OpenAI Ticktokで「sora」で生成された動画を公開中

ChatGPT

OpenAIがTikTokで動画生成AI「sora」の動画をアップロードしています。
「sora」はまだ一般公開されていませんが、TikTokにアップロードされた動画を見るだけでもその高いクオリティに驚愕します。

ビデオ生成AI「sora」について

TikTokのopenaiアカウント

個人的に気になったTikTokの動画から一部抜粋して紹介します。

プロンプト:「芋虫の変態が蝶へと変わるタイムラプスのストップモーション」

@openai

Well, that’s one way to do it. This video was generated by our text-to-video model, Sora, without modification. Prompt: “A stop motion Timelapse of a caterpillar’s metamorphisis into a butterfly” What would you like to see us make with Sora next? *Sora is not yet available to the public. We’re sharing our research progress early to learn from feedback and give the public a sense of what AI capabilities are on the horizon. #madewithSora #Sora #openai

♬ The Transformation – Bliss Looper

プロンプト:夜の都市の通りを激しい雨の中を走るスーパーカー、車の後ろから撮影

@openai

Replying to @Rozh S. Prompt: A super car driving through city streets at night with heavy rain everywhere, shot from behind the car as it drives These videos were generated by our text-to-video model, Sora, without modification. What would you like to see us make with Sora next? *Sora is not yet available to the public. We’re sharing our research progress early to learn from feedback and give the public a sense of what AI capabilities are on the horizon. #madewithSora #Sora #openai

♬ I Think I Like When It Rains – WILLIS

プロンプト:「ニューヨーク市がアトランティスのように水没。魚、クジラ、ウミガメ、サメがニューヨークの通りを泳ぎます。」

@openai

This video was generated by our text-to-video model, Sora.  Prompt: “New York City submerged like Atlantis. Fish, whales, sea turtles and sharks swim through the streets of New York.” What would you like to see us make with Sora next? *Sora is not yet available to the public. We’re sharing our research progress early to learn from feedback and give the public a sense of what AI capabilities are on the horizon. #madewithSora #Sora #openai

♬ Epic Inspiration – DM Production

プロンプト:「“SORA”と綴られたリアルな雲の画像」

@openai

Replying to @User01362648285 Yes! Our researchers chose the name because it “evokes the idea of limitless creative potential.” Prompt: “an image of a realistic cloud that spells “SORA”” #sora #madewithsora #openai

♬ Clouds (Sped up) – Tollan Kim

また「Sora」は、2つの入力ビデオの間を徐々に補間することもできるとして、その例も公開されています。

@openai

Wait for it. Our new model Sora can be prompted with text, images, or video inputs, but we can also use Sora to gradually interpolate between two input videos, creating seamless transitions between videos with entirely different subjects and scene compositions. In this example, the video in the center interpolates between the corresponding videos on the top and bottom. 
These three videos were generated by Sora without modification. *Sora is not yet available to the public. We’re sharing our research progress early to learn from feedback and give the public a sense of what AI capabilities are on the horizon. #madewithSora #Sora #openai

♬ Flute fantastic trap hip hop♬(1321576) – Ninja Muzik Tokyo
@openai

Wait for it. Our new model Sora can be prompted with text, images, or video inputs, but we can also use Sora to gradually interpolate between two input videos, creating seamless transitions between videos with entirely different subjects and scene compositions. In this example, the video in the center interpolates between the corresponding videos on the top and bottom. 
These three videos were generated by Sora without modification. *Sora is not yet available to the public. We’re sharing our research progress early to learn from feedback and give the public a sense of what AI capabilities are on the horizon. #madewithSora #Sora #openai

♬ Hip Hop Background(814204) – Pavel

動画自体は毎日アップロードされており、気になった方はぜひ確認してみてください。
一般公開されるのが楽しみですね。

AI・DX・LowCodeなど企業に役立つ情報を発信しています。

タイトルとURLをコピーしました