Diffuser
- All
- News
- Videos
- Web Stories
-
Tencent Launches HunyuanPortrait, an Open-Source AI Model for Animating Portraits
Tencent released a new artificial intelligence (AI) model on Tuesday that can animate still portrait images. Dubbed HunyuanPortrait, the large language model (LLM) is based on the diffusion architecture, and can generate videos with realistic animation based on a reference image and a guiding video. The researchers behind the project highlighted th...
-
Apple Researchers Introduce Matrix3D, a Unified AI Model That Can Turn 2D Photos Into 3D Objects
Apple researchers released a new artificial intelligence (AI) model that can generate 3D views from multiple 2D images. The large language model (LLM), dubbed Matrix3D, was developed by the company’s Machine Learning team, in collaboration with Nanjing University and the Hong Kong University of Science and Technology (HKUST). The Cupertino-based ...
-
Character AI Unveils AvatarFX Model Capable of Generating Consistent Videos From Images
Character AI, the California-based artificial intelligence (AI) platform, unveiled its first video generation model on Monday. Dubbed AvatarFX, it is an image-to-video model that can generate 2D and 3D animated characters. The AI firm claims the generated videos will hold temporal consistency with face, hand and body movement. Additionally, the vid...
-
NASA Rockets Set to Journey Through Flickering, Disappearing Auroras
NASA is set to launch two groundbreaking rocket missions in January 2025 to unravel the mysteries of auroras. The GIRAFF mission will study fast-pulsating and flickering auroras, while the Black and Diffuse Aurora Science Surveyor mission will focus on dark auroral patches or "black auroras." By using advanced instruments to measure electron activi...
-
Covalent Organic Frameworks Show Promise for Enhanced Energy Transport Efficiency
An interdisciplinary study has uncovered how covalent organic frameworks (COFs) facilitate highly efficient energy transport, even across structural imperfections. Advanced spectroscopic analysis revealed high diffusion coefficients and dual transport mechanisms—coherent and incoherent diffusion—showcasing the potential of these materials for a...
-
Astronomers Uncover New Details of CIZA0107 Galaxy Cluster Merger with VLA
A team of astronomers, led by Emma Schwartzmann from the U.S. Naval Research Laboratory, used the Very Large Array (VLA) to study the nearby galaxy cluster merger CIZA J0107.7+5408 (CIZA0107). The observations provided new insights into the dynamics of galaxy mergers, revealing a disturbed system with two subclusters and diffuse radio emission span...
-
British Influencer Leila Layzell's Viral Tactic To Avoid Unwanted Male Attention
In a viral video with over 500,000 views, Layzell cleverly diffuses a mans persistent request for her phone number by recording herself and him while humorously asking, "Can I show my mom, my husband?"
-
OpenAI Sora AI Video Generation Model Launched; Now Available to Paid Subscribers
OpenAI finally launched Sora, its artificial intelligence (AI) video generation model, on Monday. In February, the company previewed Sora to select individuals, and now, it released a different variant of the model dubbed Sora Turbo. Sora can generate videos in 1080p resolution which can be as long as 20 seconds. The AI model has been deployed on a...
-
Google’s AI-Powered Weather Prediction Model GenCast Outperforms Top Forecasting Systems, Says Study
Google introduced its weather predicting artificial intelligence (AI) model GenCast on Wednesday. The AI model was developed by the Mountain View-based tech giant’s AI research division Google DeepMind. The company’s researchers have also published a paper on the technology highlighting its capabilities in making medium-range weather forecasts....
-
Nvidia Research Introduces DiffUHaul, an AI Tool That Allows Object Relocation in Images
Nvidia researchers introduced a new artificial intelligence (AI) model that can relocate objects in an image. Dubbed DiffUHaul, the tool can spatially understand the context of an image to move an object from one place to another without impacting the background or the shape of the image. The unique aspect of this technique is that it is training-f...
-
Lightricks Introduces Open-Source LTX Video AI Model With Real-Time Video Generation Capability
Lightricks, a software company focused on image and video editing, released an open-source artificial intelligence (AI) video model in preview last week. Dubbed LTX Video, the AI model can generate medium-resolution videos in real time. While real-time video generation capability exists in a few large language models (LLMs), this is the first one t...
-
AI Technology Detects Cancerous Brain Tumours in 10 Seconds During Surgery
Researchers have developed FastGlioma, an AI-based model that can identify residual brain tumour tissue in just 10 seconds during surgery. The technology, which outperformed conventional methods, offers significant improvements in neurosurgery for diffuse gliomas and other cancers. It could revolutionise surgical practices by enabling faster, more ...
-
Indian Researchers Find a New Technique to Control Defects in MOF-Based Supercapacitors
Researchers at the Institute of Nano Science and Technology (INST), Mohali, have developed a new laser-based method to precisely control defects in MOF-based supercapacitors. This technique significantly enhances energy storage performance without altering the MOF’s crystal structure. By adjusting laser power, scientists increased the electrode's...
-
Google Researchers Announce GameNGen, an AI-Powered Game Engine That Can Run Doom
Google researchers announced a new artificial intelligence (AI) game engine last week. Dubbed GameNGen, it is entirely powered by a neural model and is capable of real-time generation over a long trajectory. The researchers claim that the game engine can generate complex environments at a high number of frames. Notably, the company claims that the ...
-
Google Releases Imagen 3 AI Image Generation Model to Users, Adds Improved Capabilities
Google released its in-house artificial intelligence (AI) model for image generation, Imagen 3, on Thursday. The tech giant did not make any announcement for the release, and instead released the model quietly to users. Additionally, a research paper detailing the workings of the image generation model was also published in an online journal.
