What's new

A new image generation and editing model is now available in our chat — Nano Banana 2 (powered under the hood by Google's Gemini 3.1 Flash Image).

What's new and why it's cool:

• Significantly cheaper: Generation has become much more affordable compared to the previous version. This is the case where quality goes up and the price goes down — an economy we like.
• High speed: The model delivers a finished result in an average of 10–15 seconds without losing quality. Time is money, and fast neural bananas are a double win.
• Perfect text: Excellent at generating typography and readable text in different languages directly on images. Ideal for mockups and presentations.
• Frame stability: Confidently maintains facial consistency (up to 5 characters) and preserves the details of complex scenes (up to 14 objects).
• Advanced logic: The model better understands complex multi-layered prompts and can rely on up-to-date data from the web.

Jump into the chat and test the new feature. It's a great tool for tasks that require a strict balance between speed, production quality, and a nice price.

Meet Furry Master v4 — a major upgrade for those crafting anthropomorphic heroes. We’ve traded the old versions for this powerful fourth-generation tool to take your generations to the next level.

Why Furry Master v4 is mastery without the air quotes:

• Anatomy Without the Surprises: The model has learned to properly handle paws, tails, and complex poses. Your heroes will no longer look like they just escaped a funhouse hall of mirrors.
• Texture Breakthrough: Incredible detail on fur, scales, and accessories. Every single hair is in its place — perfectionists, rejoice.
• Seamless "Cleaning": Version v4 plays beautifully with our editing tools. Removing an unwanted object or touching up the background is now possible without sacrificing the quality or style of the main image.
• Understands You (Finally): Enhanced comprehension of complex prompts allows for more precise rendering of lighting, atmosphere, and the fine nuances of your creative vision.

We are expanding our visual content capabilities and adding support for the Google Nano Banana Pro model.

New features are now available to you directly in the chat interface:

• Image generation: create graphics from scratch using text descriptions.
• In-dialog editing: make changes and refine images directly while chatting with the model.

This update allows you to work with images faster and more conveniently without leaving the familiar chat window.

• Improved color correction: colors are more accurate, cleaner, and more natural.
• Increased detail: finer elements and textures are rendered more thoroughly.
• Updated post-processing algorithms: images look higher quality right out of generation.
• Reduced generation cost.

• Faster generation
• Fewer artifacts
• Reduced cost
• Improved tag handling and updated documentation

• Next-level photorealism: significant reduction of the "plastic" look and artificial skin smoothness that characterized earlier versions.
• Ultra-detailed textures: high-precision rendering of complex natural elements — from skin pores and wrinkles to animal fur and water ripples.
• Advanced text rendering: the model correctly generates long captions, complex layouts, and multi-line text in multiple languages.
• Deep prompt understanding: improved interpretation of complex instructions, including the spatial arrangement of objects and stylistic nuances.

• Improved prompt fidelity and greater style versatility.
• Test users report increased detail and realism.
• Significantly improved anatomy and compositional consistency.
• Improved consistency: many issues with facial "drift" and background distortion during partial image edits have been fixed.

• Improved image quality
• Seams when stitching together multiple 5-second videos are less noticeable
• Improved human and animal anatomy
• Great for anime

🌟 What's new?

• Up-to-date dataset: The model's knowledge base has been updated, data cutoff — last month.
• Improved lighting: Faces are noticeably brighter; fixed an issue with overly deep shadows.
• Composition stability: Fixed a bug where the model often produced "collages" (multiple angles in a single image).
• Prompt adherence: Slightly improved accuracy in understanding text prompts.
• Character refinement: Characters introduced in the previous version are now trained more deeply and produce higher-quality results.

⚠️ Known issues

Although overall stability has increased, the update introduced a few caveats:

1. Prompt sensitivity: The model has become more demanding of prompt quality. Short prompts or poor structure now more often lead to unsuccessful results.
2. Eye color: Rare cases of the eye color not matching what was specified in the prompt may occur.
3. Style inconsistency: Due to weight merging to support third-party LoRAs, the style can vary, especially when generating specific characters.
4. Character limitations: Some new characters (e.g., Ye Shunguang from ZZZ) still require many tags and currently work best in portraits (close-up headshots).

🛠 Technical usage recommendations

For best results, it's recommended to follow these settings:

• Prompt composition: For a single character, use the tag combo 1girl, solo.
• SFW filtering: To avoid 18+ content, add the word nude to the negative prompt (Negative Prompt).

• Adjusted the model's default overall style
• Improved visual clarity and accuracy of character rendering