Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

It was a privilege to present in the Google booth our work: RefVNLI: Scalable Evaluation of Subject-driven Text-to-Image Generation ( – led by Aviv Slobodkin

Yonatan Bitton

3,483 subscribers

29,072 views • 1 year ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Snap presents MoA Mixture-of-Attention for Subject-Context Disentanglement in Personalized Image Generation We introduce a new architecture for personalization of text-to-image diffusion models, coined Mixture-of-Attention (MoA). Inspired by the Mixture-of-Experts

Snap presents MoA Mixture-of-Attention for Subject-Context Disentanglement in Personalized Image Generation We introduce a new architecture for personalization of text-to-image diffusion models, coined Mixture-of-Attention (MoA). Inspired by the Mixture-of-Experts

AK

47,488 views • 2 years ago

Ever had a perfect image in mind that a text-to-image model just couldn't capture? Our new reinforcement learning agent, PASTA, turns image generation into a collaborative conversation, learning your style to bring your vision to life. Learn how it works:

Ever had a perfect image in mind that a text-to-image model just couldn't capture? Our new reinforcement learning agent, PASTA, turns image generation into a collaborative conversation, learning your style to bring your vision to life. Learn how it works:

Google Research

25,808 views • 10 months ago

Google presents MobileDiffusion Subsecond Text-to-Image Generation on Mobile Devices paper page: MobileDiffusion achieves a remarkable sub-second inference speed for generating a 512 × 512 image on mobile devices, establishing a new state of the art.

Google presents MobileDiffusion Subsecond Text-to-Image Generation on Mobile Devices paper page: MobileDiffusion achieves a remarkable sub-second inference speed for generating a 512 × 512 image on mobile devices, establishing a new state of the art.

AK

150,554 views • 2 years ago

Let your audio shape the narrative with Wan2.5 🎬 Native audio-driven video generation lets you shape stories, no matter if its text-to-video and image-to-video generation. Make your images come to life now!

Let your audio shape the narrative with Wan2.5 🎬 Native audio-driven video generation lets you shape stories, no matter if its text-to-video and image-to-video generation. Make your images come to life now!

Alibaba Group

109,340 views • 9 months ago

How Jennifer Lopez's Green Gown Led to the Birth of Google Images. Back in 2000, Jennifer Lopez walked the red carpet in a daring green Versace gown, and the world couldn't stop talking about it. The dress dominated headlines and had millions of people rushing online, all asking the same thing: "Where can I see that dress?". The problem was Google at the time could only show text-based results. The massive surge of interest in J.Lo's look revealed a major gap in search, a gap that led to the birth of Google Images.

How Jennifer Lopez's Green Gown Led to the Birth of Google Images. Back in 2000, Jennifer Lopez walked the red carpet in a daring green Versace gown, and the world couldn't stop talking about it. The dress dominated headlines and had millions of people rushing online, all asking the same thing: "Where can I see that dress?". The problem was Google at the time could only show text-based results. The massive surge of interest in J.Lo's look revealed a major gap in search, a gap that led to the birth of Google Images.

Lemma’s Animal Desk

2,202,732 views • 7 months ago

Text-to-image diffusion transformer models learn to align text and image representations as a byproduct of their conditional denoising task. By taking the dot product between the text and image representations of a DiT model (like Flux 2), you can create rich saliency maps.

Text-to-image diffusion transformer models learn to align text and image representations as a byproduct of their conditional denoising task. By taking the dot product between the text and image representations of a DiT model (like Flux 2), you can create rich saliency maps.

Alec Helbling

94,195 views • 7 months ago

Starting today, we’re making it easier for everyone to verify if an image was created or edited with Google AI with SynthID, our digital watermarking technology, right in Google Gemini.

Starting today, we’re making it easier for everyone to verify if an image was created or edited with Google AI with SynthID, our digital watermarking technology, right in Google Gemini.

Google

275,805 views • 8 months ago

Arena Trends: Text-to-Image, Jan 2026 – Apr 2026 For most of the year, Google DeepMind and OpenAI traded the top spot within a tight margin - GPT-Image vs. Nano Banana - with the rest of the field clustered below 1,200. Today, GPT-Image-2 breaks away with a score of 1,512, 242 points ahead of #2 Google. The frontier continues to move.

Arena Trends: Text-to-Image, Jan 2026 – Apr 2026 For most of the year, Google DeepMind and OpenAI traded the top spot within a tight margin - GPT-Image vs. Nano Banana - with the rest of the field clustered below 1,200. Today, GPT-Image-2 breaks away with a score of 1,512, 242 points ahead of #2 Google. The frontier continues to move.

