3.2.2. Image Generation (DALL-E)

🔧 Implementation Reference: DALL-E

Parameters:

Testable Pattern:

response = client.images.generate(model="dall-e-3", prompt="A sunset over mountains", size="1024x1024")
image_url = response.data[0].url

Error Handling Pattern:

from openai import AzureOpenAI, BadRequestError, RateLimitError

try:
    response = client.images.generate(model="dall-e-3", prompt=user_prompt, size="1024x1024")
    image_url = response.data[0].url
except BadRequestError as e:
    if "content_policy_violation" in str(e):
        # Content policy violation - prompt rejected
        logging.warning("Prompt rejected by content filter")
        # Provide user-friendly message; do not expose filter details
    else:
        # Invalid parameters (e.g., unsupported size)
        logging.error(f"Invalid request: {e.message}")
except RateLimitError:
    # Quota exceeded - back off
    time.sleep(60)

CLI Equivalent (REST):

curl -X POST "https://{resource}.openai.azure.com/openai/deployments/{deployment}/images/generations?api-version=2024-08-01-preview" \
  -H "Content-Type: application/json" \
  -H "api-key: {key}" \
  -d '{"prompt": "A sunset over mountains", "size": "1024x1024", "n": 1}'

⚠️ Exam Trap: Only prompt is required. Size, quality, and n are all optional.