1K / 2K / 4K
Choose a resolution for each request. This page starts at 2K.
Nano Banana 2.1
Create and edit images with Nano Banana 2.1.
Image models you can open next
Explore other image models. Open a model to start creating.
Nano Banana 2.1
Turn your brief into an image. Give the next edit a clear direction.
Nano Banana 2.1 is Google’s updated image generation and editing model, released on October 6, 2026. Google reports improvements in visual quality, text rendering plus subject consistency. In VoraVideo, begin with a prompt or your own guides, then pick the framing and resolution for the image you need.
Text to image / Image to image1K / 2K / 4KUp to 14 references
Up to 14
Add JPEG, PNG or WebP images, as many as 20 MB each, in image-to-image mode.
1 image
Render a new image or upload a downloaded output as the guide for another edit.
Shape the subject, the layout plus the final image
Set a clear visual goal, use guides deliberately and inspect the output at its intended size.
Build a scene from a written brief
Spell out the main subject, materials, camera angle and light. Name the objects you want plus where they belong. For one ad, specify which area should stay empty for copy.
Guide an edit with reference images
Upload product stills, character guides or a style sample. Explain the role of each image and list the fine points to preserve. Clear guide roles make a complex brief easier to evaluate.
Draft posters with readable hierarchy
Put the exact headline in quotation marks and specify its position, size plus contrast. Start with a short title. Before publishing; an improved model can still make text errors, inspect spelling and individual characters.
Choose a ratio before you generate
Use one portrait frame for a poster, a square for a product card or a wide frame for a banner. Auto lets the model choose. When the focal subject and empty areas are explicit, extreme panoramas work best.
Bring search into a visual draft
Optional web search can supply current information; image search can find visual guides. Before relying on a factual graphic or publishing a design, verify names, numbers and image rights.
Refine one decision at a time
Download a output and upload it for the next edit. While naming what should stay the same, ask for one focused change, like the backdrop or light. Each request starts from the references you supply.
Core capabilities of Nano Banana 2.1
The update focuses on instruction following, subject consistency, text rendering plus overall image quality.
Better instruction following and subject consistency
Google identifies instruction following and subject consistency as key improvements in 2.1. The model combines text and guide images to interpret a creative brief, better preserve a subject's look during generation and editing, and respond to layout, light and style instructions.
Up to 14 reference images
Supply several visual guides in one request to add subject, style and framing fine points.
Generation and editing in one model
Use text-to-image or reference-based editing to make a new image or adjust a current one.
Clearer text and more refined visual detail
Google reports improvements in text rendering, visual design and overall image quality, helping express the relationships between words, graphics plus subjects. Resolution and aspect-ratio choices give you control over detail and framing. Generated text still needs proofreading.
1K, 2K and 4K output
Choose a resolution for the detail you need. This page defaults to 2K plus generates one image per request.
Flexible aspect ratios
Pick automatic sizing or 14 fixed ratios for landscape, square and portrait compositions.
How to use Nano Banana 2.1
01
Write a brief or add your references
Use text-to-image for a new scene. Pick image-to-image to upload guides and explain which fine points to preserve or change.
02
Choose the output and review the credits
Set the ratio, resolution and thinking level. Keep search off unless the task needs it. After changing settings, the button shows VoraVideo credits for your current inputs; review it.
03
Generate, inspect and refine
Wait for completion, inspect the image plus download it. Check text, faces and product details. If you want another edit, upload the output as a new guide.
FAQ
Nano Banana 2.1 · FAQ
What changed from Nano Banana 2?
Google spells out 2.1 as an update to Nano Banana 2 with better visual quality, prompt adherence, typography and subject consistency. The two models have separate settings plus pricing in VoraVideo. When deciding which suits a project, compare them with your own brief and guides.
What resolutions and aspect ratios can I choose?
Pick 1K, 2K or 4K; the default here is 2K. These are resolution tiers, with pixel dimensions varying by ratio. There are 14 ratios plus Auto, along with 1:1, 9:16, 16:9 and panoramas as many as 8:1 or 1:8. This model has no 0.5K option.
Can I combine several reference images?
Yes. Image-to-image accepts as many as 14 JPEG, PNG or WebP images, each as many as 20 MB. Explain what each image contributes. Subject consistency guides the edit but does not guarantee an exact copy of one face, logo or product.
Does this page include mask editing or one continuous chat?
This page supports prompt-based generation and reference-image editing. A mask upload plus persistent conversation are not available here. To continue an edit, download your output, upload it as a guide and write the next instruction.
What do thinking and search change?
Thinking controls how much reasoning the model applies before rendering. Auto lets it decide; Minimal, Medium plus High are also available. Web and image search are optional plus off by default. Search can help a draft use current information or visual guides, but factual inspects remain necessary.
How are VoraVideo credits calculated?
The quote includes the picked resolution, prompt and guide count, plus estimates for thinking and enabled search tools. It assumes 1,000 thinking tokens plus one query per enabled search tool; actual provider usage can differ. VoraVideo credits are separate from EvoLink credits. The button shows this credits reserved for this request.
Will the generated image contain an AI watermark?
Google states that rendered images include the invisible SynthID watermark. This identifies AI-generated content; it does not guarantee factual accuracy or grant permission to use one person, brand or third-party image.
Create your next image with Nano Banana 2.1
Begin with a clear brief, pick your guides and inspect the credits before rendering.