on December We first introduce the output of the native image of Gemini 2.0 flash to trusted testers. Now, we make it available for the developer experiment in full All Regions Currently supported by Google AI Studio. You can try new competence using a Gemini 2.0 Flash experimenter (Gemini-2.0-Flash-Exp) To Google Ai Studio and through Gemini API.
Gemini 2.0 Flash combines multimodal input, enhanced reasoning, and the natural understanding of language to create images.
Here are some examples where 2.0 Flash’s multimodans outputs shines:
1. Text and images together
Use Gemini 2.0 Flash to tell a story and it will describe it in pictures, keep the characters and settings throughout the time. Give this feedback and the model tells the story or change the style of its drawings.
Story and generation of illustration of Google Ai Studio
2. Edit to Edit Image
Gemini 2.0 Flash helps you to edit images by multiple turns in a natural language language, good for a perfect image, or explore different ideas.
Multi-turn edit editing editing context editing entire interview with Google AI Studio
3. Understanding the world
Unlike many models of image generation, Gemini 2.0 Flash Leverage World Knowledge and enhances the reasoning of making the TRUE image. It is made perfect for making detailed realistic imagery-like description of a recipe. As it strives for accuracy, like all language models, its knowledge is broad, imperfect or complete.
Interleaved text and image output for a Google Ai Studio recipe
4. Text rendering
Most of the image generation models are struggling with the proper grant of high sequences of the text, which often resulted in poor formatting or uneven characters, or misspellings. Internal benchmarks show that 2.0 flash has a stronger interpretation compared to the leading competition competitions, and good for making advertisements, social posts, or invitations.
Image outputs with high text to render Google Ai Studio
Start making images with Gemini today
Gemini 2.0 Flash Start by Gemini API. Read more about the generation of the image of our Docs.
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")
),
)
If you establish AI agents, develop apps with beautiful visuals as described as interactive stories, or withdrawing visual conversation ideas, with a generation of conversation with a model. We look forward to seeing what creates developers with output of native image and your ANSWERS We can help finish a version ready to make soon.
https://storage.googleapis.com/gweb-developer-goog-blog-assets/images/gemini-image-generation_1.2e16d0ba.fill-1200×600.png
2025-03-12 19:06:00
