使用 Amazon Titan 模型进行图像生成、编辑和搜索 |亚马逊网络服务

import boto3
import json, base64, io
from random import randint
from PIL import Image bedrock_runtime_client = boto3.client("bedrock-runtime") def titan_image( payload: dict, num_image: int = 2, cfg: float = 10.0, seed: int = None, modelId: str = "amazon.titan-image-generator-v1",
) -> list: # ImageGenerationConfig Options: # - numberOfImages: Number of images to be generated # - quality: Quality of generated images, can be standard or premium # - height: Height of output image(s) # - width: Width of output image(s) # - cfgScale: Scale for classifier-free guidance # - seed: The seed to use for reproducibility seed = seed if seed is not None else randint(0, 214783647) body = json.dumps( { **payload, "imageGenerationConfig": { "numberOfImages": num_image, # Range: 1 to 5 "quality": "premium", # Options: standard/premium "height": 1024, # Supported height list above "width": 1024, # Supported width list above "cfgScale": cfg, # Range: 1.0 (exclusive) to 10.0 "seed": seed, # Range: 0 to 214783647 }, } ) response = bedrock_runtime_client.invoke_model( body=body, modelId=modelId, accept="application/json", contentType="application/json", ) response_body = json.loads(response.get("body").read()) images = [ Image.open(io.BytesIO(base64.b64decode(base64_image))) for base64_image in response_body.get("images") ] return images 

# Text Variation
# textToImageParams Options:
#   text: prompt to guide the model on how to generate variations
#   negativeText: prompts to guide the model on what you don't want in image
images = titan_image( { "taskType": "TEXT_IMAGE", "textToImageParams": { "text": "two dogs walking down an urban street, facing the camera", # Required "negativeText": "cars", # Optional }, }
)

# Import an input image like this (only PNG/JPEG supported):
with open("<YOUR_IMAGE_FILE_PATH>", "rb") as image_file: input_image = base64.b64encode(image_file.read()).decode("utf8") # Image Variation
# ImageVariationParams Options:
#   text: prompt to guide the model on how to generate variations
#   negativeText: prompts to guide the model on what you don't want in image
#   images: base64 string representation of the input image, only 1 is supported
images = titan_image( { "taskType": "IMAGE_VARIATION", "imageVariationParams": { "text": "two dogs walking down an urban street, facing the camera", # Required "images": [input_image], # One image is required "negativeText": "cars", # Optional }, },
)

with open("<YOUR_MASK_IMAGE_FILE_PATH>", "rb") as image_file: mask_image = base64.b64encode(image_file.read()).decode("utf8") # Import an input image like this (only PNG/JPEG supported):
with open("<YOUR_ORIGINAL_IMAGE_FILE_PATH>", "rb") as image_file: input_image = base64.b64encode(image_file.read()).decode("utf8") # Inpainting
# inPaintingParams Options:
#   text: prompt to guide inpainting
#   negativeText: prompts to guide the model on what you don't want in image
#   image: base64 string representation of the input image
#   maskImage: base64 string representation of the input mask image
#   maskPrompt: prompt used for auto editing to generate mask images = titan_image( { "taskType": "INPAINTING", "inPaintingParams": { "text": "a cat", # Optional "negativeText": "bad quality, low res", # Optional "image": input_image, # Required "maskImage": mask_image, }, }, num_image=3,
)

# Import an input image like this (only PNG/JPEG supported):
with open("<YOUR_IMAGE_FILE_PATH>", "rb") as image_file: input_image = base64.b64encode(image_file.read()).decode("utf8") images = titan_image( { "taskType": "INPAINTING", "inPaintingParams": { "negativeText": "bad quality, low res", # Optional "image": input_image, # Required "maskPrompt": "white dog", # One of "maskImage" or "maskPrompt" is required }, },
)

# Import an input image like this (only PNG/JPEG supported):
with open("<YOUR_IMAGE_FILE_PATH>", "rb") as image_file: input_image = base64.b64encode(image_file.read()).decode("utf8") # OutPaintingParams Options:
#   text: prompt to guide outpainting
#   negativeText: prompts to guide the model on what you don't want in image
#   image: base64 string representation of the input image
#   maskImage: base64 string representation of the input mask image
#   maskPrompt: prompt used for auto editing to generate mask
#   outPaintingMode: DEFAULT | PRECISE
images = titan_image( { "taskType": "OUTPAINTING", "outPaintingParams": { "text": "forest", # Required "image": input_image, # Required "maskPrompt": "dogs", # One of "maskImage" or "maskPrompt" is required "outPaintingMode": "PRECISE", # One of "PRECISE" or "DEFAULT" }, }, num_image=3,
)

