Gemini 2.5 Flash Image Officially Released: New Aspect Ratios and Powerful AI Editing Features

Google has officially rolled out Gemini 2.5 Flash Image, its next-generation AI image generation and editing model, for full production use. The advanced tool, which has already drawn global attention, now comes with a wider range of aspect ratios and an option for image-only output, opening new creative possibilities for developers, designers, and enterprises.

What’s New in Gemini 2.5 Flash Image?

Gemini 2.5 Flash Image is designed to go beyond basic AI-generated visuals. The model allows users to:

Blend multiple images seamlessly.

• Maintain consistent characters for storytelling and design.
• Edit with natural language commands.
• Leverage Gemini’s vast knowledge base for realistic and context-aware modifications.

Most notably, the update introduces 10 supported aspect ratios, covering everything from cinematic landscapes to social media-friendly verticals.

Supported ratios include:

• Landscape: 21:9, 16:9, 4:3, 3:2
• Square: 1:1
• Portrait: 9:16, 3:4, 2:3
• Flexible: 5:4, 4:5

Real-World Applications

Several companies and developers are already harnessing Gemini 2.5 Flash Image to push creative boundaries:

• Cartwheel has integrated the model into its “Pose Mode” feature, enabling precise 3D posing and consistent character rendering.
• “The new Gemini 2.5 Flash Image was the first model that could balance world knowledge with pose faithfulness,” said Andrew Carr, Co-founder of Cartwheel.
• Volley, creators of the AI-powered dungeon crawler Wit’s End, use the tool for real-time edits, generating character portraits, scene visuals, and quick iterations directly from chat or voice.
• “Latency under 10 seconds allows live applications where players can refine styles in multi-turn loops,” explained James Wilsterman, CTO at Volley.
• Gemini 2.5 Flash Image has also powered hackathon projects across STEM education, AR, and marketing, showcasing its versatility.

Developer Access and Pricing

Developers can start building with Gemini 2.5 Flash Image today via the Gemini API, Google AI Studio, or Vertex AI for enterprise solutions.

Features like “build mode” in AI Studio let creators design and deploy custom apps instantly. Sample community apps include:

Bananimate – Generate animated GIFs from prompts.

Enhance – Infinite zoom and upscaling with hidden easter eggs.

Fit Check – Virtual AI-powered outfit try-ons.

Pricing: $0.039 per image, or $30 per 1M output tokens (aligned with standard Gemini 2.5 Flash pricing).

Sample Code Snippet

Here’s a Python example to generate an 80s-inspired image with a 16:9 aspect ratio:

from google import genai

from google.genai import types

from PIL import Image

client = genai.Client()

prompt = "Create a photograph of the subject as if they were living in the 1980s, capturing fashion and atmosphere."

image = Image.open('/path/to/image.png')

response = client.models.generate_content(

model="gemini-2.5-flash-image",

contents=[prompt, image],

config=types.GenerateContentConfig(

response_modalities=["IMAGE"],

image_config=types.ImageConfig(aspect_ratio="16:9")

)

)

for part in response.parts:

if part.inline_data:

generated_image = part.as_image()

generated_image.show()

The Future of AI Creativity

With its expanded aspect ratios, fast rendering, and developer-first tools, Gemini 2.5 Flash Image is set to redefine AI-powered content creation. Google says it is “continually amazed by the creativity of its developer community” and is looking forward to the next wave of innovation.