通义万相Wan2.5

Search documents
夸克发布AI创作平台“造点”,首次支持音画视频同步生成
Guan Cha Zhe Wang· 2025-09-24 09:46
具体来看,对通义万相Wan2.5的集成是平台的一大亮点。依托于最新模型能力,"造点"能生成和画面匹配的人声、音效和背景音乐,支持10S时长,单次生 成即可实现更完整的剧情故事。同时支持24帧/秒的1080P高清视频,画面质量能够满足电影级场景的创作需求。 目前,用户可直接访问zaodian.quark.cn,或通过夸克PC端"AI生图"进入"造点"。在夸克APP端,"造点"可提供轻量化的创作体验,实现"一句话P图""AI创意 视频"等玩法,也能满足日常修图需求,如滤镜、美颜、去路人等;同时支持换发型、换背景、风格转换、3D手办生成等热门AI场景。 9月24日,阿里巴巴AI旗舰应用夸克正式发布全新AI创作平台"造点"。平台集成AI生图与AI生视频两大核心能力,率先接入通义万相Wan2.5,成为国内首个 支持音画同步视频生成的平台。 在AI生图方面,"造点"全面支持 Midjourney V7的多项核心能力,包括多图参考、风格代码、精细化参数控制等,可满足专业创作者在构图、风格表达与细 节打磨上的高阶需求。 结合夸克自研能力,"造点"在亚洲人像生成、中文文字生成、国风元素等方面尤为突出,适用于电商、平面设计及影视 ...
阿里夸克发布全新AI创作平台“造点” 已接入通义万相Wan2.5
Zheng Quan Ri Bao Zhi Sheng· 2025-09-24 06:34
Core Insights - Alibaba's AI flagship application Quark has launched a new AI creation platform called "ZaoDian," integrating AI-generated images and videos, and is the first in China to support synchronized audio-visual video generation with the latest model, Tongyi Wanshang Wan2.5 [1][3] Group 1: Platform Features - "ZaoDian" incorporates advanced capabilities from the Midjourney V7 image generation model, providing a one-stop creative experience for users with both image and video functionalities [1][3] - The platform can generate synchronized voice, sound effects, and background music for videos, supporting a duration of 10 seconds and achieving 1080P HD quality at 24 frames per second, suitable for cinematic scene creation [3] - The model demonstrates strong instruction-following capabilities, allowing for complex continuous changes in video generation, such as camera movements [3] Group 2: Target Audience and Use Cases - "ZaoDian" supports various professional creator needs, including multi-image references, style codes, and detailed parameter control, making it suitable for e-commerce, graphic design, and film/game applications [3] - During the beta testing phase, "ZaoDian" attracted numerous professional AIGC creators, resulting in popular works like "Medieval Oil Painting Chorus" and "Cultural Relics Eating Mooncakes" [3] - The platform offers a lightweight creative experience for general users, allowing for fun features like "one-sentence photo editing" and "AI creative videos," as well as everyday photo editing needs [4]
阿里夸克发布AI创作平台"造点",通义万相Wan2.5生成视频7天免费
Ge Long Hui· 2025-09-24 03:58
9月24日,阿里巴巴AI旗舰应用夸克正式发布全新AI创作平台"造点"。平台集成AI生图与AI生视频两大核心能力,率先接入通义万相 Wan2.5,成为国内首个支持音画同步视频生成的平台。在生图方面,"造点"引入了全球领先的图像生成模型 Midjourney V7。结合夸 克自研技术,"造点"为用户提供了图像与视频兼备的一站式创作体验。 对通义万相Wan2.5的集成是平台的一大亮点。依托于最新模型能力,"造点"能生成和画面匹配的人声、音效和背景音乐,支持10S时 长,单次生成即可实现更完整的剧情故事;支持24帧/秒的1080P高清视频,画面质量能够满足电影级场景的创作需求。模型具备极强 的指令遵循能力,可在视频生成中完成运镜等复杂连续变化的控制。 在AI生图方面,"造点"全面支持 Midjourney V7的多项核心能力,包括多图参考、风格代码、精细化参数控制等,可满足专业创作者 在构图、风格表达与细节打磨上的高阶需求。结合夸克自研能力,"造点"在亚洲人像生成、中文文字生成、国风元素等方面尤为突 出,适用于电商、平面设计及影视游戏等应用场景。 内测期间,"造点"吸引了大量专业AIGC创作者,诞生了如"中世纪油画大 ...
