Loading video...

Video Failed to Load

Go Home

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.

_akhaliq's profile picture

AK

486,426 subscribers

150,538 views • 2 years ago •via X (Twitter)

ArtsEducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Introducing SDXL Turbo: A real-time text-to-image generation model. SDXL Turbo achieves state-of-the-art performance with a new distillation technology, enabling single-step image generation with unprecedented quality, reducing the required step count from 50 to just one. The code, research paper, and weights for non-commercial use are now available on our website. You can test SDXL Turbo on Stability AI’s image editing platform Clipdrop, with a beta demonstration of the real-time text-to-image generation capabilities. Learn more:
0:23

Introducing SDXL Turbo: A real-time text-to-image generation model. SDXL Turbo achieves state-of-the-art performance with a new distillation technology, enabling single-step image generation with unprecedented quality, reducing the required step count from 50 to just one. The code, research paper, and weights for non-commercial use are now available on our website. You can test SDXL Turbo on Stability AI’s image editing platform Clipdrop, with a beta demonstration of the real-time text-to-image generation capabilities. Learn more:

Stability AI

976,258 views • 2 years ago

Nvidia presents ConsiStory Training-Free Consistent Text-to-Image Generation paper page: enable Stable Diffusion XL (SDXL) to generate consistent subjects across a series of images, without additional training.
1:01

Nvidia presents ConsiStory Training-Free Consistent Text-to-Image Generation paper page: enable Stable Diffusion XL (SDXL) to generate consistent subjects across a series of images, without additional training.

AK

161,673 views • 2 years ago

Real-Time Neural Light Field on Mobile Devices abs: project page:
0:27

Real-Time Neural Light Field on Mobile Devices abs: project page:

AK

56,201 views • 3 years ago

Introducing Nano Banana Pro (Gemini 3 Pro Image), our new state-of-the-art image generation and editing model from Google DeepMind. It improves on the original model while adding new advanced capabilities, enhanced world knowledge and text rendering, allowing you to create and edit studio-quality, production-ready visuals.
1:18

Introducing Nano Banana Pro (Gemini 3 Pro Image), our new state-of-the-art image generation and editing model from Google DeepMind. It improves on the original model while adding new advanced capabilities, enhanced world knowledge and text rendering, allowing you to create and edit studio-quality, production-ready visuals.

Google

1,896,732 views • 6 months ago

The winner of Lovable's weekend competition: Kolbo ai - A powerful tool to help make all sorts of social media content with AI Features of the winning app: - Supabase for backend - Project-based organization system - OpenAI for text & image generation - Anthropic for text generation - Google Gemini for text generation - Midjourney for image generation - for image generation - Text-to-speech - Speech-to-text - Stripe for payments - mu for music generation Built by Zohar Vanunu 👇
5:29

The winner of Lovable's weekend competition: Kolbo ai - A powerful tool to help make all sorts of social media content with AI Features of the winning app: - Supabase for backend - Project-based organization system - OpenAI for text & image generation - Anthropic for text generation - Google Gemini for text generation - Midjourney for image generation - for image generation - Text-to-speech - Speech-to-text - Stripe for payments - mu for music generation Built by Zohar Vanunu 👇

Lovable

35,841 views • 1 year ago

Ideogram AI presents Ideogram 1.0 text-to-image model offers state-of-the-art text rendering, unprecedented photorealism, exceptional prompt adherence, and a new feature called Magic Prompt to help with prompting
1:00

Ideogram AI presents Ideogram 1.0 text-to-image model offers state-of-the-art text rendering, unprecedented photorealism, exceptional prompt adherence, and a new feature called Magic Prompt to help with prompting

