見出し画像

AWS BedrockのStable Diffusion XLで画像生成やーる

がちもとさん

はじめに

AWS BedrockのStable Diffusion XLで画像生成をやっていきます。こちらの記事を参考にしています。

導入

1．IAMロールを作成
2．アクセスキーとシークレットキーをメモ
3．ポリシーを作成

{
	"Version": "2012-10-17",
	"Statement": [
		{
			"Sid": "Statement1",
			"Effect": "Allow",
			"Action": [
				"bedrock:*"
			],
			"Resource": "*"
		}
	]
}

4．AWS BedrockのModel access->EditからStable Diffusion XLにチェック
5．AWS CLIをインストール

6．コマンドプロンプトを開く

C:\Users\admin>aws --version
aws-cli/2.13.30 Python/3.11.6 Windows/10 exe/AMD64 prompt/off

7．aws configureでアクセスキーとシークレットキーを設定

C:\Users\admin>aws configure
AWS Access Key ID [****************]: 
AWS Secret Access Key [****************]: 
Default region name [ap-northeast-1]:
Default output format [None]: json

8．anaconda promptを開き、Python 3.11環境を作成

(base) C:\Users\admin\Documents\PythonProjects>conda create -n py311 python=3.11
(base) C:\Users\admin\Documents\PythonProjects>conda activate py311

9．ライブラリのインストール

(py311) C:\Users\admin\Documents\PythonProjects>pip install --no-build-isolation --force-reinstall boto3>=1.28.57 awscli>=1.29.57 botocore>=1.31.57
(py311) C:\Users\admin\Documents\PythonProjects>pip install pillow==9.5

10．bedrockのツールをダウンロード

11．utilsをプロジェクトフォルダに置く

utils

12．app.pyを作成。os.environ["BEDROCK_ASSUME_ROLE"]はコメントアウトしてOK。

# Python Built-Ins:
import base64
import io
import json
import os
import sys

# External Dependencies:
import boto3
from PIL import Image

module_path = ".."
sys.path.append(os.path.abspath(module_path))
from utils import bedrock, print_ww


# ---- ⚠️ Un-comment and edit the below lines as needed for your AWS setup ⚠️ ----

os.environ["AWS_DEFAULT_REGION"] = "us-east-1"  # E.g. "us-east-1"
# os.environ["AWS_PROFILE"] = "<YOUR_PROFILE>"
# os.environ["BEDROCK_ASSUME_ROLE"] = "arn:aws:iam::785208610362:user/s-fujimoto"  # E.g. "arn:aws:iam::xxxxxxxxxxxx:role/xxxxxx"  # E.g.

boto3_bedrock = bedrock.get_bedrock_client(
    assumed_role=os.environ.get("BEDROCK_ASSUME_ROLE", None),
    region=os.environ.get("AWS_DEFAULT_REGION", None),
)

print(
    "1 if the image is generated using a prompt, 2 if the image is generated using an image and a prompt."
)
choice = int(input("Enter Choice :"))
print(choice)

if choice == 1:
    print("please enter the Prompt"),
    prompt = str(input())
    print(
        "Please enter 3 negative Prompt eg:poorly rendered,poor background details,poorly drawn face"
    )
    negative_prompts = []
    n = 3
    for i in range(0, n):
        # ele = [input(), str(input()),]
        ele = str(input())
        negative_prompts.append(ele)
    print(negative_prompts)
    style_preset = "photographic"
    request = json.dumps(
        {
            "text_prompts": (
                [{"text": prompt, "weight": 1.0}]
                + [
                    {"text": negprompt, "weight": -1.0}
                    for negprompt in negative_prompts
                ]
            ),
            "cfg_scale": 5,
            "seed": 5450,
            "steps": 70,
            "style_preset": style_preset,
        }
    )
    modelId = "stability.stable-diffusion-xl"

    response = boto3_bedrock.invoke_model(body=request, modelId=modelId)
    response_body = json.loads(response.get("body").read())

    print(response_body["result"])
    base_64_img_str = response_body["artifacts"][0].get("base64")
    print(f"{base_64_img_str[0:80]}...")

