Loading video...

Video Failed to Load

Go Home

A new frontier. Project Starlight—the first and only diffusion-based AI model for enhancing video. Launching soon.

topazlabs's profile picture

Topaz Labs

31,132 subscribers

22,375 views • 1 year ago •via X (Twitter)

Science & TechnologyEducationArts
LIVE

Anya Rossi• Live Now

Private livecam show

10 Comments

DreamStarter's profile picture
DreamStarter1 year ago

Is this a new product can we use it with the existing video upscaler sub?

The Information's profile picture
The Information1 year ago

OpenAI is betting on a little-known startup to stay ahead of Elon Musk in the supercomputer race.

Rob's profile picture
Rob1 year ago

LFG! Excited for this!!

jeru's profile picture
jeru1 year ago

will this also destroy a perfect loop input?

Kol Tregaskes's profile picture
Kol Tregaskes1 year ago

This sounds exciting.

Pizza Later's profile picture
Pizza Later1 year ago

Beta testers needed?!

⭕ AI & Design (Marco)'s profile picture
⭕ AI & Design (Marco)1 year ago

I'm excited! Love Video AI!

HAN YOLO 🍌's profile picture
HAN YOLO 🍌1 year ago

Still waiting for something that can upscale old ntsc home videos properly

Sakib's profile picture
Sakib1 year ago

free version is called STAR

Dagmar Bressel's profile picture
Dagmar Bressel1 year ago

🔥🔥🔥

Related Videos

🚀Big news! We’re launching Project Starlight: the first-ever diffusion model for video restoration. Enhance old, low-quality videos to stunning high-resolution. This is our biggest leap since Video AI was first launched. Like & comment Starlight 👇 to get early-access!
0:46

🚀Big news! We’re launching Project Starlight: the first-ever diffusion model for video restoration. Enhance old, low-quality videos to stunning high-resolution. This is our biggest leap since Video AI was first launched. Like & comment Starlight 👇 to get early-access!

Topaz Labs

868,493 views • 1 year ago

Wow 🤩 the response to Project Starlight, the first-ever diffusion model for AI video restoration, has been incredible🚀 Many of you couldn't wait and sent us your videos to restore with Starlight So let’s make it a thing: Send us your videos, and we’ll restore them for free using Starlight 🌟 Read instructions in 🧵👇 Like & comment Starlight to get early access, if you haven’t done so already #ProjectStarlight
0:25

Wow 🤩 the response to Project Starlight, the first-ever diffusion model for AI video restoration, has been incredible🚀 Many of you couldn't wait and sent us your videos to restore with Starlight So let’s make it a thing: Send us your videos, and we’ll restore them for free using Starlight 🌟 Read instructions in 🧵👇 Like & comment Starlight to get early access, if you haven’t done so already #ProjectStarlight

Topaz Labs

329,561 views • 1 year ago

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:
0:20

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

1,024,415 views • 2 years ago

🚀BIG NEWS! We’re launching Astra: the first-ever creative upscaler for video. Upscale AI-generated videos to crisp 4K resolution while enhancing quality and finer details, powered by our newer & more creative Starlight models. Like & comment 'Astra' to get early access. Learn more in 🧵👇
1:15

🚀BIG NEWS! We’re launching Astra: the first-ever creative upscaler for video. Upscale AI-generated videos to crisp 4K resolution while enhancing quality and finer details, powered by our newer & more creative Starlight models. Like & comment 'Astra' to get early access. Learn more in 🧵👇

Topaz Labs

549,761 views • 1 year ago

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
1:53

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

398,132 views • 3 years ago

Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion abs: project page:
1:22

Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion abs: project page:

AK

262,780 views • 3 years ago

Wave 9 is here: a frontier model built for software engineering. Introducing our new family of models: SWE-1, SWE-1-lite, and SWE-1-mini. Based on internal evals, it has performance nearing that of frontier models from the foundation labs. Available now, only in Windsurf!
1:40

Wave 9 is here: a frontier model built for software engineering. Introducing our new family of models: SWE-1, SWE-1-lite, and SWE-1-mini. Based on internal evals, it has performance nearing that of frontier models from the foundation labs. Available now, only in Windsurf!

Devin Desktop

742,615 views • 1 year ago

launching the worlds first talking video model.... hyped
1:24

launching the worlds first talking video model.... hyped

sam

1,126,920 views • 9 months ago

Inception Labs just killed the transformer. They released Mercury 2, the world's first "diffusion" reasoning model. It's fast, and it uses a completely new model architecture... just watch this 11 min video to find out more:
11:35

Inception Labs just killed the transformer. They released Mercury 2, the world's first "diffusion" reasoning model. It's fast, and it uses a completely new model architecture... just watch this 11 min video to find out more:

David Ondrej

45,692 views • 3 months ago

introducing new upscalers. Bloom, Astra, and Starlight are new frontier image and video enhancers developed by Topaz Labs. try them now in Krea Enhance.
0:22

introducing new upscalers. Bloom, Astra, and Starlight are new frontier image and video enhancers developed by Topaz Labs. try them now in Krea Enhance.

