LIVE
Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|
Appofficial publisher

Gemini / Nano Banana

App : A product you use directly

Generates and edits images through simple dialogue in the Gemini app, with remarkable text rendering and character consistency.

The best public-facing entry point for dialogue-guided image editing, almost free.

Overall score
8.0 /10
Security: one caveat, see the card
Utility
9.0
Reliability
5.0
Security
One caveat
Ease
1 click · Beginner

Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.

What it does, concretely

Retouching a photo or creating an illustration usually requires dedicated software, layers, and a learning curve. Gemini / Nano Banana solves this by integrating image generation and editing directly into a conversation: describe what you want, and the model produces or modifies the image in seconds.

In practice, you open the Gemini app, select the 'Create images' tool from the menu, then type an instruction in natural language or upload a photo to edit. You can then refine the result through follow-up messages, change the background, remove an object, alter an outfit, or blend multiple photos into one, all through simple dialogue.

This tool suits people who want to personalise photos, create visuals for social media, or explore artistic styles without mastering editing software. It is also useful for illustrating presentations or quickly testing creative ideas.

It is not suited to professionals who need pixel-level control, a non-destructive layer-based workflow, or who need to produce images of identifiable real people: these cases are blocked by the model's safety filters.

What it offers

  • ·Image generation from natural language text descriptions, supporting many styles (photorealistic, illustration, anime, painting, etc.).
  • ·Editing of uploaded images via conversational instructions: object removal, background change, outfit modification, element addition.
  • ·Consistent character and object likeness maintained across multiple successive editing turns.
  • ·Blending multiple photos into a single image and applying the style of one image to another.
  • ·Legible text rendering within images, suited to infographics, menus, and marketing visuals.
  • ·Choice between Fast, Thinking, and Pro modes from the model menu in the app.
  • ·Regeneration with the Nano Banana Pro model for higher quality output (paid).
  • ·High-resolution output up to 4K via the API, with choice of format and aspect ratio (paid).

In practice

Price
Freemium · from 5 €
Commercial use
Commercial use: paid plan
Available on
web, android, ios
FR interface
Yes

Security and data

Rating
Security: one caveat, see the card
Your data
Data with the vendor
Maintenance
Active
Last release
20 November 2025

Links and repository checked on 25 October 2026 · added on 1 August 2025

How to install Gemini / Nano Banana

1. Go to gemini.google.com or download the Gemini app on Android or iOS. 2. Sign in with a Google account (a free account is sufficient to get started). 3. In the input bar, open the tools menu and select '🍌 Create images'. 4. Choose the desired mode (Fast, Thinking, or Pro) from the model menu. 5. Type your instruction or upload an image to edit, then send. 6. Caution: do not upload photos containing sensitive personal information or faces of people who have not given their consent.

In the same category

Whole category Photo & image →