DeepMind's May 2025 text-to-image model with exceptional prompt adherence, capable of generating images with great detail, rich lighting, and few distracting artifacts.
Optional parameters:
Aspect ratio of your image (1:1, 16:9, 9:16, 4:3, 3:4).
Notes:
Non-English input will be translated first. Serves the `imagen-4.0-ultra-generate-05-20` model from Google Vertex, and has a maximum input of 480 tokens.
Powered by a server managed by @google. Learn more
Build with Imagen-4 using the Poe API
Start by creating an API key, for use with any bot on Poe:
Code samples
python
import openai
client = openai.OpenAI(
api_key = "YOUR_POE_API_KEY", # or os.getenv("POE_API_KEY")
base_url = "https://api.poe.com/v1",
)
chat = client.chat.completions.create(
model = "imagen-4",
messages = [{
"role": "user",
"content": "A bustling market scene on a distant alien planet, inspired by the intricate details of Persian miniature painting"
}]
)
print(chat.choices[0].message.content)See the full documentation for comprehensive guidance on getting started.