Generate Images
November 17, 2025 (November 16, 2026)
Table of contents
- Model Capabilities
- Content Moderation
- Request Headers
- Request Body
- Responses
- Model
- If
fifeUrlis missing - Examples
- Try It
Generate images using AI models Nano Banana 2 Lite / Gemini 3.1 Flash-Lite Image (Google Flow’s default since July 2026), Nano Banana 2.1, and Nano Banana Pro / Gemini 3 Pro Image from text prompts with optional reference images. Use any Google AI subscription or even free account for image generations.
This endpoint features dynamic concurrency management, allowing anywhere from 3 to 20 parallel generations depending on real-time capacity. Image generation typically completes within 10-20 seconds.
Model Capabilities
| Parameter | Nano Banana 2 Litenano-banana-2-lite (default) | Nano Banana 2.1nano-banana-2 | Nano Banana Pronano-banana-pro |
|---|---|---|---|
| T2I (text-to-image) | |||
| I2I (reference images) | |||
| Aspect ratios | 16:9, 4:3, 1:1, 3:4, 9:16, auto† | 16:9, 4:3, 1:1, 3:4, 9:16, auto† | 16:9, 4:3, 1:1, 3:4, 9:16, auto† |
| Default aspect ratio | 16:9 (T2I & I2I) | 16:9 (T2I) / auto (I2I) | 16:9 (T2I) / auto (I2I) |
count | |||
seed | |||
thinkingLevel | |||
| Subscription | all | all | all |
† auto is only valid in image-to-image mode (at least one reference_* provided) — the backend derives the aspect ratio from the first reference image. With multiple references the derived orientation is not guaranteed — individual images in the same batch may come back with different orientations, so pass an explicit ratio when you need a consistent output shape.
The nano-banana-2 model generates with Nano Banana 2.1.
Deprecated aliases, still accepted: nano-banana maps to nano-banana-2, and imagen-4 maps to nano-banana-2-lite (Google removed Imagen from Flow in July 2026).
Content Moderation
If your generation is moderated, retrying with the same prompt often succeeds on subsequent attempts — moderation decisions can vary between requests. Alternatively, switching between nano-banana-2-lite, nano-banana-2, and nano-banana-pro models may help, as each has different content-moderation behavior.
https://api.useapi.net/v1/google-flow/images
Request Headers
Authorization: Bearer {API token}
Content-Type: application/json
# Alternatively you can use multipart/form-data
# Content-Type: multipart/form-data
API tokenis required, see Setup useapi.net for details.
Request Body
{
"prompt": "A serene mountain landscape at sunset with vibrant colors",
"model": "nano-banana-2-lite",
"aspectRatio": "16:9",
"count": 4,
"seed": 123456
}
-
emailis optional. The email address of the Google Flow account to use.When only one account is configured, the API will automatically use that account.
With multiple accounts configured, omitting the email parameter triggers automatic load balancing based on image generation job statistics to select the healthiest account.
If reference images (
reference_1to_10) are provided, theemailparameter can be omitted—the API will automatically use the same account where the images were uploaded. promptis required, text description for image generation.modelis optional, the AI model to use for image generation (default:nano-banana-2-lite).
Supported values:nano-banana-2-lite,nano-banana-2,nano-banana-pro. Deprecated aliases are still accepted:nano-bananamaps tonano-banana-2, andimagen-4maps tonano-banana-2-lite(Google removed Imagen from Flow in July 2026).aspectRatiois optional, output image aspect ratio. Supported values:16:9,4:3,1:1,3:4,9:16,auto. Legacy aliaseslandscape(→16:9) andportrait(→9:16) are still accepted.autois only valid when at least onereference_*is provided — the backend derives the aspect ratio from the first reference image. With 2+ references the derived orientation can vary between images in the same batch, so prefer an explicit ratio for consistent output. Default:- text-to-image (no references):
16:9 nano-banana-2-liteimage-to-image:16:9nano-banana-2/nano-banana-proimage-to-image:auto
- text-to-image (no references):
countis optional, number of image variations to generate (1-4, default:4).seedis optional, random seed for reproducible results (integer ≥ 0).thinkingLevelis optional, how long Nano Banana 2.1 reasons before it draws, the same as Flow’s Thinking level switch (nano-banana-2only).
Supported values:low,medium,high(default:high).
Higher levels follow complex prompts more closely, such as exact text, counts, times on a clock or labelled diagrams, and take longer. In Flow, one image took about 11 s onlow, 14 s onmediumand 21 s onhigh. Uselowfor quick drafts.lowandmediumneed a paid Google AI plan, because Flow offers a free accounthighonly, so a free account answers400for them before any captcha is used. