The Eye of Horus part1: Image Generation and Watermark Detection with Vertex AI Imagen 3 and SynthID
Google Cloud credits are provided for this project. #VertexAISprint
Google Cloud credits are provided for this project. #VertexAISprint
Author: Jimmy Liao
Co-author: Kevin Chiu
What is this
This experiment demonstrates the application of SynthID's robust watermarking capabilities within the context of AI-generated imagery. It evaluates how effectively SynthID can embed and detect imperceptible watermarks in images produced by Imagen 3, showcasing a method for establishing provenance and authenticity in AI-generated content.
(中文版)
引言:
新聞: 數位部致力推動可信任AI 辦理審議式民主活動邀國際AI廠商交流，針對「運用AI促進資訊完整性審議式民主活動」，對於生成式AI內容進行分析及辨別方面，國際廠商皆在會中提出已建立或即將導入的相關作法，包括SynthID技術（用於AI生成圖片中建立浮水印，或偵測AI生成圖片中的浮水印，以方便辨識AI生成的圖片）等AI生成內容偵測技術、溯源標註及簽章、用戶檢舉機制，以及提醒用戶注意AI生成內容等作法。
而此文章展示了 SynthID 浮水印技術 在 AI 生成圖像 中的應用。評估 SynthID 在 Imagen 3 生成的圖像中嵌入與檢測不可見浮水印的效果，並提供了一種 驗證 AI 生成內容來源與真實性 的方法。
[圖片來源: 數發布新聞稿)
Why you should read this
Understanding AI-Generated Content Authenticity: As AI-generated images become increasingly realistic, it's crucial to have mechanisms for verifying their origin. This experiment provides insights into how SynthID addresses this challenge.
Practical Application of SynthID: This provides a real world example of how to use SynthID with Imagen.
Exploring Imagen 3 Capabilities: Readers can observe the quality of images generated by Imagen 3 and its integration with watermarking technologies.
Combating Misinformation:** Watermarking is a key tool in the fight against deepfakes and the spread of manipulated media.
(中文版)
理解 AI 生成內容的真實性：
隨著 AI 生成的圖像越來越逼真，建立可驗證其來源的機制變得至關重要。本實驗提供了 SynthID 如何應對這一挑戰 的見解。探索 Imagen 3 的能力與 SynthID 的實際應用：
讀者可以觀察 Imagen 3 生成的圖像品質，以及它如何與 浮水印技術整合。打擊錯誤資訊：
浮水印技術是對抗深偽技術（deepfake）和防止媒體被操控的重要工具。
Background:
Imagen 3 (Vertex AI): Google Cloud's Imagen is a powerful text-to-image diffusion model.
SynthID: A technology developed by Google DeepMind that embeds digital watermarks directly into the pixels of an image during its creation.
Imagen 3: The newest iteration of Imagen, offering improved image quality and adherence to prompts.
(中文版)
Imagen 3 (Vertex AI)：
Google Cloud 的 Imagen 是一款強大的 文字轉圖像（text-to-image）擴散模型。SynthID：
由 Google DeepMind 開發 的技術，能在圖像生成時 直接將數位浮水印嵌入圖像像素中。Imagen 3：
Imagen 的最新版本，提供 更高的圖像品質，並能更準確地遵循輸入提示（prompts）。
Experiment:
1. Image Generation with Imagen 3:
Use Imagen 3 to generate images of the "Eye of Horus" based on specific prompts.
Load the image generation models:
imagen-3.0-generate-002
generation_model = "imagen-3.0-generate-002"Conduct two sets of generation:
One set with the SynthID watermark enabled.
Another set without the SynthID watermark.
2. Watermark Verification with WatermarkVerificationModel:
Take the generated images from both sets.
Use the WatermarkVerificationModel to analyze each image and determine if a SynthID watermark is present.
image1 = "./generated_image_watermark.png"
check_watermark(image1)Watermark verification result: ACCEPT
image2 = "./generated_image.png"
check_watermark(image2)Watermark verification result: REJECT
Source code under this repository: https://github.com/jimmyliao/HorusEye
Please give us a star ⭐️