The model supports multimodal inputs including text, images and video, and generates high-fidelity 1080p videos of 5 to 20 seconds with natively synchronized audio BEIJING, CHINA - Media OutReach ...
HiDream-O1-Embodied tops RoboColiseum’s Robustness leaderboard, highlighting the model’s ability to maintain stable performance under complex real-world conditions BEIJING, CHINA - Media OutReach ...
The round brings HiDream.ai’s total financing over the past three months to more than RMB 2.1 billion and marks its entry into unicorn status BEIJING, CHINA – Media OutReach Newswire – 27 July 2026 – ...
(MENAFN- Media OutReach Newswire) -share-copy-box" class="mo-ui-news-article-share-copy-box" hidden>The model supports multimodal inputs including text, images and ...
9月15日,智象未来(HiDream.ai)正式发布首个原生全模态视频生成模型 HiDream-O1-Video-1.0。该模型采用智象自研原生全模态架构,支持文本、图片、视频等多种模态输入,可一键直出 5-20 秒 1080p ...
AI的“神仙打架”从未停歇,尤其在文生图这个烧钱又内卷的赛道。 但当所有人的目光都聚集在OpenAI、Google、Midjourney等“头号玩家”时,一个相对低调的中国团队,却悄然登上了多个AI模型能力 ...
36氪获悉,HiDream.ai近期已完成新一轮融资,由科大讯飞创投基金领投,将门创投等多家机构跟投。其中,上一轮投资的阿尔法公社、中喝大种子一号基金也都再次跟投。 从创立到现在,HiDream.ai ...
近日,智象未来(HiDream.ai) 全新推出的商用版图像生成模型 HiDream-O1-Image-1.5 再次实现 SOTA,在全球知名独立 AI 模型评测与分析平台 Artificial Analysis的文生图榜单(Text to Image Leaderboard)上,一举 ...
雷峰网讯 “8B 开源版是一扇窗,真正的风景还在 200B+ 参数的 Pro 版本之后。” 智象未来 HiDream-O1-Image 开源版(8B)发布之后,我在测评最后留下了这样一句判断。前者以 Peanut 匿名登上 AA 榜 ...
雷峰网讯 2026 年 5 月,智象未来开源了文生图模型 HiDream-O1-Image(8B),直接登顶 Artificial Analysis 开源模型全球第一,Elo 1187 的分数力压 Qwen Image(27B)和 FLUX.2 dev。值得注意的是,这也是 Artificial ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results