即時財經新聞
OpenAI測試新AI模型Sora 利用文字生成影片
人工智能公司OpenAI公布新生成式AI模型「Sora」，可利用根據文字提示生成短影片，現時尚未開放公眾使用。
OpenAI在社交平台X發文指，Sora可以快速製作長達一分鐘的影片，內容可以呈現「具有多個角色、特定類型的動作、以及主題和背景的準確細節的複雜場景」。
OpenAI在X平台發布部分測試影片，以「時尚女性在東京雨後街頭慢步」為提示字的短片可見，地面上的水漬倒影細節逼真，燈光效果亦與實景接近。
Prompt: “A stylish woman walks down a Tokyo street filled with warm glowing neon and animated city signage. she wears a black leather jacket, a long red dress, and black boots, and carries a black purse. she wears sunglasses and red lipstick. she walks confidently and casually.… pic.twitter.com/cjIdgYFaWq
— OpenAI (@OpenAI) February 15, 2024
不過，OpenAI指出，Sora仍為未完成的產品，現時難以準確模擬複雜的物理或空間細節。
Prompt: “A stylish woman walks down a Tokyo street filled with warm glowing neon and animated city signage. she wears a black leather jacket, a long red dress, and black boots, and carries a black purse. she wears sunglasses and red lipstick. she walks confidently and casually.… pic.twitter.com/cjIdgYFaWq
— OpenAI (@OpenAI) February 15, 2024