Meta新AI影片生成器Movie Gen:技術突破與未來展望

Ai




我為嘲笑Meta的AI視頻努力感到後悔——Movie Gen看起來驚人地出色

由Joe Foley撰寫,發表於17小時前

Meta仍然可能成為AI視頻領域的一大玩家。

當你通過我們的網站購買時,我們可能會賺取聯盟佣金。以下是運作方式。

我可能在兩年前過於急於嘲笑Meta宣布其AI視頻生成器的消息,這款名為Make-A-Video的產品名字毫無創意。當時,這正值CEO馬克·扎克伯格對元宇宙的痴迷,看起來這又是這家擁有Facebook和Instagram的公司浪費大量資源研究與其核心業務無關的另一次愚蠢行為,所產生的視頻甚至連用作迷因都顯得怪異且故障頻繁。

那是在2022年10月。Make-A-Video從未公開發布,但Meta繼續在背後努力。現在,它剛剛展示了其最新的AI視頻生成器。儘管Movie Gen這個名字僅稍微好了一些,但其輸出效果看起來比前身先進了許多。它甚至可能比Runway和OpenAI的Sora更好。

介紹Meta Movie Gen

根據Meta的Movie Gen研究論文,該公司的新AI視頻模型可以根據文本提示創建出令人印象深刻的連貫視頻。不僅如此,文本提示還可以用來生成視頻中的音頻,將音樂和音效與影像匹配。該模型還可以編輯現有視頻,靜態圖像也可以用作參考。

Meta表示,Movie Gen可以在不同的長寬比下創建最多16秒的視頻和最多45秒的音頻。它聲稱該模型與Runway、OpenAI的Sora和Kling相比表現良好,提供的少量示例也證實了這一點。人和動物的解剖結構、服裝和其他物體通常看起來是令人信服的,儘管有時還是有些模糊或過於銳利且卡通化。光影效果尤其令人印象深刻。

何時公開發布?

雖然OpenAI最初表示Sora將在今年公開發布,但Meta似乎並不急於發布其模型。在Threads上,首席產品官Chris Cox寫道:「我們還未準備好將其作為產品發布——它仍然昂貴且生成時間過長——但我們想分享一下我們的進展,因為結果變得相當令人印象深刻。」

Sora和Runway一直被認為是迄今為止最強大的AI視頻生成器,後者的開發商最近還與電影和電視製作公司獅門影業達成了一項協議,將為其創建一個定制模型。如果獲得發布,Meta的AI視頻生成器也可能會與Adobe Firefly Video競爭,後者是Photoshop和Premiere Pro背後的公司承諾「即將推出」的產品。目前,Meta的模型看起來更強大,但Firefly Video可能會有一些實用的優勢,比如可以直接在Premiere Pro中使用。

尚不清楚這兩款模型是如何訓練的。有聲稱Runway是通過從YouTube上抓取視頻進行訓練的,而YouTube的CEO表示這將違反平台的使用條款。Meta表示,Movie Gen是通過「結合授權和公開可用的數據集」進行訓練的。它沒有具體說明是哪些數據集,但Meta可以通過其自身產品Instagram和Facebook直接訪問大量視頻數據。

編輯評論

Meta在AI技術方面的持續投入顯示出其對未來的堅定信心。從初期的Make-A-Video到如今的Movie Gen,這不僅是技術進步的體現,更反映出Meta對創新應用場景的深刻理解。儘管在元宇宙的投入上曾經遭受質疑,但Meta在AI視頻生成方面顯然已取得實質性突破。這種技術不僅能夠提升用戶體驗,還有可能在影視製作、廣告創意等領域帶來革命性變革。

然而,技術的進步也伴隨著倫理和法律問題。數據來源的透明度和合法性問題無疑是未來需要解決的關鍵。Meta在這方面的表態顯得模糊,這可能會引發外界對其數據使用方式的質疑。隨著AI技術的進一步發展,如何在創新和合規之間找到平衡,將是每個科技公司面臨的重要課題。

總的來說,Movie Gen的出現展示了AI技術在視頻生成領域的巨大潛力。無論是從技術角度還是應用前景來看,這都是一個令人興奮的進展。未來,我們期待看到更多這類技術的公開發布和實際應用,並希望相關公司能夠在技術創新和責任擔當方面取得更好的平衡。

