Are you still troubled by unclear photos? A brand new image super-resolution tool called InvSR has emerged, allowing images to be instantly transformed into clear and sharp ones with minimal processing steps. The strength of this tool lies in its utilization of the rich prior knowledge embedded in large pre-trained diffusion models, achieving efficient and high-quality image resolution enhancement. The core technology of InvSR is its innovative partial noise prediction strategy. It cleverly constructs the intermediate state of the diffusion model as the starting point for the sampling process and employs a deep noise.

With the development of digital art, automated image processing technology has received increasing attention. Recently, a research team from Tsinghua University and Tencent's ARC Lab proposed a novel image sequence coloring model called ColorFlow. This model aims to address the challenge of maintaining consistency in character and object identity while coloring black and white image sequences, fulfilling the practical needs of industries such as comics and animation. ColorFlow is a three-stage diffusion base framework that leverages contextual information by utilizing a reference image pool for black and white.

In 2024, the global AI craze continues to rise, and Thailand is no exception, standing on the brink of an explosion in artificial intelligence (AI). Imagine strolling through the streets of Bangkok, where everything around you is quietly changing. Restaurants have smart ordering systems that can converse with you fluently in Thai, hospitals have AI diagnostic systems capable of accurately analyzing your health status, and even the shared bicycles on the roadside are equipped with smart navigation. This is no fantasy; it is the ongoing AI transformation in Thailand. Image source note: The image is generated by AI, and the image is authorized.

Yesterday, Shanji Technology announced the launch of China's first mass-produced AI photography glasses - Shanji AI拍照 Glasses. The retail price for these glasses is 1499 Yuan, while the first batch of 50,000 co-creation versions is discounted to 999 Yuan, along with a promotional offer of a refundable 300-day purchase if used for 200 days. The Shanji AI拍照 Glasses are the first in the industry to feature a Sony 16MP, 123-degree ultra-wide-angle camera module, and are equipped with a flagship low-power ARM platform from UNISOC. These glasses also include a 6500mAh extended battery, supporting HI-F.

Beijing TuSimple Technology Co., Ltd. has officially changed its name to CreateAI. This rebranding comes alongside the announcement of several significant advancements in the generative AI field, marking its ambitious plans to apply generative AI technology in the animation and video game industries. Additionally, CreateAI announced that it has acquired the official licensing rights to the renowned wuxia intellectual property 'The Legend of the Condor Heroes' and plans to develop a large-scale open-world RPG game. Furthermore, the company will collaborate with notable animation director Masashi Hoshino and leading animation production company Hashimoto Co., Ltd. to utilize AIGC.

FF has announced a series of in-vehicle software updates for its flagship model, the FF 91 2.0 Futurist Alliance. These updates are designed to enhance the in-car entertainment experience and user control functions, further improving the vehicle's revolutionary user experience and creating a mobile, interconnected, intelligent, and luxurious Third AI Space. The updates take effect immediately via OTA (Over-The-Air), optimizing vehicle interaction for a more intuitive and convenient operation.

The AI application development platform Coze has announced the launch of its new version—Coze 1.5—at the Volcano Engine FORCE Power Conference. This update marks a significant step forward for the Coze platform in the field of AI application development, aiming to provide users with a more powerful and convenient development environment. The core highlight of Coze 1.5 is its support for a GUI (Graphical User Interface) development interface, allowing one-click publishing to various application formats such as mini programs, H5, and APIs. This feature enables users to quickly build applications based on large models, regardless of whether they have programming knowledge.

During the 2024 Volcano Engine FORCE Power Conference · Winter, Volcano Engine announced a brand new upgrade of the Doubao Large Model family, showcasing its latest advancements in the field of artificial intelligence. The daily tokens usage of the Doubao Large Model has exceeded 4 trillion, reflecting an increase of over 33 times since its release in May, demonstrating its widespread application and rapid growth in the industry.

YouTube recently announced a collaboration with the Creative Artists Agency (CAA) to help celebrities and creators identify content on the platform using their AI-generated images and submit removal requests. This technology is planned to be tested early next year, initially focusing on celebrities and athletes, before expanding to 'top YouTube creators, creative professionals, and other leading partners representing talent.' Last year, CAA launched CAAVault, a service that scans and stores its clients' digital images.

Pollo AI, a leader in the field of AI video generation, recently released four new AI effects, attracting attention in the industry once again. Users can easily achieve effects like 'squeeze,' 'inflate,' 'explode,' and 'melt' by simply uploading static images, bringing anything (or anyone) to 'life' in videos using advanced AI technology. Additionally, Pollo AI has appropriately introduced several holiday-themed templates to help users quickly create short videos filled with a Christmas atmosphere. The four newly launched effects each have their own unique characteristics.

Slack recently announced a deep integration of its Agentforce AI assistant with Salesforce, aimed at enhancing business efficiency through contextual intelligence. This integration will be a key component of Salesforce Agentforce 2.0, which is expected to launch officially on December 17. In an exclusive interview, Slack's Chief Product Officer Rob Seaman pointed out that the Slack platform typically reflects the structure of the organization and when

In the field of video analysis, the persistence of objects is an important cue for humans to understand that objects still exist even when completely occluded. However, current object segmentation methods mainly focus on visible (modal) objects, lacking the capability to handle non-modal (visible + invisible) objects. To address this issue, researchers proposed a two-stage method based on diffusion priors, Diffusion-Vas, aimed at improving the effectiveness of non-modal segmentation and content completion in videos, enabling the tracking of specified targets within the video and using diffusion models to complete the occluded parts.

Recently, Meta officially launched an open-source AI virtual try-on framework named Leffa. This framework aims to enhance the user dressing experience by generating new images, allowing users to switch between different clothing and poses based on a reference image. Compared to previous methods, Leffa excels in detail retention and reducing image distortion. The launch of Leffa brings new possibilities for online shopping and virtual try-ons. Users only need to upload a reference image, and the system can generate an entirely new outfit effect based on that image.