Nano Banana creates images from natural-language prompts and edits existing visuals with image references. Describe the subject, materials, lighting and composition for a new scene, or provide prepared photographs and identify a local change, an added object or the sources to combine. The prompt explains the details to preserve, while size selects one of ten aspect ratios for the result. Use these inputs for photographic concepts, material variations, character placement and scene studies, then review the current per-generation estimate on the matching task.
Nano Banana is developed by Google. Vidgo provides access to the model. Model names and trademarks belong to their respective owners.Choose Text to Image when words should establish the whole composition. Choose Image Editing when a source supplies the person, object or environment to retain. Describe each reference’s role, the desired change and the visual details to preserve, then select a framing that suits the intended result.
Google's leaderboard-topping image model (Gemini 2.5 Flash) excelling in natural language editing, character consistency, and multi-image blending.
Google's leaderboard-topping image model (Gemini 2.5 Flash) excelling in natural language editing, character consistency, and multi-image blending.
Text generation uses prompt and optional size. Editing also supplies image_urls with one or more source images. A single reference can define the whole scene for a local change, while separate references can provide the person and destination. Explain that relationship in the prompt so the request clearly identifies what should change and what should remain consistent.
| Model / task | Input and workflow |
|---|---|
| Nano Banana Text to Image | Google's leaderboard-topping image model (Gemini 2.5 Flash) excelling in natural language editing, character consistency, and multi-image blending. |
| Nano Banana Edit | Google's leaderboard-topping image model (Gemini 2.5 Flash) excelling in natural language editing, character consistency, and multi-image blending. |
Describe concrete subjects and specify the parts that define the scene. The existing records below show a clockmaker’s mechanism, a lettered station window, a local glaze change, an added cat and a person placed on a raft.
Write the mechanism, working hands, tool and light. The clockmaker record asks for tweezers placing a brass gear beside another wheel, with visible wear, oil and wood grain. Inspect the actual result for contact and material relationships when developing a workshop visual concept.
Describe the wording, line order and the surface carrying it. The station-window record asks for LOST and FOUND on the glass and a small opening-hours card. Inspect the actual lettering, reflections and object placement before using the image in a scene proposal.
Supply the original photograph and name the exact object to modify. The tile record changes only the middle glaze from celadon to cobalt and updates its handwritten label, while retaining the other tiles, wall, camera and lighting. Compare the source and result for that localized change.
Describe where the new subject belongs and how it touches the existing scene. The boat record adds a sleeping cat and folded blanket while retaining the oars, mist and water. Inspect scale, support and contact shadow against the photograph.
Assign one image to identity and another to the setting, then describe pose and activity. The raft record places the same woman cutting red paper in the river scene while retaining her appearance, the cliffs and raft. Inspect the person, hands and contact with the new setting.
The first record supplies a tile photograph and requests the middle glaze and label to change while the rest of the display stays consistent. The second uses one image for the woman’s identity and one for the river and raft, then describes her seated paper-cutting activity. Read the full prompts and compare every source with its actual result to inspect the retained details, local replacement and combined scene.
Use this photograph as the only source. Change only the middle tile: replace the celadon-green glaze with a deep glossy cobalt-blue glaze, and change its handwritten label from "CELADON" to "COBALT BLUE" in the same letter size, paper and handwriting. Keep the left copper-red tile and "COPPER RED" label, the right iron-black tile and "IRON BLACK" label, the plaster wall, lighting and camera angle exactly. No other tiles, no extra text, no logos, no watermarks.
Use image 1 as the identity reference and image 2 as the destination. Place this same woman sitting cross-legged on the bamboo raft, cutting a sheet of red paper with small scissors, a few red scraps resting on the raft. Preserve her face, age, silver bun, indigo coat and ink-stained fingers from image 1. Preserve the river, limestone cliffs and raft from image 2. Natural overcast light, physically consistent contact with the raft, one woman only, no collage edges. No extra people, no text, no logos, no watermarks.
Use text to develop a new photographic scene or prepare images for a material edit, added object or person-and-environment composition. State the input roles and intended result, identify the details to preserve and choose one of ten aspect ratios. Inspect the completed image for a storyboard, workshop concept, material study, character presentation or illustration reference.
Describe the hands, tools, contact and light, then choose a text task and framing. Inspect the generated structure and materials for a workshop visual proposal.
Write the exact words, line order and location within the scene. Review the actual lettering and its relationship to the surrounding objects before selecting an image for a presentation.
Provide the photograph and identify the exact surface to change, including any related label. Preserve the remaining objects and light, then compare the edit for a material study.
Supply the scene and describe the subject’s size, position and supporting contact. Inspect the resulting placement and shadows for a photographic or narrative concept.
Provide identity and destination references, explain their roles and describe the activity. Review face, clothing, hands and spatial continuity for a character presentation.
Retain the selected model, prompt, reference URLs and size setting. Submit the authenticated API request and track its task ID to retrieve the completed image.
Nano Banana uses the current per-generation rate shown for each task in the dynamic table. The text and editing workflows have the same current rate. Open the selected task with your prompt, references and framing to review the request estimate, then use that full amount and the planned number of tests when budgeting the project.
| Model | Provider | Workflow | Input material | Output specification | Starting rate |
|---|---|---|---|---|---|
| Nano Banana Text to Image | Text to Image | Text prompt | Aspect-ratio settings | $0.025 / generation | |
| Nano Banana Edit | Image Editing | Reference images | Aspect-ratio settings | $0.025 / generation |
Test your creative brief online, then bring the verified request into your application.
Enter the prompt, add source images for editing and select a supported aspect ratio where needed. Review the per-generation estimate, create the image and compare appearance, structure, text, lighting and the requested changes with the brief.
Choose a task, inspect its settings and cost, and follow the result from an online test to an authenticated API request.
Choose Text to Image for a written scene or Image Editing for existing visual sources. Describe what to create or change and the details to preserve, assign each reference a role and choose the size aspect ratio suited to the result.
Open the matching task, enter your brief and supply the required images. Review the generated result against subject appearance, composition and the requested changes before carrying the workflow into a project.
Review the selected task’s current per-generation estimate and include the planned number of tests. Keep the prompt, source roles and framing clear so each test can answer a concrete creative question.
Read the actual prompt and inspect its source images and result together. Use those examples to understand how to assign input roles and describe the details to preserve or change in your own request.
Retain the task ID returned by the API to query status and retrieve completed file URLs. Use your online generation history to review earlier results and the creative direction you tested.
Use the documentation linked from each task for its exact model identifier, accepted inputs, authentication and response format. Integrate the same task you tested online so its media and settings match the request.
Nano Banana is Google’s image-generation and editing model available on Vidgo through two tasks. Text to Image creates a scene from a written prompt, and Image Editing combines a prompt with source images. Both use an optional size setting with ten aspect ratios and the current per-generation price.
Explore model introductions, API guides and platform comparisons to understand input preparation, request integration and cost planning for your project.
