Sunday, May 26, 2024

Amazon Titan Picture Generator and watermark detection API are actually obtainable in Amazon Bedrock


Voiced by Polly

Throughout AWS re:Invent 2023, we introduced the preview of Amazon Titan Picture Generator, a generative synthetic intelligence (generative AI) basis mannequin (FM) that you should use to shortly create and refine sensible, studio-quality pictures utilizing English pure language prompts.

I’m pleased to share that Amazon Titan Picture Generator is now typically obtainable in Amazon Bedrock, supplying you with a simple method to construct and scale generative AI functions with new picture era and picture modifying capabilities, together with immediate customization of pictures.

In my earlier publish, I additionally talked about that every one pictures generated by Titan Picture Generator include an invisible watermark, by default, which is designed to assist scale back the unfold of misinformation by offering a mechanism to determine AI-generated pictures.

I’m excited to announce that watermark detection for Titan Picture Generator is now typically obtainable within the Amazon Bedrock console. At this time, we’re additionally introducing a brand new DetectGeneratedContent API (preview) in Amazon Bedrock that checks for the existence of this watermark and helps you affirm whether or not a picture was generated by Titan Picture Generator.

Let me present you tips on how to get began with these new capabilities.

On the spot picture customization utilizing Amazon Titan Picture Generator
Now you can generate new pictures of a topic by offering as much as 5 reference pictures. You possibly can create the topic in numerous scenes whereas preserving its key options, switch the fashion from the reference pictures to new pictures, or combine kinds from a number of reference pictures. All this may be finished with out extra immediate engineering or fine-tuning of the mannequin.

For this demo, I immediate Titan Picture Generator to create a picture of a “parrot consuming a banana.” Within the first try, I exploit Titan Picture Generator to create this new picture with out offering a reference picture.

Be aware: Within the following code examples, I’ll use the AWS SDK for Python (Boto3) to work together with Amazon Bedrock. You will discover extra code examples for C#/.NET, Go, Java, and PHP within the Bedrock Consumer Information.

import boto3
import json

bedrock_runtime = boto3.consumer(service_name="bedrock-runtime")

physique = json.dumps(
    {
        "taskType": "TEXT_IMAGE",
        "textToImageParams": {
            "textual content": "parrot consuming a banana",   
        },
        "imageGenerationConfig": {
            "numberOfImages": 1,   
            "high quality": "premium", 
            "top": 768,
            "width": 1280,
            "cfgScale": 10, 
            "seed": 42
        }
    }
)
response = bedrock_runtime.invoke_model(
    physique=physique, 
    modelId="amazon.titan-image-generator-v1",
    settle for="software/json", 
    contentType="software/json"
)

You possibly can show the generated picture utilizing the next code.

import io
import base64
from PIL import Picture

response_body = json.masses(response.get("physique").learn())

pictures = [
    Image.open(io.BytesIO(base64.b64decode(base64_image)))
    for base64_image in response_body.get("images")
]

for img in pictures:
    show(img)

Right here’s the generated picture:

Image of a parrot eating a banana generated by Amazon Titan Image Generator

Then, I exploit the brand new immediate picture customization functionality with the identical immediate, however now additionally offering the next two reference pictures. For simpler comparability, I’ve resized the pictures, added a caption, and plotted them aspect by aspect.

Reference images for Amazon Titan Image Generator

Right here’s the code. The brand new immediate customization is out there by way of the IMAGE_VARIATION job:

# Import reference pictures
image_path_1 = "parrot-cartoon.png"
image_path_2 = "bird-sketch.png"

with open(image_path_1, "rb") as image_file:
    input_image_1 = base64.b64encode(image_file.learn()).decode("utf8")

with open(image_path_2, "rb") as image_file:
    input_image_2 = base64.b64encode(image_file.learn()).decode("utf8")

# ImageVariationParams choices:
#   textual content: Immediate to information the mannequin on tips on how to generate variations
#   pictures: Base64 string illustration of a reference picture, as much as 5 pictures are supported
#   similarityStrength: Parameter you'll be able to tune to regulate similarity with reference picture(s)

physique = json.dumps(
    {
        "taskType": "IMAGE_VARIATION",
        "imageVariationParams": {
            "textual content": "parrot consuming a banana",  # Required
            "pictures": [input_image_1, input_image_2],  # Required 1 to five pictures
            "similarityStrength": 0.7,  # Vary: 0.2 to 1.0
        },
        "imageGenerationConfig": {
            "numberOfImages": 1,
            "high quality": "premium",
            "top": 768,
            "width": 1280,
            "cfgScale": 10,
            "seed": 42
        }
    }
)

response = bedrock_runtime.invoke_model(
    physique=physique, 
    modelId="amazon.titan-image-generator-v1",
    settle for="software/json", 
    contentType="software/json"
)

As soon as once more, I’ve resized the generated picture, added a caption, and plotted it aspect by aspect with the initially generated picture. Amazon Titan Image Generator instance customization results

You possibly can see how the parrot within the second picture that has been generated utilizing the moment picture customization functionality resembles in fashion the mixture of the offered reference pictures.

