蘋果，AI和圖像生成：新的流狀態？

蘋果對使用標準化流量的AI圖像生成的創新方法可以重塑設備AI的未來。

The world of AI image generation is heating up, and Apple is throwing its hat into the ring with a fresh take on an old technique. While diffusion models and autoregressive models dominate the scene, Apple's recent research suggests that Normalizing Flows, with a Transformer twist, might be the dark horse we didn't see coming. Could this be the key to powerful, on-device AI image generation?

AI圖像的世界正在加熱，Apple用新的舊技術將其帽子扔進了戒指。儘管擴散模型和自迴旋模型占據了現場的主導，但蘋果的最新研究表明，通過變壓器扭曲的流動可能是我們沒有看到的黑馬。這可能是強大的，設備AI圖像生成的關鍵嗎？

Normalizing Flows: A Blast from the Past?

歸一化流：過去的爆炸？

Normalizing Flows (NFs) aren't exactly new, but Apple's revisiting them with a modern spin. Think of NFs as AI that learns to transform images into structured noise, and then reverses the process to create new images. The cool part? They can calculate the exact likelihood of each image, something diffusion models struggle with. This is super useful where understanding probability matters.

標準化流量（NFS）並不是什麼新鮮事物，但是蘋果正在用現代旋轉來重新審視它們。將NFS視為AI，學會將圖像轉換為結構化噪聲，然後逆轉創建新圖像的過程。很酷的部分？他們可以計算每個圖像的確切可能性，擴散模型與之困擾。在理解概率很重要的情況下，這非常有用。

So, why aren't NFs all the rage? Early versions produced blurry, underwhelming images. But Apple believes they've cracked the code.

那麼，為什麼NFS並不是所有的憤怒呢？早期版本產生了模糊，不足的圖像。但是蘋果認為他們已經破解了代碼。

TarFlow: Transformers to the Rescue

TARFLOW：救援的變壓器

Apple's first study introduces TarFlow (Transformer AutoRegressive Flow). The secret sauce? Swapping out old-school layers for Transformer blocks. TarFlow chops images into patches and generates them block by block, predicting each one based on what came before. Sound familiar? It's similar to how OpenAI generates images, but with a crucial difference.

蘋果的第一項研究引入了TARFLOW（變壓器自動回歸流）。秘密調味料？將老式層交換為變壓器塊。 TARFLOW將圖像置於補丁中，並通過塊生成它們，並根據以前的內容預測每個圖像。聽起來很熟悉嗎？這類似於OpenAI生成圖像的方式，但差異至關重要。

Instead of generating discrete tokens (like words), TarFlow generates pixel values directly. This avoids the quality loss that comes with compressing images into a fixed vocabulary. It's a subtle but significant advantage.

Tarflow無需生成離散令牌（如單詞），而是直接生成像素值。這避免了將圖像壓縮成固定詞彙的質量損失。這是一個微妙但很大的優勢。

STARFlow: Scaling Up the Vision

Starflow：擴大視覺

But TarFlow had its limits, especially with high-res images. That's where STARFlow (Scalable Transformer AutoRegressive Flow) comes in. The big change? STARFlow works on a compressed version of the image, then uses a decoder to upscale it. This "latent space" approach lets STARFlow focus on the big picture, leaving the fine details to the decoder.

但是TARFLOW具有其限制，尤其是使用高分辨率圖像。那就是Starflow（可擴展的變壓器自迴旋流程）的出現。大變化？ Starflow在圖像的壓縮版本上工作，然後使用解碼器對其進行更大的幅度。這種“潛在空間”方法使Starflow專注於大局，將細節留給解碼器。

Apple also cleverly integrates existing language models (like Google's Gemma) for text prompts. This keeps the image generation focused on visual refinement.

蘋果還巧妙地將現有語言模型（例如Google的Gemma）集成為文本提示。這使圖像產生集中在視覺上。

Apple vs. OpenAI: A Different Approach

蘋果與Openai：另一種方法

While Apple's rethinking flows, OpenAI's GPT-4o is also moving beyond diffusion. But their approaches are worlds apart. GPT-4o treats images as sequences of tokens, giving it incredible flexibility. The same model can generate text, images, and audio.

蘋果重新思考流動時，OpenAI的GPT-4O也超越了擴散。但是他們的方法與眾不同。 GPT-4O將圖像視為令牌序列，從而使其具有令人難以置信的靈活性。相同的模型可以生成文本，圖像和音頻。

The downside? Token-by-token generation can be slow and computationally expensive. But since GPT-4o runs in the cloud, OpenAI isn't as worried about latency or power.

缺點？逐個代幣的生成可能很慢，計算上的昂貴。但是，由於GPT-4O在雲中運行，因此Openai不必擔心潛伏期或力量。

The key takeaway: OpenAI is building for data centers, while Apple is clearly building for our iPhones. The ability to run powerful AI image generation on-device, without relying on cloud connectivity, is a game-changer. It opens up possibilities for real-time creativity and enhanced privacy.

關鍵要點：OpenAI正在為數據中心建造，而Apple顯然正在為我們的iPhone建造。在不依賴雲連接的情況下運行強大的AI圖像生成功能的能力是改變遊戲規則的能力。它為實時創造力和增強隱私性開闢了可能性。

Why Normalizing Flows Matter

為什麼正常流量很重要

Normalizing flows offer the ability to calculate the exact likelihood of the generated image. This is a key advantage over other methods and makes flows appealing for tasks where understanding the probability of an outcome really matters.

歸一化流提供了計算生成圖像的確切可能性的能力。這是比其他方法的關鍵優勢，並且使流量吸引了理解結果的可能性確實很重要的任務。

The Future of AI Image Generation on Apple Devices

AI圖像在Apple設備上的未來

Apple's approach could lead to faster, more private, and energy-efficient AI image generation on its devices. Imagine creating stunning visuals on your iPhone without needing a constant internet connection or worrying about your data being sent to the cloud. That's the promise of Apple's Normalizing Flows.

蘋果的方法可能會導致其設備上更快，更私密和節能的AI圖像生成。想像一下，在iPhone上創建令人驚嘆的視覺效果，而無需持續的Internet連接或擔心將數據發送到雲。這就是蘋果正常化流動的承諾。

While Large Reasoning Models (LRMs) reasoning capabilities are debated, as highlighted by Apple's "Illusion of Thinking" paper and Anthropic's rebuttal, the focus on efficient, on-device AI suggests Apple is prioritizing practicality and user experience.

雖然辯論了大型推理模型（LRMS）推理能力，但蘋果的“思考”紙張和人類的反駁強調了，但專注於高效的，on device AI的重點表明，蘋果正在優先考慮實用性和用戶體驗和用戶體驗。

A Personal Take

個人看法

It's easy to get caught up in the hype around massive cloud-based AI models. But Apple's focus on bringing AI to our pockets is incredibly exciting. The potential for on-device AI to revolutionize creativity, productivity, and privacy is immense. I think Apple's bet on Normalizing Flows is a smart one, and I can't wait to see what they come up with next.

很容易圍繞大型基於雲的AI模型吞噬炒作。但是，蘋果專注於將AI帶到我們的口袋裡的關注非常令人興奮。在設備AI革新創造力，生產力和隱私的潛力是巨大的。我認為蘋果對歸一化流量的賭注是一個聰明的人，我迫不及待地想看看他們接下來想出的內容。

So, there you have it. Apple's taking a different path in the AI image generation race, and it's definitely one to watch. Who knows, maybe Normalizing Flows will be the next big thing. One thing's for sure: the future of AI is looking pretty flow-tastic!

所以，你有。蘋果在AI圖像生成競賽中採取了不同的道路，這絕對是值得關注的。誰知道，也許將流量標準化將是下一個大事。可以肯定的是：AI的未來看起來很流暢！