    os.makedirs("data", exist_ok=True)
    image_1 = Image.open(
        io.BytesIO(base64.decodebytes(bytes(base_64_img_str, "utf-8")))
    )
    image_1.save("data/image_1.png")
    image_1

if choice == 2:
    print("please enter the image file path"),
    image_path = str(input())
    print("please enter the Prompt"),
    change_prompt = str(input())
    print(
        "Please enter 3 negative Prompt eg:poorly rendered,poor background details,poorly drawn face"
    )
    negative_prompts = []
    n = 3
    for i in range(0, n):
        # ele = [input(), str(input()),]
        ele = str(input())
        negative_prompts.append(ele)
    print(negative_prompts)
    style_preset = "photographic"

    def image_to_base64(img) -> str:
        """Convert a PIL Image or local image file path to a base64 string for Amazon Bedrock"""
        if isinstance(img, str):
            if os.path.isfile(img):
                print(f"Reading image from file: {img}")
                with open(img, "rb") as f:
                    return base64.b64encode(f.read()).decode("utf-8")
            else:
                raise FileNotFoundError(f"File {img} does not exist")
        elif isinstance(img, Image.Image):
            print("Converting PIL Image to base64 string")
            buffer = io.BytesIO()
            img.save(buffer, format="PNG")
            return base64.b64encode(buffer.getvalue()).decode("utf-8")
        else:
            raise ValueError(f"Expected str (filename) or PIL Image. Got {type(img)}")

    original_image = Image.open(image_path)
    image_1 = original_image.resize((512, 512))
    init_image_b64 = image_to_base64(image_1)
    print(init_image_b64[:80] + "...")

    request = json.dumps(
        {
            "text_prompts": (
                [{"text": change_prompt, "weight": 1.0}]
                + [
                    {"text": negprompt, "weight": -1.0}
                    for negprompt in negative_prompts
                ]
            ),
            "cfg_scale": 10,
            "init_image": init_image_b64,
            "seed": 321,
            "start_schedule": 0.6,
            "steps": 50,
            "style_preset": style_preset,
        }
    )
    modelId = "stability.stable-diffusion-xl"

    response = boto3_bedrock.invoke_model(body=request, modelId=modelId)
    response_body = json.loads(response.get("body").read())

    print(response_body["result"])
    image_2_b64_str = response_body["artifacts"][0].get("base64")
    print(f"{image_2_b64_str[0:80]}...")

    image_2 = Image.open(
        io.BytesIO(base64.decodebytes(bytes(image_2_b64_str, "utf-8")))
    )
    image_2.save("data/image.png")

実行

オプション1は、プロンプトから画像生成します

(py311) C:\Users\admin\Documents\PythonProjects\Bedrocks>python app.py
Create new client
  Using region: us-east-1
boto3 Bedrock client successfully created!
bedrock-runtime(https://bedrock-runtime.us-east-1.amazonaws.com)
1 if the image is generated using a prompt, 2 if the image is generated using an image and a prompt.
Enter Choice :1
1
please enter the Prompt
japanese mountain
Please enter 3 negative Prompt eg:poorly rendered,poor background details,poorly drawn face
poorly rendered
poor background details
poorly drawn face
['poorly rendered', 'poor background details', 'poorly drawn face']
success
iVBORw0KGgoAAAANSUhEUgAAAgAAAAIACAIAAAB7GkOtAAADWmVYSWZNTQAqAAAACAAGAQAABAAAAAEA...


japanese mountain

オプションの2は、画像とプロンプトを入力して画像生成します

(py311) C:\Users\admin\Documents\PythonProjects\Bedrocks>python app.py
Create new client
  Using region: us-east-1
boto3 Bedrock client successfully created!
bedrock-runtime(https://bedrock-runtime.us-east-1.amazonaws.com)
1 if the image is generated using a prompt, 2 if the image is generated using an image and a prompt.
Enter Choice :2
2
please enter the image file path
image.jpg
please enter the Prompt
cute girl
Please enter 3 negative Prompt eg:poorly rendered,poor background details,poorly drawn face
poorly rendered
poor background details
poorly drawn face
['poorly rendered', 'poor background details', 'poorly drawn face']
Converting PIL Image to base64 string
iVBORw0KGgoAAAANSUhEUgAAAgAAAAIACAIAAAB7GkOtAAABdmlDQ1BJQ0MgUHJvZmlsZQAAeJylkLFL...
success
iVBORw0KGgoAAAANSUhEUgAAAgAAAAIACAIAAAB7GkOtAACj0GVYSWZNTQAqAAAACAAGAQAABAAAAAEA...


input image
cute girl

だいぶ変えてきたなｗ



この記事が参加している募集

AIとやってみた

25,329件

この記事が気に入ったらサポートをしてみませんか？