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。

Topaz Labs - "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."

Chubby♨️

126,564 subscribers

67,019 次观看 • 1 年前 •via X (Twitter)

科学技术教育艺术

Anya Rossi• Live Now

Private livecam show

11 条评论

Carl Peterson 的头像

Carl Peterson1 年前

Something tells me most of these users won’t be enhancing moon landing footage

Akool Inc 的头像

Akool Inc1 年前

AI has made it easy for anyone to create realistic avatar videos without expensive gear. AKOOL and Synthesia are top choices for AI-generated "talking photo" videos. Which one is best for your team?

VascularHand 的头像

VascularHand1 年前

I have a subscription to their video product...I wonder if this will be included or a stand alone thing.

Chubby♨️ 的头像

Chubby♨️1 年前

Nice. Is it good so far?

Ian Lucas 的头像

Ian Lucas1 年前

So cool

Tim Eckard 的头像

Tim Eckard1 年前

I use Topaz Labs software and it's amazing both for video and photography.

Chubby♨️ 的头像

Chubby♨️1 年前

Good to hear

Drew 👷‍♂️ 🛠️ 🚀 的头像

Drew 👷‍♂️ 🛠️ 🚀1 年前

They need to enhance the JFK video

erosYume 的头像

erosYume1 年前

surprised they're still in the game, used to use some of their stuff in photoshop way back.

TMS 的头像

TMS1 年前

What's video restoration good for? "ENHANCE?"

L8NTLABS 的头像

L8NTLABS1 年前

Project Starlight sounds like a game-changer for video restoration. I can already think of a few old family videos that could benefit from this technology. The potential for preserving memories and historical footage is huge.

相关视频

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

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

Topaz Labs

22,375 次观看 • 1 年前

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

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

329,617 次观看 • 1 年前

🚀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 🧵👇

🚀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

550,052 次观看 • 1 年前

🐵 ALEX MERCER: THE GOLDEN MONKEY My submission for Runway's GEN:48 competition. This is the first chapter of Alex Mercer's adventures! Videos: Runway Images: Leonardo AI Upscaling: Magnific Narration: Gemelo AI Music and SFX: Epidemic Sound & Artlist Video upscale: Topaz Labs AI Video

🐵 ALEX MERCER: THE GOLDEN MONKEY My submission for Runway's GEN:48 competition. This is the first chapter of Alex Mercer's adventures! Videos: Runway Images: Leonardo AI Upscaling: Magnific Narration: Gemelo AI Music and SFX: Epidemic Sound & Artlist Video upscale: Topaz Labs AI Video

Alex Patrascu

140,281 次观看 • 2 年前

NVIDIA just released AnyFlow on Hugging Face The first any-step video diffusion model that generates high-quality text-to-video with any inference budget - 4 steps or 50, quality scales smoothly without degradation.

NVIDIA just released AnyFlow on Hugging Face The first any-step video diffusion model that generates high-quality text-to-video with any inference budget - 4 steps or 50, quality scales smoothly without degradation.

DailyPapers

41,670 次观看 • 2 个月前

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

1,024,498 次观看 • 2 年前

VIDEO UPSCALE TEST: The new Astra 2 Creative model from Topaz Labs is a big improvement over the v1 model - with the sharpness and creativity kept low, the filmic look of the original is being well preserved without the over-sharpness effect common in v1. Comparison test attached: Kling 3 720p original for the first 15 seconds (with a fake upscale to 1080p to make the size match), then Topaz Astra 2 1080p upscale for the next 15 seconds. Image: Midjourney. Video: Kling AI

VIDEO UPSCALE TEST: The new Astra 2 Creative model from Topaz Labs is a big improvement over the v1 model - with the sharpness and creativity kept low, the filmic look of the original is being well preserved without the over-sharpness effect common in v1. Comparison test attached: Kling 3 720p original for the first 15 seconds (with a fake upscale to 1080p to make the size match), then Topaz Astra 2 1080p upscale for the next 15 seconds. Image: Midjourney. Video: Kling AI

Christopher Gwinn | Grindhouse Glitch

12,400 次观看 • 2 个月前

We are thrilled to announce the open-source release of Hallo2: a new avatar video generative model capable of generating stunning 4K resolution videos for up to 1 hour! 🎥✨ Explore the project for the open source code: Let's push the boundaries of avatar video generative model! #OpenSource #AI #FaceAnimation #GenerativeArt

Siyu ZHU

58,323 次观看 • 1 年前

Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution paper page: Text-based diffusion models have exhibited remarkable success in generation and editing, showing great promise for enhancing visual content with their generative prior. However, applying these models to video super-resolution remains challenging due to the high demands for output fidelity and temporal consistency, which is complicated by the inherent randomness in diffusion models. Our study introduces Upscale-A-Video, a text-guided latent diffusion framework for video upscaling. This framework ensures temporal coherence through two key mechanisms: locally, it integrates temporal layers into U-Net and VAE-Decoder, maintaining consistency within short sequences; globally, without training, a flow-guided recurrent latent propagation module is introduced to enhance overall video stability by propagating and fusing latent across the entire sequences. Thanks to the diffusion paradigm, our model also offers greater flexibility by allowing text prompts to guide texture creation and adjustable noise levels to balance restoration and generation, enabling a trade-off between fidelity and quality. Extensive experiments show that Upscale-A-Video surpasses existing methods in both synthetic and real-world benchmarks, as well as in AI-generated videos, showcasing impressive visual realism and temporal consistency.

Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution paper page: Text-based diffusion models have exhibited remarkable success in generation and editing, showing great promise for enhancing visual content with their generative prior. However, applying these models to video super-resolution remains challenging due to the high demands for output fidelity and temporal consistency, which is complicated by the inherent randomness in diffusion models. Our study introduces Upscale-A-Video, a text-guided latent diffusion framework for video upscaling. This framework ensures temporal coherence through two key mechanisms: locally, it integrates temporal layers into U-Net and VAE-Decoder, maintaining consistency within short sequences; globally, without training, a flow-guided recurrent latent propagation module is introduced to enhance overall video stability by propagating and fusing latent across the entire sequences. Thanks to the diffusion paradigm, our model also offers greater flexibility by allowing text prompts to guide texture creation and adjustable noise levels to balance restoration and generation, enabling a trade-off between fidelity and quality. Extensive experiments show that Upscale-A-Video surpasses existing methods in both synthetic and real-world benchmarks, as well as in AI-generated videos, showcasing impressive visual realism and temporal consistency.

AK

32,849 次观看 • 2 年前

First AI video model to generate native 4K. No upscaling needed Kling 3.0 is now available at its highest resolution ever → Text-to-video, image-to-video, reference editing → 3 to 15 sec at true 4K resolution → Ready for ads, film, TV, and livestreams Now on Freepik 💥

First AI video model to generate native 4K. No upscaling needed Kling 3.0 is now available at its highest resolution ever → Text-to-video, image-to-video, reference editing → 3 to 15 sec at true 4K resolution → Ready for ads, film, TV, and livestreams Now on Freepik 💥

Magnific

43,898 次观看 • 3 个月前

At Physical Intelligence (π) our mission is to bring general-purpose AI into the physical world. We're excited to show the first step towards this mission - our first generalist model π₀ 🧠 🤖 Paper, blog, uncut videos:

At Physical Intelligence (π) our mission is to bring general-purpose AI into the physical world. We're excited to show the first step towards this mission - our first generalist model π₀ 🧠 🤖 Paper, blog, uncut videos:

Physical Intelligence

565,344 次观看 • 1 年前

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:

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 次观看 • 4 个月前

Today we are launching Dream Machine, our first AI model that generates cinematic and fluid videos from text instructions and images. I generated this 1-minute 60 fps video entirely from our model. Try Dream Machine → Join us →

Today we are launching Dream Machine, our first AI model that generates cinematic and fluid videos from text instructions and images. I generated this 1-minute 60 fps video entirely from our model. Try Dream Machine → Join us →

Dan Kondratyuk

38,992 次观看 • 2 年前

Showcase: Old Hacklord Huge thanks to Erin for lending us the model and giving us the thumbs-up to post this! This is the first high-quality recording of this skin since April 2025!!! Hope you guys enjoy! Sadly, we couldn't get the intro to work, sorry! #Forsaken

Showcase: Old Hacklord Huge thanks to Erin for lending us the model and giving us the thumbs-up to post this! This is the first high-quality recording of this skin since April 2025!!! Hope you guys enjoy! Sadly, we couldn't get the intro to work, sorry! #Forsaken

Forsaken Wiki (Fandom)

28,334 次观看 • 4 个月前

Honored to have been voted Fan Favourite in the Hailuo AI x Topaz Labs Xtreme Challenge, my first AI video contest participation. Congratulations to the winners for their incredible work, and grateful to be surrounded by so many brilliant participants. Thank you.

Honored to have been voted Fan Favourite in the Hailuo AI x Topaz Labs Xtreme Challenge, my first AI video contest participation. Congratulations to the winners for their incredible work, and grateful to be surrounded by so many brilliant participants. Thank you.

Umesh

36,031 次观看 • 11 个月前

Announcement trailer for "Gala", my new feature-length film project. Created with the just-announced Luma video AI model, #LumaDreamMachine. This is nothing less than a sea change moment for AI video. Thank you to Luma Labs for allowing me to share in the release!

Announcement trailer for "Gala", my new feature-length film project. Created with the just-announced Luma video AI model, #LumaDreamMachine. This is nothing less than a sea change moment for AI video. Thank you to Luma Labs for allowing me to share in the release!

Christopher Fryant

147,469 次观看 • 2 年前

Krea 1 is now available to everyone. today, we're releasing the public beta of our first image model trained in collaboration with Black Forest Labs to offer superior aesthetic control and image quality. learn how to use it for free 👇

Krea 1 is now available to everyone. today, we're releasing the public beta of our first image model trained in collaboration with Black Forest Labs to offer superior aesthetic control and image quality. learn how to use it for free 👇

KREA AI

286,441 次观看 • 1 年前

A parade of the chosen theocracy on Callisto… The AI workflow had a really heavy use of photoshop, Magnific.ai, Kling AI and Topaz Labs Astra for the first shot which was a 480p Midjourney video… also used Runway references through Freepik (now Magnific)

A parade of the chosen theocracy on Callisto… The AI workflow had a really heavy use of photoshop, Magnific.ai, Kling AI and Topaz Labs Astra for the first shot which was a 480p Midjourney video… also used Runway references through Freepik (now Magnific)

Ryan McCoy

32,791 次观看 • 1 年前

This is a short video about the Model Y and what has happened since it was first unveiled in 2019! 🚀

This is a short video about the Model Y and what has happened since it was first unveiled in 2019! 🚀

Billy

125,514 次观看 • 2 年前