Gemini 新「智繪」

import os
import time
from google import genai
from google.genai import types
from PIL import Image
from io import BytesIO

client = genai.Client(
    api_key="sk-***", # 🔑 換成你在 AiHubMix 生成的密鑰
    http_options={"base_url": "https://aihubmix.com/gemini"},
)

# 目前只支援英文 prompt，繪製大量文字的表現較差
response = client.models.generate_images(
    model='imagen-3.0-generate-002',
    prompt='A minimalist logo for a LLM router market company on a solid white background. trident in a circle as the main symbol, with ONLY text \'InferEra\' below.',
    config=types.GenerateImagesConfig(
        number_of_images=1,
        aspect_ratio="1:1", # supports "1:1", "9:16", "16:9", "3:4", or "4:3".
    )
)

script_dir = os.path.dirname(os.path.abspath(__file__))
output_dir = os.path.join(script_dir, "output")

os.makedirs(output_dir, exist_ok=True)

# 生成時間戳作為文件名前綴，避免文件名衝突
timestamp = int(time.time())

# 保存並顯示生成的圖片
for i, generated_image in enumerate(response.generated_images):
  image = Image.open(BytesIO(generated_image.image.image_bytes))
  image.show()
  
  file_name = f"imagen3_{timestamp}_{i+1}.png"
  file_path = os.path.join(output_dir, file_name)
  image.save(file_path)
  
  print(f"圖片已保存至：{file_path}")

IMG_PATH="/your_path/image.jpg"

if [[ "$(base64 --version 2>&1)" = *"FreeBSD"* ]]; then
  B64FLAGS="--input"
else
  B64FLAGS="-w0"
fi

IMG_BASE64=$(base64 "$B64FLAGS" "$IMG_PATH" 2>&1)

curl https://aihubmix.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-***" \
  -d '{
    "model": "gemini-2.0-flash-preview-image-generation",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type":"text",
            "text":"describe the image with a concise and engaging paragraph, then fill color as children's crayon style"
          },
          {
            "type": "image_url",
            "image_url": {
              "url": "data:image/jpeg;base64,'$IMG_BASE64'"
            }
          }
        ]
      }
    ],
    "modalities": ["text","image"],
    "temperature": 0.7
}' \
  | grep -o '"data":"[^"]*"' \
  | cut -d'"' -f4 \
  | base64 --decode > /your_path/imageGen.jpg

import os
from openai import OpenAI
from PIL import Image
from io import BytesIO
import base64

client = OpenAI(
    api_key="sk-***", # 換成你在 AiHubMix 生成的密鑰
    base_url="https://aihubmix.com/v1",
)

# Using text-only input
response = client.chat.completions.create(
    model="gemini-2.0-flash-preview-image-generation",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "generate an adorable mermaid in the sea, bold outline, chibi cartoon, in the style of Children coloring book, B&W, HD",
                }
            ],
        },
    ],
    modalities=["text", "image"],
    temperature=0.7,
)
try:
    # Print basic response information
    print(f"Creation time: {response.created}")
    print(f"Token usage: {response.usage.total_tokens}")
    
    # Check if multi_mod_content field exists
    if (
        hasattr(response.choices[0].message, "multi_mod_content")
        and response.choices[0].message.multi_mod_content is not None
    ):
        print("\nResponse content:")
        for part in response.choices[0].message.multi_mod_content:
            if "text" in part and part["text"] is not None:
                print(part["text"])
            
            # Process image content
            elif "inline_data" in part and part["inline_data"] is not None:
                print("\n🖼️ [Image content received]")
                image_data = base64.b64decode(part["inline_data"]["data"])
                mime_type = part["inline_data"].get("mime_type", "image/png")
                print(f"Image type: {mime_type}")
                
                image = Image.open(BytesIO(image_data))
                image.show()
                
                # Save image
                output_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), "output")
                os.makedirs(output_dir, exist_ok=True)
                output_path = os.path.join(output_dir, "generated_image.jpg")
                image.save(output_path)
                print(f"✅ Image saved to: {output_path}")
            
    else:
        print("No valid multimodal response received, check response structure")
except Exception as e:
    print(f"Error processing response: {str(e)}")

import os
from openai import OpenAI
from PIL import Image
from io import BytesIO
import base64

client = OpenAI(
    api_key="sk-***", # 換成你在 AiHubMix 生成的密鑰
    base_url="https://aihubmix.com/v1",
)

project_root = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))

image_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), "resources", "filled.jpg")
if not os.path.exists(image_path):
    raise FileNotFoundError(f"image {image_path} not exists")

def encode_image(image_path):
    with open(image_path, "rb") as image_file:
        return base64.b64encode(image_file.read()).decode("utf-8")

base64_image = encode_image(image_path)

response = client.chat.completions.create(
    model="gemini-2.0-flash-preview-image-generation",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "describe the image with a concise and engaging paragraph, then fill color as children's crayon style",
                },
                {
                    "type": "image_url", 
                    "image_url": {"url": f"data:image/jpeg;base64,{base64_image}"},
                },     
            ],
        },
    ],
    modalities=["text", "image"],
    temperature=0.7,
)
try:
    # Print basic response information without base64 data
    print(f"Creation time: {response.created}")
    print(f"Token usage: {response.usage.total_tokens}")
    
