Experiment with Gemini 2.0 Flash native image generation
In December, we first introduced the original photos in Gemini 2.0 Flash to their trusted laboratories. Today, we are making it available for the experience of developers in all areas currently supported by Google Ai Studio. You can test this new possibility using a pilot version of Gemini 2.0 Flash (Gemini-2.0-Flash-EXP) in Google Ai Studio and across the Gemini Application interface.
Gemini 2.0 Flash combines multimedia inputs, improved thinking, and an understanding of the natural language to create images.
Below are some examples in which the 2.0 multimedia flash outputs shine:
1. Text and pictures together
Use Flash Gemini 2.0 to tell a story and will show it with pictures, while preserving the characters and settings consistently all the time. Give her notes and the model will re -tell the story or change his drawing style.
The generation of story and clarification at Google Ai Studio
2. Editing the conversation photos
Gemini 2.0 Flash helps you to edit photos with many turns in natural linguistic dialogue, which is great for repetition towards an ideal image, or to explore different ideas together.
Editing
3. Understand the world
Unlike many other photo generation models, Gemini 2.0 Flash enhances global knowledge and augmented thinking to create right image. This makes it ideal for creating realistic detailed images – such as clarifying a recipe. Although it strives for accuracy, like all language models, its knowledge is wide and public, not absolute or complete.
Take the text and interlocking images to get a recipe in Google Ai Studio
4. Text of display
Most photo generating models are struggled to provide long sequences of the text accurately, which often leads to bad coordination characters or unread, or spelling errors. Interior standards show that 2.0 Flash has a stronger display compared to the leading competitive models, and is wonderful to create ads, social publications, or even invitations.
Photo outputs with a long text in Google AI studio
Start making pictures with Gemini today
Start with Gemini 2.0 Flash via API Gemini. Read more about generating photos in our 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"]
),
)
Whether you are building artificial intelligence agents, or developing applications with beautiful images such as interactive stories, or brainstorming visual ideas in conversation, Gemini 2.0 Flash allows you to add text and pictures with only one model. We are excited to find out what the developers create with the original photos and your notes will help us finish the touches on a ready -to -produce version soon.
2025-03-12 14:58:00
