google/nano-banana/text-to-imageNano Banana Text to Image transforms text prompts into high-fidelity visuals with legible typography and 10 versatile aspect ratios. It accurately maps complex spatial prompts while delivering naturally balanced lighting.
Get API Key
Extreme close-up photograph of a clockmaker's hands assembling a brass gear train under a warm bench lamp. Fine steel tweezers hold one small gear so its teeth mesh cleanly with the neighboring wheel; the rest of the train sits in an open wooden movement frame. Accurate mechanical contact, visible tool steel, brass wear, a drop of oil on a pivot, wood grain, shallow depth of field and workshop bokeh. Show only the hands and the mechanism, no face, no text, no logos, no watermarks.
Photorealistic documentary photograph of a train-station lost-and-found glass window in late afternoon. Two centered lines of white painted capital letters on the glass: the first line is exactly LOST and the second line is exactly FOUND. No ampersand, no extra letters, no other words on the glass. A small paper card taped inside the lower right corner shows only the time 8:00-18:00. Behind the glass, on one wooden shelf: a brass tuba lying on its side, a folded red umbrella, and a pair of white ice skates. Soft concourse reflections, warm side light, realistic glass and wood. No advertisements, brands, logos, signatures, or watermarks.
A behind-the-screen rehearsal photograph of a traditional shadow-puppet stage. In the foreground, two adult puppeteers hold a deer puppet and a boat puppet against a taut rice-paper screen; an oil lamp throws sharp silhouettes of the deer and the boat onto the paper. The carved leather puppets and the puppeteers' hands stay visible on the lamp side, while the silhouettes read clearly on the screen. Warm amber practical light, layered space, empty room, no audience. No text, no logos, no watermarks.
REST API
This flow submits one valid Nano Banana Text to Image request, captures its task_id, and reads image URLs after the asynchronous task ends.
Create an API key, keep it on the server, and send it as Authorization: Bearer VIDGO_API_KEY.
https://api.vidgo.ai/api/generate/submitSend the current model ID, prompt to the unified submit endpoint. The example keeps only first-call fields.
curl --request POST \
--url "https://api.vidgo.ai/api/generate/submit" \
--header "Authorization: Bearer $VIDGO_API_KEY" \
--header "Content-Type: application/json" \
--data '{
"model": "google/nano-banana/text-to-image",
"input": {
"prompt": "Extreme close-up photograph of a clockmaker's hands assembling a brass gear train under a warm bench lamp. Fine steel tweezers hold one small gear so its teeth mesh cleanly with the neighboring wheel; the rest of the train sits in an open wooden movement frame. Accurate mechanical contact, visible tool steel, brass wear, a drop of oil on a pivot, wood grain, shallow depth of field and workshop bokeh. Show only the hands and the mechanism, no face, no text, no logos, no watermarks.",
"size": "3:2"
}
}'Read data.task_id and poll only while status is not_started or running. Stop on both finished and failed.
GET https://api.vidgo.ai/api/generate/status/{task_id}Poll every 2–5 seconds and back off on 429/5xx. Or provide top-level callback_url to receive a terminal-state callback.
not_startedrunningfinishedfailed{
"code": 200,
"data": {
"task_id": "KG06ZZCMOWHJ6CM0",
"status": "running",
"created_time": "2026-09-26T10:31:54"
}
}{
"code": 200,
"data": {
"task_id": "KG06ZZCMOWHJ6CM0",
"status": "finished",
"files": [
{
"file_type": "image",
"file_url": "https://cdn.vidgo.ai/apis/models/google/nano-banana-2/text-to-image/v1/02/output.jpg"
}
],
"created_time": "2026-09-26T10:31:54",
"error_message": null,
"progress": 100
}
}Expand for the same payload end to end, including business-code, missing-task-ID, failed-state, unexpected-state, and network-error handling.