Watermark detection for Amazon Titan Picture Generator
All Amazon Titan FMs are constructed with accountable AI in thoughts. They detect and take away dangerous content material from knowledge, reject inappropriate consumer inputs, and filter mannequin outputs. As content material creators create realistic-looking pictures with AI, it’s necessary to advertise accountable improvement of this know-how and scale back the unfold of misinformation. That’s why all pictures generated by Titan Picture Generator include an invisible watermark, by default. Watermark detection is an progressive know-how, and Amazon Net Companies (AWS) is among the many first main cloud suppliers to broadly launch built-in watermarks for AI picture outputs.

Titan Picture Generator’s new watermark detection characteristic is a mechanism that lets you determine pictures generated by Amazon Titan. These watermarks are designed to be tamper-resistant, serving to enhance transparency round AI-generated content material as these capabilities proceed to advance.

Watermark detection utilizing the console
Watermark detection is mostly obtainable within the Amazon Bedrock console. You possibly can add a picture to detect watermarks embedded in pictures created by Titan Picture Generator, together with these generated by the bottom mannequin and any personalized variations. In the event you add a picture that was not created by Titan Picture Generator, then the mannequin will point out {that a} watermark has not been detected.

The watermark detection characteristic additionally comes with a confidence rating. The boldness rating represents the boldness degree in watermark detection. In some circumstances, the detection confidence could also be low if the unique picture has been modified. This new functionality allows content material creators, information organizations, danger analysts, fraud detection groups, and others to higher determine and mitigate deceptive AI-generated content material, selling transparency and accountable AI deployment throughout organizations.

Watermark detection utilizing the API (preview)
Along with watermark detection utilizing the console, we’re introducing a brand new DetectGeneratedContent API (preview) in Amazon Bedrock that checks for the existence of this watermark and helps you affirm whether or not a picture was generated by Titan Picture Generator. Let’s see how this works.

For this demo, let’s verify if the picture of the inexperienced iguana I confirmed within the Titan Picture Generator preview publish was certainly generated by the mannequin.

Green iguana generated by Amazon Titan Image Generator

I outline the imports, arrange the Amazon Bedrock boto3 runtime consumer, and base64-encode the picture. Then, I name the DetectGeneratedContent API by specifying the muse mannequin and offering the encoded picture.

import boto3
import json
import base64

bedrock_runtime = boto3.consumer(service_name="bedrock-runtime")

image_path = "green-iguana.png"

with open(image_path, "rb") as image_file:
    input_image_iguana = image_file.learn()

response = bedrock_runtime.detect_generated_content(
    foundationModelId = "amazon.titan-image-generator-v1",
    content material = {
        "imageContent": { "bytes": input_image_iguana }
    }
)

Let’s verify the response.

response.get("detectionResult")
'GENERATED'
response.get("confidenceLevel")
'HIGH'

The response GENERATED with the boldness degree HIGH confirms that Amazon Bedrock detected a watermark generated by Titan Picture Generator.

Now, let’s verify one other picture I generated utilizing Secure Diffusion XL 1.0 on Amazon Bedrock. On this case, a “meerkat dealing with the sundown.”

Meerkat facing the sunset

I name the API once more, this time with the picture of the meerkat.

image_path = "meerkat.png"

with open(image_path, "rb") as image_file:
    input_image_meerkat = image_file.learn()

response = bedrock_runtime.detect_generated_content(
    foundationModelId = "amazon.titan-image-generator-v1",
    content material = {
        "imageContent": { "bytes": input_image_meerkat }
    }
)

response.get("detectionResult")
'NOT_GENERATED'

And certainly, the response NOT_GENERATED tells me that there was no watermark by Titan Picture Generator detected, and subsequently, the picture more than likely wasn’t generated by the mannequin.

Utilizing Amazon Titan Picture Generator and watermark detection within the console
Right here’s a brief demo of tips on how to get began with Titan Picture Generator and the brand new watermark detection characteristic within the Amazon Bedrock console, put collectively by my colleague Nirbhay Agarwal.

Availability
Amazon Titan Picture Generator, the brand new immediate customization capabilities, and watermark detection within the Amazon Bedrock console can be found immediately within the AWS Areas US East (N. Virginia) and US West (Oregon). Examine the full Area record for future updates. The brand new DetectGeneratedContent API in Amazon Bedrock is out there immediately in public preview within the AWS Areas US East (N. Virginia) and US West (Oregon).

Amazon Titan Picture Generator, now additionally obtainable in PartyRock
Titan Picture Generator is now additionally obtainable in PartyRock, an Amazon Bedrock playground. PartyRock provides you a no-code, AI-powered app-building expertise that doesn’t require a bank card. You should utilize PartyRock to create apps that generate pictures in seconds by choosing out of your selection of picture era fashions from Stability AI and Amazon.

Extra assets
To be taught extra concerning the Amazon Titan household of fashions, go to the Amazon Titan product web page. For pricing particulars, verify Amazon Bedrock Pricing.

Give Amazon Titan Picture Generator a attempt in PartyRock or discover the mannequin’s superior picture era and modifying capabilities within the Amazon Bedrock console. Ship suggestions to AWS re:Put up for Amazon Bedrock or by way of your common AWS contacts.

For extra deep-dive technical content material and to interact with the generative AI Builder group, go to our generative AI area at group.aws.

— Antje

Related Articles

LEAVE A REPLY

Please enter your comment!
Please enter your name here

Stay Connected

0FansLike
3,912FollowersFollow
0SubscribersSubscribe
- Advertisement -spot_img

Latest Articles