboards automatically for your generations.

Krea

19,633 次观看 • 2 个月前

You can create a Grok Project, have it search for relevant research papers, and attach the good ones to your project. Because Grok 4 can parse PDFs, you can interact with the model, and it will have direct knowledge of your research.

You can create a Grok Project, have it search for relevant research papers, and attach the good ones to your project. Because Grok 4 can parse PDFs, you can interact with the model, and it will have direct knowledge of your research.

tetsuo

1,662,794 次观看 • 10 个月前

Introducing Interact AI: a new interface for the web. Add it to your website, and it talks to every visitor, answers questions, and shows your product. Try it now ->

Introducing Interact AI: a new interface for the web. Add it to your website, and it talks to every visitor, answers questions, and shows your product. Try it now ->

Interact AI

2,230,680 次观看 • 3 个月前

Many of you asked for code & weights for π₀, we are happy to announce that we are releasing π₀ and pre-trained checkpoints in our new openpi repository! We tested the model on a few public robots, and we include code for you to fine-tune it yourself.

Many of you asked for code & weights for π₀, we are happy to announce that we are releasing π₀ and pre-trained checkpoints in our new openpi repository! We tested the model on a few public robots, and we include code for you to fine-tune it yourself.

Physical Intelligence

441,382 次观看 • 1 年前

I vibecoded this neural network visualization for my students and open sourced it. It shows a simple MLP trained on MNIST handwritten digits at several training steps. The visualization is using Three.js and it comes with training code in PyTorch . Link + repo 👇

I vibecoded this neural network visualization for my students and open sourced it. It shows a simple MLP trained on MNIST handwritten digits at several training steps. The visualization is using Three.js and it comes with training code in PyTorch . Link + repo 👇

David Finsterwalder | eu/acc

487,830 次观看 • 9 个月前

Dear Visionaries, it is a unique joy to create along with you and your energy. We loaded this clip with love and codes. All creators in this video have been rewarded. Interact for a chance to be rewarded too!

Dear Visionaries, it is a unique joy to create along with you and your energy. We loaded this clip with love and codes. All creators in this video have been rewarded. Interact for a chance to be rewarded too!

Eth OS

35,985 次观看 • 1 年前

🚀 Introducing Code Remix for MicroGPT! 🧑‍💻✨ Now, you can highlight any piece of code and let MicroGPT generate optimized and varied versions instantly! ⚡ Improve performance, explore different approaches, and refine your code—all with a single request.

🚀 Introducing Code Remix for MicroGPT! 🧑‍💻✨ Now, you can highlight any piece of code and let MicroGPT generate optimized and varied versions instantly! ⚡ Improve performance, explore different approaches, and refine your code—all with a single request.

MicroGPT

161,330 次观看 • 1 年前

In 2023 we have changed the lives of hundreds of people, thanks to YOUR support. 2024 we hope to help even more people, and with your help we will. Thank you to all our participants, our staff, our partners and to you for making 2023 a huge success. Here’s to a huge 2024 for the Inclusive Hub 🥂

In 2023 we have changed the lives of hundreds of people, thanks to YOUR support. 2024 we hope to help even more people, and with your help we will. Thank you to all our participants, our staff, our partners and to you for making 2023 a huge success. Here’s to a huge 2024 for the Inclusive Hub 🥂

The Inclusive Hub

12,537 次观看 • 2 年前

Introducing Stable Audio 2.0 – a new model capable of producing high-quality, full tracks with coherent musical structure up to three minutes long at 44.1 kHz stereo from a single prompt. Explore the model and start creating for free at: Read the blogpost here: (1/3)

Introducing Stable Audio 2.0 – a new model capable of producing high-quality, full tracks with coherent musical structure up to three minutes long at 44.1 kHz stereo from a single prompt. Explore the model and start creating for free at: Read the blogpost here: (1/3)

Stability AI

457,892 次观看 • 2 年前

Want one? I have a discount code available. Say "CODE" and I'll send it to you. Get your strike in shape - even at home - ready for the start of the season

Want one? I have a discount code available. Say "CODE" and I'll send it to you. Get your strike in shape - even at home - ready for the start of the season

Adam Young Golf

10,076 次观看 • 1 年前

We built a real-time multiplayer game generated entirely by a neural network—and now you can actually play it. In collaboration with Modal, we just launched the live demo for MultiGen, our diffusion-based multiplayer game engine. Grab some friends and try it here 👇

We built a real-time multiplayer game generated entirely by a neural network—and now you can actually play it. In collaboration with Modal, we just launched the live demo for MultiGen, our diffusion-based multiplayer game engine. Grab some friends and try it here 👇

Gordon Wetzstein

26,720 次观看 • 4 个月前

We built a visual canvas for tracking changes and experimenting with claude code. Describe your change → auto-commit with git → view a preview of that change → drag and drop a new branch to keep experimenting. It's called Cascade and here's how it works...

We built a visual canvas for tracking changes and experimenting with claude code. Describe your change → auto-commit with git → view a preview of that change → drag and drop a new branch to keep experimenting. It's called Cascade and here's how it works...

Avinash

25,109 次观看 • 10 个月前

Introducing EvoSkill V1, an open-source toolkit that takes a benchmark and a coding agent, and evolves it into a state-of-the-art specialist in minutes. Here’s all you need to start evolving, starting with your Claude Code ↓

Introducing EvoSkill V1, an open-source toolkit that takes a benchmark and a coding agent, and evolves it into a state-of-the-art specialist in minutes. Here’s all you need to start evolving, starting with your Claude Code ↓

Sentient

30,007 次观看 • 3 个月前

Introducing; Mii Creator! A website that allows you to make your Mii! It doesn't stop there! It also allows you to create a full-body render of it with a free camera and change facial expressions! (and download a 3D model of your Mii!) Try it here:

Introducing; Mii Creator! A website that allows you to make your Mii! It doesn't stop there! It also allows you to create a full-body render of it with a free camera and change facial expressions! (and download a 3D model of your Mii!) Try it here:

FlipZ

918,098 次观看 • 1 年前

The PostgreSQL extension for Visual Studio Code is here! GPS shows you how to get started with creating a new Docker PostreSQL server, managing your connections, chatting with your database, and more.

Sensitive content

The PostgreSQL extension for Visual Studio Code is here! GPS shows you how to get started with creating a new Docker PostreSQL server, managing your connections, chatting with your database, and more.

Visual Studio Code

42,177 次观看 • 1 年前

Try a new way to explore & interact with DeFi!💫 Swaps Market brings your favorite dApps together in one automated and intuitive interface. Explore thousands of staking & restaking opportunities or create them by becoming a contributor. Let's change DeFi for the better!

Try a new way to explore & interact with DeFi!💫 Swaps Market brings your favorite dApps together in one automated and intuitive interface. Explore thousands of staking & restaking opportunities or create them by becoming a contributor. Let's change DeFi for the better!

Swaps.io

28,633 次观看 • 1 年前