Search AI Products and News

3DV-TON (Textured 3D-Guided Consistent Video Try-on via Diffusion Models) is an innovative technology that delivers a realistic video try-on experience with texture 3D guidance using diffusion models. According to AIbase, 3DV-TON leverages advanced 3D geometry and texture modeling combined with video diffusion models to ensure consistency and realism of clothing in dynamic videos, offering significant potential for e-commerce, fashion, and virtual reality applications.

Tencent has recently unveiled GeometryCrafter, a new AI model released via Hugging Face. This model excels at consistent geometric estimation in open-world videos, quickly gaining attention in the tech community. Leveraging diffusion priors, GeometryCrafter opens up new possibilities for deep understanding and processing of video content, offering benefits to creators and researchers alike.

On February 19, Beijing Zhipu Huazhang Technology Co., Ltd. announced that its multimodal creation platform 'Qingying' has formed a strategic partnership with the AI character creation platform 'NianTa'. Together, they will explore a complete path from AI character design to animation creation, and promote the technological realization of IP consistency. This collaboration aims to deeply explore the needs of secondary dimension users and AI application scenarios, providing users with higher quality generation effects and faster inference speeds.

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.

H2O.ai recently announced the launch of its new multi-agent platform h2oGPTe, which combines generative and predictive AI models to provide businesses with more consistent responses. Sri Ambati, founder and CEO of H2O.ai, stated that a major demand from enterprises for AI agents is to maintain response consistency. The h2oGPTe platform utilizes H2O.ai's proprietary models Mississippi and Danube, while also allowing access to other models.

On the occasion of Vidu's launch anniversary, Shengshu Technology is proud to announce the release of the new version Vidu 1.5, which achieves world-leading breakthroughs, especially in understanding diverse inputs and overcoming the 'consistency' challenge. The launch of Vidu 1.5 marks a new 'contextual' era for visual models, accelerating the arrival of Artificial General Intelligence (AGI). From its global debut, Vidu has demonstrated the ability to generate character consistency.

Recently, Kling introduced a brand new "Custom Models" feature, a significant update that will thoroughly address the technical challenges of character consistency in AI video generation. Based on feedback from early testing users on the platform, this feature allows creators to upload 10 to 30 different video clips for model training, with each clip requiring at least 10 seconds. Unlike traditional models that rely solely on image training, KLING innovatively utilizes video materials as the training basis and even supports using AI-generated videos created by Kling for training.

Recently, the Meta AI team introduced LongVU, a novel spatio-temporal adaptive compression mechanism aimed at enhancing the language understanding capabilities of long videos. Traditional multimodal large language models (MLLMs) face limitations in context length when processing long videos, and LongVU was created to address this challenge. LongVU operates primarily by filtering duplicate frames and employing inter-frame token compression techniques to efficiently utilize context length, allowing it to reduce video data while preserving visual details.

At the 2024 Volcano Engine AI Innovation Roadshow, Volcano Engine President Tan Dai unveiled the latest Doubao · Video Generation Model. This model incorporates several advanced technologies, including the efficient DIT Fusion Computing Unit, which enables deep compression encoding of video and text; it also employs a novel diffusion model training approach to ensure consistency in generating multi-camera videos; in addition, the model integrates a deeply optimized Transformer architecture, significantly enhancing the generalization ability of video generation.

China's first fully self-developed video model, Vidu, created by Shengshu Technology and Tsinghua University, introduces the 'Subject Reference' feature to ensure character consistency in AI-generated videos. Users can upload images, and Vidu maintains consistency across various scenes. This free feature marks a new era in AI video creation, aiming for precise multi-subject interaction and style uniformity. Director Shi Yuxiang praised its enhanc....

In July this year, Aishi Technology released the newly upgraded AI video generation product PixVerse V2, which is based on the Diffusion+Transformer (DiT) architecture, achieving multiple innovations in video generation technology. PixVerse V2 offers longer, more consistent, and more engaging video generation capabilities, supporting the generation of multiple video clips at once.