IN December First, we introduced a native image output in Gemini 2.0 Flash into trusted testers. Today we make it available for a programmer experiments all regions Currently served by Google AI Studio. You can test this fresh ability using the experimental version of Gemini 2.0 flash (Gemini-2.0-Flash-Exp) In Google AI Studio and via API Gemini.
Gemini 2.0 Flash combines multimodal input data, improved reasoning and understanding of the natural language to create images.
Here are some examples in which the 2.0 flash multimodal outputs shine:
1. Text and images Together
Apply Flash Gemini 2.0 to tell the story and illustrates it with photos, maintaining the consistency of characters and settings. Give him an opinion, and the model in addition to history or changes the style of its drawings.
Story and generating illustrations in Google AI Studio
2. Edition of image conversation
Gemini 2.0 Flash helps to edit images by many corners of dialogue in a natural language, ideal for iteration towards an ideal image or jointly discovering various ideas.
Multi-Turn Conversion Editing Image Maintenance of context during a conversation at Google AI Studio
3. World understanding
Unlike many other models of generating images, Gemini 2.0 Flash uses world knowledge and improved reasoning to create Normal picture. This makes it ideal for creating detailed photos that are realistic – like an illustrating recipe. Although he strives for accuracy, like all language models, his knowledge is wide and general, not absolute or complete.
Interspersed for the initial data of the text and image for the recipe at Google AI Studio
4. Text rendering
Most models of generating images try to thoroughly draw long text sequences, often causing poorly formatted or illegible characters or incorrect. Internal references show that 2.0 Flash has stronger rendering compared to leading competitive models and perfect for creating ads, social posts and even invitations.
Image outputs with long text rendering in Google AI Studio
Start taking photos from Gemini today
Start from Gemini 2.0 Flash via API Gemini. Read more about generating images in ours documents.
from google import genai
from google.genai import types
client = genai.Client(api_key="GEMINI_API_KEY")
response = client.models.generate_content(
model="gemini-2.0-flash-exp",
contents=(
"Generate a story about a cute baby turtle in a 3d digital art style. "
"For each scene, generate an image."
),
config=types.GenerateContentConfig(
response_modalities=["Text", "Image"]
),
)
Regardless of whether you are building AI agents, you develop applications with stunning visualizations such as Illustrated Interactive Stories, or brainstorming in conversation, Gemini 2.0 Flash allows you to add text and image generation with one model. We are elated to see what developers create with a native image output and yours feedback It will soon support us finalize the ready for production version.