Nano Banana 2.1
Nano Banana 2.1 is an image model by Google. A generation and editing model for scene images and reference-based compositions. Version 2.1 is distinct from the earlier Nano Banana 2; cached outputs from the older version are not new evidence for 2.1.
| Setting | Value |
|---|---|
| Model ID | nano_banana_21 |
| Name | Nano Banana 2.1 |
| Availability | available |
| Default for new nodes | no |
| Earlier IDs resolving to this record | nano_banana_2 |
Common declared limits
Section titled “Common declared limits”| Setting | Value |
|---|---|
| Capabilities | text to image, reference edit, multi reference |
| Maximum prompt length | 50000 |
| Controls | quality: draft, max; fallback max; resolution: 1K, 2K, 4K; fallback 1K |
| Element input form | sheet |
| Maximum image references | 14 |
Limits apply together. initial is the studio choice for a new node; default is the fallback for an existing node without that value. Declared language or input support does not guarantee a successful result.
Prompting playbook
Section titled “Prompting playbook”Describe the full scene first, then identify what each reference should contribute. Anchor left/right instructions with visible features. In an edit, say what changes and what stays.
Studio example
Section titled “Studio example”On an Image node (Картинка), choose Nano Banana 2.1. Supply the input image or Element when the selected operation requires a reference. Use this original example as a starting point:
Use the reference for the gardener’s appearance. Show the gardener on the left beside a red wheelbarrow, holding a small blue watering can. Soft morning light; one complete scene.
Review the prompt and expected format before running. Compare the output against the source, including hands, face, object count, lettering and crop. Use the resulting scene image as a video first frame only after approving it. For automation, follow the supported MCP workflow.
Known failure modes
Section titled “Known failure modes”Inspect small writing, body poses and left/right placement. Search and other author-side tools described by Google are not implied by a standard Vini image generation.
Evidence and limits
Section titled “Evidence and limits”On 10 October 2026, one character-sheet test retained the two subjects without reproducing the sheet layout, but added a fragment of sign text despite a no-text request. Do not transfer older 2.0 measurements to 2.1.
An available reference input is not a guarantee of identity preservation. See reference workflows and image style samples. Generation and editing are different tasks; keep their evidence separate.
Reviewed 14 October 2026 against Vini’s image registry and dated research. Official model-author documentation checked on that date. Recheck the guidance when the model version or connected operation changes.