KREA AI

19,635 views • 8 months ago

Love is timeless, and so are classic films. 💝 Watch as we bring the iconic final scene of Breakfast at Tiffany’s back to life with our new AI model, Starlight—restoring cinematic magic like never before. Happy Valentine's day, Happy enhancing!
1:57

Love is timeless, and so are classic films. 💝 Watch as we bring the iconic final scene of Breakfast at Tiffany’s back to life with our new AI model, Starlight—restoring cinematic magic like never before. Happy Valentine's day, Happy enhancing!

Topaz Labs

42,907 views • 1 year ago

First, we are excited to share a number of new updates to our frontier video generation model, Gen-4.5 Soon you will be able to both generate and edit native audio with Gen-4.5 and edit video at arbitrary lengths with multi-shot editing.
2:10

First, we are excited to share a number of new updates to our frontier video generation model, Gen-4.5 Soon you will be able to both generate and edit native audio with Gen-4.5 and edit video at arbitrary lengths with multi-shot editing.

Runway

33,308 views • 6 months ago

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data. Check out our results in the video (wait for dynamic scenes in the second half!) : Project Page: Code and Models: Paper:
0:50

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data. Check out our results in the video (wait for dynamic scenes in the second half!) : Project Page: Code and Models: Paper:

Sherwin Bahmani

66,417 views • 8 months ago

Introducing Contra Labs. The first frontier data and evaluation lab for Creative AI.
1:54

Introducing Contra Labs. The first frontier data and evaluation lab for Creative AI.

ben

445,740 views • 2 months ago

Introducing SubQ - a major breakthrough in LLM intelligence. It is the first model built on a fully sub-quadratic sparse-attention architecture (SSA), And the first frontier model with a 12 million token context window which is: - 52x faster than FlashAttention at 1MM tokens - Less than 5% the cost of Opus Transformer-based LLMs waste compute by processing every possible relationship between words (standard attention). Only a small fraction actually matter. Subquadratic finds and focuses only on the ones that do. That's nearly 1,000x less compute and a new way for LLMs to scale.
1:24

Introducing SubQ - a major breakthrough in LLM intelligence. It is the first model built on a fully sub-quadratic sparse-attention architecture (SSA), And the first frontier model with a 12 million token context window which is: - 52x faster than FlashAttention at 1MM tokens - Less than 5% the cost of Opus Transformer-based LLMs waste compute by processing every possible relationship between words (standard attention). Only a small fraction actually matter. Subquadratic finds and focuses only on the ones that do. That's nearly 1,000x less compute and a new way for LLMs to scale.

Alexander Whedon

13,095,080 views • 1 month ago

video editing is stuck in 2005, time for something new introducing diffusion the first infinite canvas for video and motion graphics like figma, but for editing
0:36

video editing is stuck in 2005, time for something new introducing diffusion the first infinite canvas for video and motion graphics like figma, but for editing

konstantinpaulus

128,691 views • 1 month ago

Introducing The Matrix --- a foundation world model for generating infinite-length, hyper-realistic videos with real-time, frame-level control: - Infinite-length video generation - 720p high-quality rendering - Real-time, frame-level control at 16 FPS - Generalization to real-world video control 🔗Blog: 📄Paper: 💻Code & Playable Demo: Coming soon! Key Innovation: A brand new technique called the shift-window denoise process model, enabling auto-regressive generation for diffusion and consistency models in real-time. Special thanks to project leader Ruili Feng and the entire Matrix team for their dedication and hard work over the year-long project.
1:00

Introducing The Matrix --- a foundation world model for generating infinite-length, hyper-realistic videos with real-time, frame-level control: - Infinite-length video generation - 720p high-quality rendering - Real-time, frame-level control at 16 FPS - Generalization to real-world video control 🔗Blog: 📄Paper: 💻Code & Playable Demo: Coming soon! Key Innovation: A brand new technique called the shift-window denoise process model, enabling auto-regressive generation for diffusion and consistency models in real-time. Special thanks to project leader Ruili Feng and the entire Matrix team for their dedication and hard work over the year-long project.

Hongyang Zhang

178,322 views • 1 year ago

Today, we’re thrilled to announce the open weights for Stable Diffusion 3 Medium, the latest and most advanced text-to-image AI model in our Stable Diffusion 3 series! This new release represents a major milestone in the evolution of generative AI and continues our commitment to democratising this powerful technology. 🎉 Learn more and get started here:
0:21

Today, we’re thrilled to announce the open weights for Stable Diffusion 3 Medium, the latest and most advanced text-to-image AI model in our Stable Diffusion 3 series! This new release represents a major milestone in the evolution of generative AI and continues our commitment to democratising this powerful technology. 🎉 Learn more and get started here:

Stability AI

307,838 views • 2 years ago

🏃Motion Tokenizer Bridging Semantic and Kinematic Conditions🏃‍♀️ #MoTok is a diffusion-based tokenizer that unifies *perception-planning-control*, combining the strengths of continuous diffusion & discrete tokens - Project: - Code:
5:01

🏃Motion Tokenizer Bridging Semantic and Kinematic Conditions🏃‍♀️ #MoTok is a diffusion-based tokenizer that unifies *perception-planning-control*, combining the strengths of continuous diffusion & discrete tokens - Project: - Code:

Ziwei Liu

19,228 views • 2 months ago