Nano Banana Pro uses Google’s Gemini 3 Pro image model for text generation and reference-image editing on Vidgo. Describe the subject, lighting, composition and exact wording for a new image, or supply one to five references and identify the material, object or scene details to modify. Select 1K, 2K or 4K and a supported aspect ratio, with one image per request in the current task. Use these controls for photographic concepts, lettering, material studies and local image changes, then review the current generation tier before submitting.
Nano Banana Pro is developed by Google. Vidgo provides access to the model. Model names and trademarks belong to their respective owners.Choose Text to Image when the image begins with a written brief. Choose Image Editing for one to five references that supply the person, object or environment to retain. Describe the change and preserved details, select resolution and framing and inspect the full task estimate.
Google's Nano Banana Pro image model powered by Gemini 3 Pro for 4K generation, strong text rendering, multi-image blending, and production-ready image editing.
Google's Nano Banana Pro image model powered by Gemini 3 Pro for 4K generation, strong text rendering, multi-image blending, and production-ready image editing.
The text and editing tasks both use prompt, resolution and optional size, with n fixed at one in the current workflow. Editing also accepts image_urls. Identify the subject, materials and lighting that define the scene, then state the specific surfaces, objects or environmental details to change.
| Model / task | Input and workflow |
|---|---|
| Nano Banana Pro Text-to-Image | Google's Nano Banana Pro image model powered by Gemini 3 Pro for 4K generation, strong text rendering, multi-image blending, and production-ready image editing. |
| Nano Banana Pro Image Edit | Google's Nano Banana Pro image model powered by Gemini 3 Pro for 4K generation, strong text rendering, multi-image blending, and production-ready image editing. |
Write concrete instructions for text, light and materials and identify the source details to preserve. The examples below include a lettered ceramic mug, a fisherman’s hands and a pottery-studio photograph with selected clothing, object and lighting changes.
Write the exact words, type treatment, surface and camera. The existing mug example requests GOOD MORNING on ceramic with window light and steam. Inspect the actual letter shapes, placement and relationship to the material before choosing the image for a visual presentation.
Name the person’s activity, focal detail and environment. The existing fisherman example asks for net-mending hands in focus and a softly receding harbor at dawn. Inspect hand structure, net texture and lighting relationships when developing a photographic concept.
Provide the source photograph and list the face, hair, expression, hands, clothing and equipment to retain. The pottery-studio source establishes the artist, bowl and workbench before the prompt directs the local changes.
Describe the exact modifications and the remaining scene. The Vidgo pottery example changes the apron to indigo linen, places a fern on the rear stool and warms the window light while retaining the artist and workshop. Compare the result with the source for all three requested changes.
Select 1K, 2K or 4K and the supported size ratio suited to the composition. Review the full generation estimate, then inspect the completed image at its intended placement for material detail, lettering and layout.
The first image comes from an existing public example of the same model and its original ceramic-mug prompt. The second is the Vidgo task’s pottery-studio demonstration, using one photograph and a prompt for the apron, fern and warmer light. Read the complete prompts and compare the studio source with the displayed result to inspect retained identity, hands, pottery and the requested local changes.
A hyperrealistic product photo of a matte ceramic coffee mug on a wooden table, morning light streaming through a window casting soft shadows, steam rising from the cup with the text 'GOOD MORNING' embossed on the side in a clean serif font, shallow depth of field, 85mm lens
Edit this documentary pottery-studio photograph while preserving the artist exactly. Change only the charcoal apron to a muted indigo linen apron, add one small leafy potted fern on the empty stool in the back right, and warm the existing window light to gentle late-afternoon sunlight. Preserve the woman's face, identity, hair, expression, pose, both hands, clay bowl, camera angle, crop, shelves, pottery, workbench, and all object positions. Keep it natural and photorealistic, with no text or advertising.
Describe a new photographic scene, visible lettering and material detail, or prepare references for a local wardrobe, object, lighting or environment change. State the sources and preserved details, choose resolution and framing and inspect the single output for a visual proposal, character presentation, material study or integrated editing workflow.
Write the exact wording, type treatment and location, together with the subject and light. Review the actual lettering and surface interaction before selecting the image for a presentation.
Describe the person’s activity, hands, tools and environment and choose the framing. Inspect anatomy, texture and light for a photographic or storyboard proposal.
Provide the portrait or scene and identify the garment to modify. Preserve identity, pose and silhouette, then compare the new texture and color with the source for a wardrobe study.
Supply the image and describe the object’s location, scale and supporting contact. Review the result for spatial continuity and coordinated lighting before using it in a scene concept.
Identify the existing light sources and describe their new warmth, direction or intensity while retaining scene geometry. Compare the edit with the source for a visual direction proposal.
Retain the selected model, prompt, reference URLs, resolution and size. Submit the authenticated API request and track its task ID to retrieve the completed image.
Nano Banana Pro is billed per generation, with the current catalog using one tier for 1K/2K and a separate tier for 4K. The dynamic table shows the lowest current rate for each task. The current workflow requests one output image. Open the selected task with the intended resolution and references to review the full estimate before submitting.
| Model | Provider | Workflow | Input material | Output specification | Starting rate |
|---|---|---|---|---|---|
| Nano Banana Pro Text-to-Image | Text to Image | Text prompt | 4K | $0.04 / generation | |
| Nano Banana Pro Image Edit | Image Editing | 1–5 reference images | 4K | $0.04 / generation |
Test your creative brief online, then bring the verified request into your application.
Enter the prompt and upload the editing references as JPEG, PNG or WebP files within 10 MiB each. Choose the resolution and framing, review the one-image generation estimate and create the result. Compare identity, hands, material, objects and light with the brief and source photographs.
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 composition or Image Editing for one to five references. Describe the desired result and details to preserve, then choose 1K, 2K or 4K and a supported size ratio. Keep the current request’s output count at one.
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 1K/2K or 4K generation tier and its complete one-image estimate. Use that request cost and the planned number of tests when budgeting text generation and reference editing.
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 Pro is Google’s Gemini 3 Pro image model available through text generation and image editing on Vidgo. The tasks support 1K, 2K and 4K, ten aspect ratios and editing with one to five references. The current workflow requests one image and uses the catalog’s per-generation resolution tiers.
Explore model introductions, API guides and platform comparisons to understand input preparation, request integration and cost planning for your project.