-
Tencent Launches HunyuanPortrait, an Open-Source AI Model for Animating Portraits
Tencent released a new artificial intelligence (AI) model on Tuesday that can animate still portrait images. Dubbed HunyuanPortrait, the large language model (LLM) is based on the diffusion architecture, and can generate videos with realistic animation based on a reference image and a guiding video. The researchers behind the project highlighted th...
-
Apple Researchers Introduce Matrix3D, a Unified AI Model That Can Turn 2D Photos Into 3D Objects
Apple researchers released a new artificial intelligence (AI) model that can generate 3D views from multiple 2D images. The large language model (LLM), dubbed Matrix3D, was developed by the company’s Machine Learning team, in collaboration with Nanjing University and the Hong Kong University of Science and Technology (HKUST). The Cupertino-based ...
-
Character AI Unveils AvatarFX Model Capable of Generating Consistent Videos From Images
Character AI, the California-based artificial intelligence (AI) platform, unveiled its first video generation model on Monday. Dubbed AvatarFX, it is an image-to-video model that can generate 2D and 3D animated characters. The AI firm claims the generated videos will hold temporal consistency with face, hand and body movement. Additionally, the vid...
-
NASA Rockets Set to Journey Through Flickering, Disappearing Auroras
NASA is set to launch two groundbreaking rocket missions in January 2025 to unravel the mysteries of auroras. The GIRAFF mission will study fast-pulsating and flickering auroras, while the Black and Diffuse Aurora Science Surveyor mission will focus on dark auroral patches or "black auroras." By using advanced instruments to measure electron activi...
-
Covalent Organic Frameworks Show Promise for Enhanced Energy Transport Efficiency
An interdisciplinary study has uncovered how covalent organic frameworks (COFs) facilitate highly efficient energy transport, even across structural imperfections. Advanced spectroscopic analysis revealed high diffusion coefficients and dual transport mechanisms—coherent and incoherent diffusion—showcasing the potential of these materials for a...
-
Astronomers Uncover New Details of CIZA0107 Galaxy Cluster Merger with VLA
A team of astronomers, led by Emma Schwartzmann from the U.S. Naval Research Laboratory, used the Very Large Array (VLA) to study the nearby galaxy cluster merger CIZA J0107.7+5408 (CIZA0107). The observations provided new insights into the dynamics of galaxy mergers, revealing a disturbed system with two subclusters and diffuse radio emission span...
-
British Influencer Leila Layzell's Viral Tactic To Avoid Unwanted Male Attention
In a viral video with over 500,000 views, Layzell cleverly diffuses a mans persistent request for her phone number by recording herself and him while humorously asking, "Can I show my mom, my husband?"
-
OpenAI Sora AI Video Generation Model Launched; Now Available to Paid Subscribers
OpenAI finally launched Sora, its artificial intelligence (AI) video generation model, on Monday. In February, the company previewed Sora to select individuals, and now, it released a different variant of the model dubbed Sora Turbo. Sora can generate videos in 1080p resolution which can be as long as 20 seconds. The AI model has been deployed on a...
-
Google’s AI-Powered Weather Prediction Model GenCast Outperforms Top Forecasting Systems, Says Study
Google introduced its weather predicting artificial intelligence (AI) model GenCast on Wednesday. The AI model was developed by the Mountain View-based tech giant’s AI research division Google DeepMind. The company’s researchers have also published a paper on the technology highlighting its capabilities in making medium-range weather forecasts....
-
Nvidia Research Introduces DiffUHaul, an AI Tool That Allows Object Relocation in Images
Nvidia researchers introduced a new artificial intelligence (AI) model that can relocate objects in an image. Dubbed DiffUHaul, the tool can spatially understand the context of an image to move an object from one place to another without impacting the background or the shape of the image. The unique aspect of this technique is that it is training-f...
-
Lightricks Introduces Open-Source LTX Video AI Model With Real-Time Video Generation Capability
Lightricks, a software company focused on image and video editing, released an open-source artificial intelligence (AI) video model in preview last week. Dubbed LTX Video, the AI model can generate medium-resolution videos in real time. While real-time video generation capability exists in a few large language models (LLMs), this is the first one t...
-
AI Technology Detects Cancerous Brain Tumours in 10 Seconds During Surgery
Researchers have developed FastGlioma, an AI-based model that can identify residual brain tumour tissue in just 10 seconds during surgery. The technology, which outperformed conventional methods, offers significant improvements in neurosurgery for diffuse gliomas and other cancers. It could revolutionise surgical practices by enabling faster, more ...
-
Indian Researchers Find a New Technique to Control Defects in MOF-Based Supercapacitors
Researchers at the Institute of Nano Science and Technology (INST), Mohali, have developed a new laser-based method to precisely control defects in MOF-based supercapacitors. This technique significantly enhances energy storage performance without altering the MOF’s crystal structure. By adjusting laser power, scientists increased the electrode's...
-
Google Researchers Announce GameNGen, an AI-Powered Game Engine That Can Run Doom
Google researchers announced a new artificial intelligence (AI) game engine last week. Dubbed GameNGen, it is entirely powered by a neural model and is capable of real-time generation over a long trajectory. The researchers claim that the game engine can generate complex environments at a high number of frames. Notably, the company claims that the ...
-
Google Releases Imagen 3 AI Image Generation Model to Users, Adds Improved Capabilities
Google released its in-house artificial intelligence (AI) model for image generation, Imagen 3, on Thursday. The tech giant did not make any announcement for the release, and instead released the model quietly to users. Additionally, a research paper detailing the workings of the image generation model was also published in an online journal.