阿里夸克发布全新AI创作平台“造点”,已接入通义万相Wan2.5
Ge Long Hui· 2025-09-24 03:46
对通义万相Wan2.5的集成是平台的一大亮点。依托于最新模型能力,"造点"能生成和画面匹配的人声、 音效和背景音乐,支持10S时长,单次生成即可实现更完整的剧情故事;支持24帧/秒的1080P高清视 频,画面质量能够满足电影级场景的创作需求。模型具备极强的指令遵循能力,可在视频生成中完成运 镜等复杂连续变化的控制。 在AI生图方面,"造点"全面支持 Midjourney V7的多项核心能力,包括多图参考、风格代码、精细化参 数控制等,可满足专业创作者在构图、风格表达与细节打磨上的高阶需求。结合夸克自研能力,"造 点"在亚洲人像生成、中文文字生成、国风元素等方面尤为突出,适用于电商、平面设计及影视游戏等 应用场景。 9月24日,阿里巴巴AI旗舰应用夸克正式发布全新AI创作平台"造点"。平台集成AI生图与AI生视频两大 核心能力,率先接入通义万相Wan2.5,成为国内首个支持音画同步视频生成的平台。在生图方面,"造 点"引入了全球领先的图像生成模型 Midjourney V7。结合夸克自研技术,"造点"为用户提供了图像与视 频兼备的一站式创作体验。 目前,用户可直接访问 zaodian.quark.cn,或通过夸 ...
阿里夸克发布AI创作平台“造点”,支持音画同步视频生成
Xin Lang Cai Jing· 2025-09-24 03:41
9月24日,阿里巴巴AI旗舰应用夸克正式发布全新AI创作平台"造点"。平台集成AI生图与AI生视频两大 核心能力,率先接入通义万相Wan2.5,成为国内首个支持音画同步视频生成的平台。在生图方面,"造 点"还引入了图像生成模型Midjourney V7。 ...
Wan2.5+Midjourney V7,阿里夸克这个新AI鲨疯了!价格还砍一大刀
量子位· 2025-09-24 03:32
Core Viewpoint - Quark has officially launched its "ZaoDian" AI platform, integrating the latest Midjourney V7 model and Alibaba's video generation model Wan2.5, while halving membership prices for users [1][48]. Group 1: Product Features - "ZaoDian" AI focuses on two core functionalities: AI image generation and AI video generation, allowing users to create images and videos seamlessly [8][12]. - The platform supports audio-visual synchronization during video generation, automatically matching voice, sound effects, and background music [8][21]. - Users can switch between two models: Midjourney V7 for aesthetic image generation and Wan2.5 for video creation, catering to different needs [11][12]. Group 2: User Experience - The interface allows for easy access to features like intelligent retouching and a feature word library with over 120 prompts for various artistic styles [14][46]. - The mobile version of "ZaoDian" enables users to edit images using voice commands, enhancing user interaction and creativity [36][38]. - The platform offers a 7-day free trial for video generation, making it accessible for users to explore its capabilities [51]. Group 3: Competitive Pricing - Membership for Midjourney V7 is priced at 48 yuan per month, allowing the generation of 400 images, significantly lower than the overseas version priced at 10 USD for 200 images [49]. - The pricing strategy aims to attract a larger user base by reducing creative costs while providing high-quality AI tools [48][49].