AK

96,079 views • 2 years ago

VideoRF: Rendering Dynamic Radiance Fields as 2D Feature Video Streams paper page: Neural Radiance Fields (NeRFs) excel in photorealistically rendering static scenes. However, rendering dynamic, long-duration radiance fields on ubiquitous devices remains challenging, due to data storage and computational constraints. In this paper, we introduce VideoRF, the first approach to enable real-time streaming and rendering of dynamic radiance fields on mobile platforms. At the core is a serialized 2D feature image stream representing the 4D radiance field all in one. We introduce a tailored training scheme directly applied to this 2D domain to impose the temporal and spatial redundancy of the feature image stream. By leveraging the redundancy, we show that the feature image stream can be efficiently compressed by 2D video codecs, which allows us to exploit video hardware accelerators to achieve real-time decoding. On the other hand, based on the feature image stream, we propose a novel rendering pipeline for VideoRF, which has specialized space mappings to query radiance properties efficiently. Paired with a deferred shading model, VideoRF has the capability of real-time rendering on mobile devices thanks to its efficiency. We have developed a real-time interactive player that enables online streaming and rendering of dynamic scenes, offering a seamless and immersive free-viewpoint experience across a range of devices, from desktops to mobile phones.
4:56

VideoRF: Rendering Dynamic Radiance Fields as 2D Feature Video Streams paper page: Neural Radiance Fields (NeRFs) excel in photorealistically rendering static scenes. However, rendering dynamic, long-duration radiance fields on ubiquitous devices remains challenging, due to data storage and computational constraints. In this paper, we introduce VideoRF, the first approach to enable real-time streaming and rendering of dynamic radiance fields on mobile platforms. At the core is a serialized 2D feature image stream representing the 4D radiance field all in one. We introduce a tailored training scheme directly applied to this 2D domain to impose the temporal and spatial redundancy of the feature image stream. By leveraging the redundancy, we show that the feature image stream can be efficiently compressed by 2D video codecs, which allows us to exploit video hardware accelerators to achieve real-time decoding. On the other hand, based on the feature image stream, we propose a novel rendering pipeline for VideoRF, which has specialized space mappings to query radiance properties efficiently. Paired with a deferred shading model, VideoRF has the capability of real-time rendering on mobile devices thanks to its efficiency. We have developed a real-time interactive player that enables online streaming and rendering of dynamic scenes, offering a seamless and immersive free-viewpoint experience across a range of devices, from desktops to mobile phones.

AK

38,686 views • 2 years ago

DOMINATE THE BATTLEFIELD Counter Fire is officially live on mobile devices and available to download on the App Store and Google Play:
0:40

DOMINATE THE BATTLEFIELD Counter Fire is officially live on mobile devices and available to download on the App Store and Google Play:

Immutable

590,433 views • 1 year ago

How to Use Automator on Google Flow for Image Generation — New 2026 Update. 🔥 A step-by-step guide on setting up automated image generation workflows smoothly and efficiently on Google Flow. RT if you gained value. 🚀
5:34

How to Use Automator on Google Flow for Image Generation — New 2026 Update. 🔥 A step-by-step guide on setting up automated image generation workflows smoothly and efficiently on Google Flow. RT if you gained value. 🚀

Mayowa

23,513 views • 1 month ago

Going to #CVPR2023 ? Checkout our tutorial on Efficient Neural Networks: From Algorithm Design to Practical Mobile Deployment. We’ll do a deep dive into mobile transformers, mobile neural rendering and SnapFusion--the fastest mobile text-to-image model. Our content in 32 seconds
0:32

Going to #CVPR2023 ? Checkout our tutorial on Efficient Neural Networks: From Algorithm Design to Practical Mobile Deployment. We’ll do a deep dive into mobile transformers, mobile neural rendering and SnapFusion--the fastest mobile text-to-image model. Our content in 32 seconds

Sergey Tulyakov

23,359 views • 3 years ago

GoogleAI just released "Muse", a text-to-image generation/editing model via Masked Generative Transformers: - Achieves new SOTA - Zero-shot, Mask-free editing - Zero-shot Inpainting/Outpainting - 900M params 📄 Paper: ⚙️ Project:
0:27

GoogleAI just released "Muse", a text-to-image generation/editing model via Masked Generative Transformers: - Achieves new SOTA - Zero-shot, Mask-free editing - Zero-shot Inpainting/Outpainting - 900M params 📄 Paper: ⚙️ Project:

Lior Alexander

630,453 views • 3 years ago

Mobile developers! Unreal Engine 5.5 is here, with a bunch of improvements to help your projects being developed for mobile devices. Let’s take a look 🧵
0:32

Mobile developers! Unreal Engine 5.5 is here, with a bunch of improvements to help your projects being developed for mobile devices. Let’s take a look 🧵

Unreal Engine

19,375 views • 1 year ago

Here is Hugo Feiler talking about Minima and running a full node on mobile devices, and the vision for chips
0:28

Here is Hugo Feiler talking about Minima and running a full node on mobile devices, and the vision for chips

We are DePIN

22,691 views • 11 months ago

Designing an Encoder for Fast Personalization of Text-to-Image Models TL;DR: use an encoder to personalize a text-to-image model to new concepts with a single image and 5-15 tuning steps abs: project page:
0:43

Designing an Encoder for Fast Personalization of Text-to-Image Models TL;DR: use an encoder to personalize a text-to-image model to new concepts with a single image and 5-15 tuning steps abs: project page:

AK

165,158 views • 3 years ago

Introducing Image to App. Turn any image into a native mobile app. Just paste an image. Claude Code Opus 4.6 will design, code, deploy and translate a mobile app inspired by original design. We’ve used this internally a lot for consumer apps on iOS/Android.
0:30

Introducing Image to App. Turn any image into a native mobile app. Just paste an image. Claude Code Opus 4.6 will design, code, deploy and translate a mobile app inspired by original design. We’ve used this internally a lot for consumer apps on iOS/Android.

David Ch

173,352 views • 1 month ago

The World’s Game in Your Pocket. EA SPORTS FC™ MOBILE 24 is now available for mobile devices on Android and iOS. Play #FCMOBILE now! Android/Google Play: iOS/App Store:
0:30

The World’s Game in Your Pocket. EA SPORTS FC™ MOBILE 24 is now available for mobile devices on Android and iOS. Play #FCMOBILE now! Android/Google Play: iOS/App Store:

EA SPORTS FC MOBILE

4,031,897 views • 2 years ago

Excited to share a Google DeepMind Gemini 2.0 Flash Image Generation and Editing Quickstart. We build a Next.js reference app on how to use the new image editing feature of Gemini 2.0 Flash. Demo to test ⬇️ > Generate images from text prompts using Gemini 2.0 Flash > Or upload an image and edit it using prompts
0:48

Excited to share a Google DeepMind Gemini 2.0 Flash Image Generation and Editing Quickstart. We build a Next.js reference app on how to use the new image editing feature of Gemini 2.0 Flash. Demo to test ⬇️ > Generate images from text prompts using Gemini 2.0 Flash > Or upload an image and edit it using prompts

Philipp Schmid

52,406 views • 1 year ago

Introducing StyleDrop, a model that allows a significantly higher level of stylized text-to-image synthesis by using a few style reference images that describe the style for text-to-image generation, bypassing the burden of text prompt engineering. More→
0:42

Introducing StyleDrop, a model that allows a significantly higher level of stylized text-to-image synthesis by using a few style reference images that describe the style for text-to-image generation, bypassing the burden of text prompt engineering. More→

Google AI

80,357 views • 2 years ago

Guild Wars Reforged hits mobile devices this summer with a new, mobile‑optimized UI and controls. Preregister to get notified at launch. Already playing with an ArenaNet account? You'll be able to log in on mobile and play cross‑platform.
0:30

Guild Wars Reforged hits mobile devices this summer with a new, mobile‑optimized UI and controls. Preregister to get notified at launch. Already playing with an ArenaNet account? You'll be able to log in on mobile and play cross‑platform.

Guild Wars

197,704 views • 1 month ago

🚀 Announcing Nano Banana Pro!🍌 State of the art image generation from Google DeepMind! Here's 7m of demos:
6:38

🚀 Announcing Nano Banana Pro!🍌 State of the art image generation from Google DeepMind! Here's 7m of demos:

Addy Osmani

11,198 views • 6 months ago