Nano Banana 2.1 supports Text to image workflows. sjolt connects the model to one queue, account controls, and task status API so teams can test parameters before API integration.
Average generation time is about a few minutes. The Playground keeps the same request body across Examples and README sections. Create a single image from a prompt, or add up to 14 references to guide an edit.
Resolution pricing
Playground Examples
A translucent amber glass teapot with a curved handle and two small porcelain cups on pale limestone, a soft teal studio backdrop, angled morning sunlight casting detailed caustics, precise material textures, refined editorial product photograph, wide 16:9 composition, no text, logos, or watermarks.
A tranquil coastal library with curved white plaster walls, oak bookshelves, one sculptural rust-colored chair and a tall arched window overlooking the sea, soft afternoon sunlight, realistic architectural editorial photography, wide 16:9 composition, no people, text, logos, or watermarks.
A tiny red panda astronomer tending a brass telescope in a hilltop observatory surrounded by flowering trees, a luminous crescent moon over a quiet valley, intricate gouache illustration with warm paper texture and a teal and amber palette, wide 16:9 composition, no text, logos, or watermarks.
Similar Models
High-fidelity image generation and reference-guided editing with photorealistic detail, typography, and flexible framing.
Create expressive images with Midjourney 8.2, 8.1, 7, or Niji 7, with controls for composition, stylization, and repeating patterns.
ByteDance image generation and editing for cinematic visuals, product shots, precise local edits, and reference-guided creative work.
Model overview
Turn a written brief into an image for product concepts, social visuals, and illustrated scenes. Choose text-to-image for a new composition, or image edit when you have source images to guide the result.
Build a product concept by naming the subject, materials, background, and lighting. Give the image a clear visual focus, then refine one detail at a time.
Add 1–14 PNG, JPEG, or WebP images and explain which features to preserve. Use references for subject appearance, setting, color, or composition, and describe the intended change explicitly.
Both generation modes support 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9. Choose a landscape, square, portrait, or ultrawide frame to match your composition.
Model characteristics
Each task produces one image at the selected resolution tier. Pixel dimensions follow the selected aspect ratio.
State the subject and setting first, then add composition, light, materials, and style. For an edit, distinguish the elements to keep from those to change.
Use text-to-image without references, or image edit with 1–14 reference images. Both modes require a prompt.
Submit the selected generation task, retain its task ID, and poll for completion or receive a webhook. Completed tasks return the image URL.
FAQ
Choose 1K, 2K, 4K. The API defaults resolution to 1K.
Choose image edit and supply 1–14 PNG, JPEG, or WebP images with a prompt describing the desired edit. API references must use public HTTP(S) URLs.
Both modes support 10 aspect ratios: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9. The default is 1:1.
