Nano Banana·de GoogleText to image

Nano Banana 2 Text-to-Image

Google's lightweight yet powerful AI image generation model, built for creators who need fast, high-quality visuals from simple text prompts.

Abrir en el espacio de trabajo →google/nano-banana-2/text-to-image

Parámetros

Parámetro	Tipo	Por defecto	Rango u opciones
aspect ratio `aspect_ratio` The aspect ratio of the generated media.	select	1:1	1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9
resolution `resolution` The resolution of the output image.	select	1k	1k, 2k, 4k
output format `output_format` The format of the output image.	select	default	default, png, jpeg
enable image search `enable_image_search` If enabled, the model will use image search to ground the generation with real-time information.	select	false	true, false
enable web search `enable_web_search` If enabled, the model will use web search to ground the generation with real-time information.	select	false	true, false
media resolution `media_resolution` Controls how input media is processed. LOW reduces tokens per image/video, possibly losing detail but allowing longer videos in context. Supported values: HIGH, MEDIUM, LOW.	select	default	default, low, medium, high
thinking level `thinking_level` Controls the amount of internal reasoning the model performs before generating a response. Higher levels may improve quality on complex tasks but increase latency.	select	default	default, high, minimal

Sin archivos de referencia: este modelo trabaja solo con el prompt.

Nano Banana has no negative_prompt — describe positively (“an empty, deserted street”, not “no cars”). Naming what you don’t want can summon it into the frame.
There is no negative prompt on this family; write exclusions as positive constraints.
Weight syntax such as (word:1.3) is ignored; it only wastes prompt space.
Keep to at most 5 distinct characters in one prompt.

De las reglas verificadas de LUVI para esta familia.