以上文章由特價GPT API KEY所翻譯

發佈留言

發佈留言必須填寫的電子郵件地址不會公開。 必填欄位標示為 *

🎨 Nano Banana Pro 圖像生成器|打幾句說話就出圖

想畫人像、產品圖、插畫?SSFuture 圖像生成器支援 Flux Gemini Nano Banana Pro 改圖 / 合成, 打廣東話都得,仲可以沿用上一張圖繼續微調。

🆓 Flux 模型即玩,不用登入
🤖 登入後解鎖 Gemini 改圖
📷 支援上載參考圖再生成
⚡ 每天免費額度任你玩
✨ 即刻玩 AI 畫圖
Base Setup
keep 100 percent facial information adherence of the attached image and turn her into a lone night hiker standing in the shallow river at the mouth of the canyon, captured as a live action photograph or movie still, not an illustration or CGI render, with an alluring, confident, quietly sexy mood.

Shot and Camera
Three quarter body shot from slightly low height on the riverbank, placing her on the left third while the water leads into the dark canyon and the star filled sky dominates the top of the frame, preserving the original wide vertical composition.

Identity and Pose
She has a slim athletic build, natural proportions, medium length loose hair, and lightly tanned skin, 8k Photorealistic and hyper realistic. She stands barefoot in the water with one leg forward, hips relaxed, wearing a fitted cropped technical top and separate high waisted trail shorts with an open lightweight jacket slipping off one shoulder, one hand loosely holding a headlamp at her side and the other brushing hair from her face as she looks up at the stars.

Lighting and Environment
Keep the soft starlight and faint glow from the distant horizon, giving a gentle rim on her shoulders and hair while a subtle fill from the reflected sky reveals her features. The canyon walls, river reflections, pebbled shore, and dense star field stay exactly like the reference, with small ripples around her feet grounding her in the water.

Masking and Constraints
Change only by adding the subject and her outfit, keep lighting, perspective, white balance, canyon geometry, and river reflections the same, with realistic scale, body proportions, and clear contact between feet and water surface. Change only the requested element and keep lighting, perspective, white balance, pose, face geometry, body proportions, and silhouette the same, and absolutely avoid added text, painterly or toon styling, CGI look, blown highlights, banding, plastic skin, overly tidy backgrounds, or floating feet while requiring consistent perspective, consistent white balance, subtle film like grain, and physically correct contact shadows and reflections. 攝影主題:暖陽下的清新隨興肖像
人物與神態: 一位擁有烏黑長髮的年輕女性,左手輕扶髮絲,髮絲隨風輕拂臉龐。她展現燦爛自信的笑容,露出潔白牙齒,眼神明亮,散發青春活力的感染力,動作俏皮可愛。
服裝細節: 
上衣: 米白色寬鬆針織毛衣,材質柔軟。右肩自然滑落(露肩設計),展現優美的鎖骨線條;短版剪裁露出平坦腹部與肚臍。
下裝: 復古洗色藍色牛仔褲,細節可見鈕扣與部分拉鍊。
配飾: 左肩背著米色帆布環保袋,袋面上印有「Made in Kowloon」等深色文藝感字樣。
場景與構圖: 戶外環境(如公園或林蔭道),背景呈現柔焦效果,可見模糊的綠意樹葉與遠處人影。主體居中,背景的虛化使人物極致突出。
光線與氛圍: 採用自然光攝影,陽光從右上方灑落,於頭髮、肩膀與衣物纖維上形成鮮明的光影對比。整體呈現溫暖的米、藍、綠色調,畫質達 4K 寫實等級,光影層次豐富,營造出輕鬆愉悅的高級攝影感 Certainly! Here’s an enhanced, detailed, and artistic version of your prompt:

A charming and elegant cat sitting gracefully on a Parisian balcony, overlooking the romantic cityscape of Paris at sunset. The cat’s fur is soft and glossy, perhaps a classic tabby or a sleek black cat, with expressive, intelligent eyes. Delicate wrought-iron railings surround the balcony, adorned with blooming flower boxes of vibrant geraniums and lavender. In the distance, the Eiffel Tower rises majestically above the rooftops, bathed in warm golden and pink light. The artist’s style is a blend of impressionism and realism, capturing intricate city details—cobblestone streets, classic Parisian architecture, and atmospheric lighting. The mood is dreamy, whimsical, and full of European charm, evoking a sense of wonder and adventure.