Multimodale Interaktion mit Gemini

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-***", # 🔑 Replace with your key generated on AiHubMix
    http_options={"base_url": "https://aihubmix.com/gemini"},
)

# Currently only supports English prompts, performance is poor with large amounts of text
response = client.models.generate_images(
    model='imagen-4.0-fast-generate-001',
    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)

# Generate timestamp as filename prefix to avoid filename conflicts
timestamp = int(time.time())

# Save and display the generated images
if response and hasattr(response, 'generated_images') and response.generated_images:
    for i, generated_image in enumerate(response.generated_images):
        try:
            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"Image saved to: {file_path}")
        except Exception as e:
            print(f"Error processing image {i+1}: {e}")
else:
    print("Error: No valid image response received")
    print(f"Response type: {type(response)}")
    if response:
        print(f"Response attributes: {dir(response)}")
        if hasattr(response, 'generated_images'):
            print(f"generated_images value: {response.generated_images}")
    else:
        print("Response is empty, please check API key and network connection")

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-2.5-flash-image-preview",
    "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-***", # 🔑 Replace with your key generated on AiHubMix
    base_url="https://aihubmix.com/v1",
)

# Using text-only input
response = client.chat.completions.create(
    model="gemini-2.5-flash-image-preview",
    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",
                }
            ],
        },
    ],
    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.png")
                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 mimetypes
from google import genai
from google.genai import types
import os

def save_binary_file(file_name, data):
    f = open(file_name, "wb")
    f.write(data)
    f.close()
    print(f"File saved to to: {file_name}")

def generate():
    client = genai.Client(
        api_key="sk-***", # 🔑 Replace with your key generated on AiHubMix
        http_options={"base_url": "https://aihubmix.com/gemini"},
    )

    model = "gemini-2.5-flash-image-preview"
    contents = [
        types.Content(
            role="user",
            parts=[
                types.Part.from_text(text="""generate image: an adorable mermaid in the sea, bold outline, chibi cartoon, in the style of Children coloring book, super cute, B&W, HD"""),
            ],
        ),
    ]
    generate_content_config = types.GenerateContentConfig(
        response_modalities=[
            "IMAGE",
            "TEXT",
        ],
    )

    file_index = 0
    for chunk in client.models.generate_content_stream(
        model=model,
        contents=contents,
        config=generate_content_config,
    ):
        if (
            chunk.candidates is None
            or chunk.candidates[0].content is None
            or chunk.candidates[0].content.parts is None
        ):
            continue
        if chunk.candidates[0].content.parts[0].inline_data and chunk.candidates[0].content.parts[0].inline_data.data:
            file_name = f"ENTER_FILE_NAME_{file_index}"
            file_index += 1
            inline_data = chunk.candidates[0].content.parts[0].inline_data
            data_buffer = inline_data.data
            file_extension = mimetypes.guess_extension(inline_data.mime_type)
            save_binary_file(f"{file_name}{file_extension}", data_buffer)
        else:
            print(chunk.text)

if __name__ == "__main__":
    generate()

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

client = OpenAI(
    api_key="sk-***", # 🔑 Replace with your key generated on AiHubMix
    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-2.5-flash-image-preview",
    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"
    }
}'

# Use the operation ID from the name field returned in Step 1
curl "https://aihubmix.com/gemini/v1beta/models/veo-3.0-generate-preview/operations/ff5***?key=sk-***"

import json
import base64

# 1. Read the response JSON file
with open('yourpath/response.json', 'r') as f:
    data = json.load(f)

# 2. Get the base64 encoded video string
b64_str = data['response']['videos'][0]['bytesBase64Encoded']

# 3. Decode and write to mp4 file
with open('output.mp4', 'wb') as f:
    f.write(base64.b64decode(b64_str))

print("Video saved as output.mp4")

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

client = genai.Client(
    api_key="sk-***", # 🔑 Replace with your key generated on AiHubMix
    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" or "allow_adult"
        aspect_ratio="16:9",  # "16:9" or "9:16"
        number_of_videos=1, # Integer, options are 1 or 2, default is 2
        durationSeconds=5, # Integer, options are 5 or 8, default is 8
    ),
)

# Takes 2-3 minutes, video duration is 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")  # Save the video

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-***", # 🔑 Replace with your key generated on AiHubMix
    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")  # your image path
    ),
    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")