Arena.ai

514,995 views • 3 months ago

One of the best men in history. It was a privilege to get to know you

One of the best men in history. It was a privilege to get to know you

Nala Ray

111,047 views • 10 months ago

From product image to video with just one tool - Dzine As you may have noticed, this is one of my favorite tools. It is also very underrated, as probably 50% of my tutorials include some workflow. I was testing the new image-to-video option today, and I love it. Step - by step guide in comments 🔽 I can do 95% of a workflow without switching between apps. Image generation, Image to image with style reference, background removal, background generation, and 2 frames image to video. The only other app I have been using for this video is CapCut so that I can stitch it together. Step by step 🔽

From product image to video with just one tool - Dzine As you may have noticed, this is one of my favorite tools. It is also very underrated, as probably 50% of my tutorials include some workflow. I was testing the new image-to-video option today, and I love it. Step - by step guide in comments 🔽 I can do 95% of a workflow without switching between apps. Image generation, Image to image with style reference, background removal, background generation, and 2 frames image to video. The only other app I have been using for this video is CapCut so that I can stitch it together. Step by step 🔽

Teodora P L

28,523 views • 1 year ago

For a ridiculously long time, I was creating a CMS field in Webflow for alt text for every image. I thought it was just me, but apparently not. So, this is for everyone else who didn't know you can add alt text directly to the image in CMS.

For a ridiculously long time, I was creating a CMS field in Webflow for alt text for every image. I thought it was just me, but apparently not. So, this is for everyone else who didn't know you can add alt text directly to the image in CMS.

Jordan Gilroy

11,704 views • 1 year ago

Switti -- a new scale-wise transformer for text-to-image generation 🦾 🔥 Improved generation of fine-grained details. Outperforms existing T2I AR models and competes with state-of-the-art T2I diffusion models while being up to 7x faster.

Switti -- a new scale-wise transformer for text-to-image generation 🦾 🔥 Improved generation of fine-grained details. Outperforms existing T2I AR models and competes with state-of-the-art T2I diffusion models while being up to 7x faster.

Gradio

29,314 views • 1 year ago

We’re rolling out Veo to Vertex AI in private preview to help businesses generate high-quality video from a text/image prompt, with our Synth ID watermark embedded. Here’s an example of how it generates a short clip based on a text prompt.

We’re rolling out Veo to Vertex AI in private preview to help businesses generate high-quality video from a text/image prompt, with our Synth ID watermark embedded. Here’s an example of how it generates a short clip based on a text prompt.

Sundar Pichai

211,649 views • 1 year ago

🚨 BIG BREAKING: Major attack on the IDF in Tel Aviv. According to recent reports, Iran has launched a massive missile strike on an IDF facility in Tel Aviv. Benjamin Netanyahu, Israel's Prime Minister, was killed instantly in the attack. It is reported that Benjamin Netanyahu was present at the site at the time of the attack.

🚨 BIG BREAKING: Major attack on the IDF in Tel Aviv. According to recent reports, Iran has launched a massive missile strike on an IDF facility in Tel Aviv. Benjamin Netanyahu, Israel's Prime Minister, was killed instantly in the attack. It is reported that Benjamin Netanyahu was present at the site at the time of the attack.

Ebrahim Zolfaghari ابراهیم ذوالفقاری

37,065 views • 8 days ago

In 2022, a man from Devon in England was running from the cops when cows started chasing him, which led to the police catching the subject.

In 2022, a man from Devon in England was running from the cops when cows started chasing him, which led to the police catching the subject.

Historic Vids

749,044 views • 2 years ago

Tired of 1B+ parameter VLMs that require massive GPUs and take 1s+ to process an image? Do you miss live demos? Come to the CVPR Meta booth Friday + Saturday 10am-12pm, I'll be giving a new live demo running on a LAPTOP of our egocentric 3DBB demo of our latest work, Boxer

Tired of 1B+ parameter VLMs that require massive GPUs and take 1s+ to process an image? Do you miss live demos? Come to the CVPR Meta booth Friday + Saturday 10am-12pm, I'll be giving a new live demo running on a LAPTOP of our egocentric 3DBB demo of our latest work, Boxer

Daniel DeTone

17,818 views • 1 month ago

Today our worst fear have become a reality. As we had previously anticipated the actions of the previous government have led to a situation where the Indian military is unlawfully present in our seas.! #IndiaOut

Today our worst fear have become a reality. As we had previously anticipated the actions of the previous government have led to a situation where the Indian military is unlawfully present in our seas.! #IndiaOut

Soofi

10,009 views • 2 years ago

Last day of #MidsummerScream! Stop by booth 618 to claim one of our many prizes left in the claw machine!

Last day of #MidsummerScream! Stop by booth 618 to claim one of our many prizes left in the claw machine!

Mob Entertainment

93,711 views • 11 months ago

👑 Female-led, creator-driven, and powered by innovation. Meet Gabrielle Taylor, our visionary CEO. She’s on a mission to revolutionize content creation.

👑 Female-led, creator-driven, and powered by innovation. Meet Gabrielle Taylor, our visionary CEO. She’s on a mission to revolutionize content creation.

SUBBD

191,722 views • 1 year ago

📍Bilaspur, Chhattisgarh: An out-of-control Maruti Suzuki Swift Dzire rammed into a Renault Triber parked outside a house. CCTV footage shows the car crashing in a dramatic, filmi-style impact. The vehicle was being driven by a minor. Fortunately, no one was standing nearby at the time; otherwise, it could have led to a serious tragedy.

📍Bilaspur, Chhattisgarh: An out-of-control Maruti Suzuki Swift Dzire rammed into a Renault Triber parked outside a house. CCTV footage shows the car crashing in a dramatic, filmi-style impact. The vehicle was being driven by a minor. Fortunately, no one was standing nearby at the time; otherwise, it could have led to a serious tragedy.

Deadly Kalesh

24,035 views • 5 months ago