    # Check if multi_mod_content field exists
    if (
        hasattr(response.choices[0].message, "multi_mod_content")
        and response.choices[0].message.multi_mod_content is not None
    ):
        print("\nResponse content:")
        for part in response.choices[0].message.multi_mod_content:
            if "text" in part and part["text"] is not None:
                print(part["text"])
            
            # Process image content
            elif "inline_data" in part and part["inline_data"] is not None:
                print("\n🖼️ [Image content received]")
                image_data = base64.b64decode(part["inline_data"]["data"])
                mime_type = part["inline_data"].get("mime_type", "image/png")
                print(f"Image type: {mime_type}")
                
                image = Image.open(BytesIO(image_data))
                image.show()
                
                # Save image
                output_dir = os.path.join(os.path.dirname(image_path), "output")
                os.makedirs(output_dir, exist_ok=True)
                output_path = os.path.join(output_dir, "edited_image.jpg")
                image.save(output_path)
                print(f"✅ Image saved to: {output_path}")
            
    else:
        print("No valid multimodal response received, check response structure")
except Exception as e:
    print(f"Error processing response: {str(e)}")

curl "https://aihubmix.com/gemini/v1beta/models/veo-3.0-generate-preview:predictLongRunning?key=sk-***" \
  -H "Content-Type: application/json" \
  -X "POST" \
  -d '{
    "instances":
    [
        {
            "prompt": "A cat playing with a ball"
        }
    ],
    "parameters":
    {
        "numberOfVideos": 1,
        "durationSeconds": 8,
        "aspectRatio": "16:9",
        "personGeneration": "dont_allow"
    }
}'

# 使用步驟 1 返回的 name 字段中的操作ID
curl "https://aihubmix.com/gemini/v1beta/models/veo-3.0-generate-preview/operations/ff5***?key=sk-***"

import json
import base64

# 1. 讀入響應 JSON 文件
with open('yourpath/response.json', 'r') as f:
    data = json.load(f)

# 2. 獲取 base64 編碼的影片字符串
b64_str = data['response']['videos'][0]['bytesBase64Encoded']

# 3. 解碼並寫入 mp4 文件
with open('output.mp4', 'wb') as f:
    f.write(base64.b64decode(b64_str))

print("影片已保存為 output.mp4")

import os
import time
from google import genai
from google.genai import types

client = genai.Client(
    api_key="sk-***", # 換成你在 AiHubMix 生成的密鑰
    http_options={"base_url": "https://aihubmix.com/gemini"},
)

operation = client.models.generate_videos(
    model="veo-2.0-generate-001",
    prompt="Panning wide shot of a calico kitten sleeping in the sunshine",
    config=types.GenerateVideosConfig(
        person_generation="dont_allow",  # "dont_allow" 或 "allow_adult"
        aspect_ratio="16:9",  # "16:9" 或 "9:16"
        number_of_videos=1, # 整數，可選 1、2，默認 2
        durationSeconds=5, # 整數，可選 5、8，默認 8
    ),
)

# 耗時 2-3 分鐘，影片時長 5-8s
while not operation.done:
    time.sleep(20)
    operation = client.operations.get(operation)

for n, generated_video in enumerate(operation.response.generated_videos):
    client.files.download(file=generated_video.video)
    generated_video.video.save(f"video{n}.mp4")  # 保存影片

import os
import time
from google import genai
from google.genai import types

def load_image(path):
    with open(path, "rb") as image_file:
        return image_file.read()
    
client = genai.Client(
    api_key="sk-***", # 換成你在 AiHubMix 生成的密鑰
    http_options={"base_url": "https://aihubmix.com/gemini"},
)

operation = client.models.generate_videos(
    model="veo-2.0-generate-001",
    prompt="The waves in the background keep flowing",
    image=types.Image(
        mime_type="image/png", 
        image_bytes=load_image("img/inferbanner.png")  # 使用你的圖片路徑
    ),
    config=types.GenerateVideosConfig(
        person_generation="dont_allow",
        aspect_ratio="16:9",
        numberOfVideos=1,
        durationSeconds=5,
    ),
)

while not operation.done:
    time.sleep(20)
    operation = client.operations.get(operation)

for n, generated_video in enumerate(operation.response.generated_videos):
    client.files.download(file=generated_video.video)
    generated_video.video.save(f"video{n}.mp4")