What are the Nano Banana image generation models and how do they replace Imagen?

from google import genai

client = genai.Client()

# Generate an image with Nano Banana 2 (Gemini 3.1 Flash Image)
interaction = client.interactions.create(
    model="gemini-3.1-flash-image-preview",  # Nano Banana 2
    input="A photorealistic image of a Python snake debugging code on a glowing terminal.",
)
# Access the generated image:
for step in interaction.steps:
    if step.type == "model_output":
        for part in step.content:
            if part.type == "image":
                with open("output.png", "wb") as f:
                    f.write(part.data)  # image bytes

# Multi-turn editing (conversational editing):
edit = client.interactions.create(
    model="gemini-3.1-flash-image-preview",
    input="Now make the snake wearing a debugging hat and smiling.",
    previous_interaction_id=interaction.id,  # maintains image context
)

# Or via generateContent with Gen Media endpoint:
response = client.models.generate_images(
    model="gemini-3-pro-image-preview",   # Nano Banana Pro
    prompt="Studio quality portrait of an AI robot",
)