日本語(JA) 写真1枚から“裏側まで”3D化するAI「Idol」無償公開、VRAM10GBでも動く https:// pc.watch.impress.co.jp/docs/ne ws/2153055.html # impress # 市場 # AI # その他

AI Idol 可从单张照片生成3D模型，需要10GB显存

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-03 06:42

一款名为“AI Idol”的新AI模型已发布，能够从单张照片生成3D模型。该模型可以仅凭一张图像创建详细的3D表示，包括“背面”或未见部分。值得注意的是，“AI Idol”仅需10GB显存即可运行，使得硬件配置较低的用户也能使用。 AI

影响能够从单张图像创建3D模型，可能降低3D内容生成的门槛。

排序理由发布一款具有特定技术能力的新AI模型。 [lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 5 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 发布一款具有特定技术能力的新AI模型。 [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: model release, product; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。