set -euo pipefail
: "${VIDGO_API_KEY:?Set VIDGO_API_KEY in your environment}"
REQUEST_BODY=$(cat <<'JSON'
{
"model": "google/nano-banana/text-to-image",
"input": {
"prompt": "Extreme close-up photograph of a clockmaker's hands assembling a brass gear train under a warm bench lamp. Fine steel tweezers hold one small gear so its teeth mesh cleanly with the neighboring wheel; the rest of the train sits in an open wooden movement frame. Accurate mechanical contact, visible tool steel, brass wear, a drop of oil on a pivot, wood grain, shallow depth of field and workshop bokeh. Show only the hands and the mechanism, no face, no text, no logos, no watermarks.",
"size": "3:2"
}
}
JSON
)
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
--request POST \
--url "https://api.vidgo.ai/api/generate/submit" \
--header "Authorization: Bearer $VIDGO_API_KEY" \
--header "Content-Type: application/json" \
--data "$REQUEST_BODY")
TASK_ID=$(printf '%s' "$SUBMIT_RESPONSE" | jq -r '.data.task_id // .task_id // empty')
if [ -z "$TASK_ID" ]; then
printf 'Submit response did not include task_id:
%s
' "$SUBMIT_RESPONSE" >&2
exit 1
fi
while true; do
STATUS_RESPONSE=$(curl --silent --show-error --fail-with-body \
--url "https://api.vidgo.ai/api/generate/status/$TASK_ID" \
--header "Authorization: Bearer $VIDGO_API_KEY")
STATUS=$(printf '%s' "$STATUS_RESPONSE" | jq -r '.data.status // .status // empty')
case "$STATUS" in
finished)
printf '%s' "$STATUS_RESPONSE" | jq -r '(.data.files // .files // [])[]?.file_url'
break
;;
failed)
printf '%s' "$STATUS_RESPONSE" | jq -r '.data.error_message // .error_message // "Generation failed"' >&2
exit 1
;;
not_started|running)
sleep 2
;;
*)
printf 'Unexpected task status: %s
' "$STATUS" >&2
exit 1
;;
esac
doneThis table lists only public fields inside input. See Quick Start for top-level model and optional callback_url usage.
| Field | Type | Required | Default | Description |
|---|---|---|---|---|
| input.prompt | string | Yes | – | Describe the image to generate using 1–5,000 characters, including at least one non-whitespace character. |
| input.size | string | No | – | Output image aspect ratio. Select auto to let the model choose the framing; the API request then omits size. |
The submit response identifies the task. The status response supplies image files or failure details at a terminal state.
| Field | Type | Description |
|---|---|---|
| code | integer | Business response code; 0 or 200 indicates success. |
| message | string | Optional human-readable response message. |
| data.task_id | string | Unique task ID used for status queries after submission. |
| data.status | string | not_started, running, finished, or failed. |
| data.created_time | string | Task creation timestamp. |
| data.progress | integer | Progress from 0–100 in status responses. |
| data.files[] | array | Generated files in returned order when finished. |
| data.files[].file_url | string | Direct generated-image URL. |
| data.files[].file_type | string | Image results are identified as image. |
| data.files[].watermark_url | string | null | Optional watermarked-file URL when present. |
| data.error_message | string | null | Readable failure reason for failed tasks. |
Only the first two states may be polled again. finished and failed are terminal.
not_startedAccepted and queued; wait before checking again.
runningImage generation is in progress; continue polling.
finishedSuccessful terminal state; validate files and read image URLs.
failedFailure terminal state; read error_message and stop.
| Specification | Value | Details |
|---|---|---|
| Input mode | Prompt only | The prompt is the complete creative source. |
| Prompt length | 1–5,000 | Counted in characters after trimming leading and trailing whitespace. |
| Output | Image | Returns image files asynchronously. |
| Aspect ratio | 10 ratios | Supports 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9. |
| Billing | Each generation costs 5 credits ($0.025). 1 credit = $0.005. | 1 credit = $0.005; the backend remains authoritative for final billing. |
Nano Banana Text to Image is a Google DeepMind model for generating high-fidelity images from natural language text prompts. It produces high-resolution images with legible in-image typography rendering, deep real-world landmark understanding, and native support for 10 aspect ratios. Built on the Gemini 2.5 Flash Image multimodal architecture, it strictly follows complex spatial and lighting prompts while maintaining natural depth and balanced textures. You can call it programmatically or try it from the playground above.
Yes. The model is specifically optimized for visual text rendering across multiple languages, accurately placing legible short phrases on posters, street signs, and packaging. Wrapping requested text in straight double quotes (e.g., "SUMMER SALE") ensures the highest spelling accuracy and crisp letterforms.
Yes. Powered by Google's comprehensive world knowledge base, Nano Banana recognizes and accurately reconstructs recognizable landmarks such as the Eiffel Tower or Mount Fuji, ensuring structural authenticity without spatial distortions.
The model natively supports 10 aspect ratios: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, and 21:9. If you omit the size parameter or select auto, the model automatically selects an optimal framing format tailored to your prompt description.
The models serve complementary roles: Nano Banana (Gemini 2.5 Flash) emphasizes deep prompt fidelity, factual landmark precision, and balanced photorealism, whereas Nano Banana 2 Lite is engineered for maximum speed (~4s generation) in latency-sensitive interactive prototyping.
Each generation costs a fixed 5 credits ($0.025, with 1 credit = $0.005) regardless of the chosen aspect ratio. In the event of a system failure or rejected task, all charged credits are automatically refunded.
Follow the structured FRAME framework by detailing your main subject, rendering texture, camera angle, lighting setup, and typography. Using explicit descriptors such as "diffused studio rim lighting" yields superior clarity compared to generic aesthetic adjectives.