def titan_multimodal_embedding( image_path: str = None, # maximum 2048 x 2048 pixels description: str = None, # English only and max input tokens 128 dimension: int = 1024, # 1,024 (default), 384, 256 model_id: str = "amazon.titan-embed-image-v1",
): payload_body = {} embedding_config: dict = {"embeddingConfig": {"outputEmbeddingLength": dimension}} # You can specify either text or image or both if image_path: # Maximum image size supported is 2048 x 2048 pixels with open(image_path, "rb") as image_file: payload_body["inputImage"] = base64.b64encode(image_file.read()).decode( "utf8" ) if description: payload_body["inputText"] = description assert payload_body, "please provide either an image and/or a text description" print("n".join(payload_body.keys())) response = bedrock_runtime_client.invoke_model( body=json.dumps({**payload_body, **embedding_config}), modelId=model_id, accept="application/json", contentType="application/json", ) return json.loads(response.get("body").read())

from scipy.spatial.distance import cdist
import numpy as np def search(query_emb: np.array, indexes: np.array, top_k: int = 1): dist = cdist(query_emb, indexes, metric="cosine") return dist.argsort(axis=-1)[0, :top_k], np.sort(dist, axis=-1)[:top_k]

1. T-shirt
- A red cotton t-shirt with a crew neck and short sleeves.
- A blue cotton t-shirt with a v-neck and short sleeves.
- A black polyester t-shirt with a scoop neck and cap sleeves. 2. Jeans
- Classic blue relaxed fit denim jeans with a mid-rise waist.
- Black skinny fit denim jeans with a high-rise waist and ripped details at the knees.
- Stonewash straight leg denim jeans with a standard waist and front pockets. 3. Sneakers
- White leather low-top sneakers with an almond toe cap and thick rubber outsole.
- Gray mesh high-top sneakers with neon green laces and a padded ankle collar.
- Tan suede mid-top sneakers with a round toe and ivory rubber cupsole. 4. Backpack
- A purple nylon backpack with padded shoulder straps, front zipper pocket and laptop sleeve.
- A gray canvas backpack with brown leather trims, side water bottle pockets and drawstring top closure.
- A black leather backpack with multiple interior pockets, top carry handle and adjustable padded straps. 5. Smartwatch
- A silver stainless steel smartwatch with heart rate monitor, GPS tracker and sleep analysis.
- A space gray aluminum smartwatch with step counter, phone notifications and calendar syncing.
- A rose gold smartwatch with activity tracking, music controls and customizable watch faces. 6. Coffee maker
- A 12-cup programmable coffee maker in brushed steel with removable water tank and keep warm plate.
- A compact 5-cup single serve coffee maker in matt black with travel mug auto-dispensing feature.
- A retro style stovetop percolator coffee pot in speckled enamel with stay-cool handle and glass knob lid. 7. Yoga mat
- A teal 4mm thick yoga mat made of natural tree rubber with moisture-wicking microfiber top.
- A purple 6mm thick yoga mat made of eco-friendly TPE material with integrated carrying strap.
- A patterned 5mm thick yoga mat made of PVC-free material with towel cover included.

import re def extract_text(input_string): pattern = r"- (.*?)($|n)" matches = re.findall(pattern, input_string) extracted_texts = [match[0] for match in matches] return extracted_texts product_description = extract_text(response_cat) titles = []
for prompt in product_description: images = titan_image( { "taskType": "TEXT_IMAGE", "textToImageParams": { "text": prompt, # Required }, }, num_image=1, ) title = "_".join(prompt.split()[:4]).lower() titles.append(title) images[0].save(f"{title}.png", format="png")

multimodal_embeddings = []
for image_filename, description in zip(titles, product_description): embedding = titan_multimodal_embedding(f"{image_filename}.png", dimension=1024)["embedding"] multimodal_embeddings.append(embedding)

query_prompt = "<YOUR_QUERY_TEXT>"
query_embedding = titan_multimodal_embedding(description=query_prompt, dimension=1024)["embedding"]
# If searching via Image
# query_image_filename = "<YOUR_QUERY_IMAGE>"
# query_emb = titan_multimodal_embedding(image_path=query_image_filename, dimension=1024)["embedding"]
idx_returned, dist = search(np.array(query_embedding)[None], np.array(multimodal_embeddings))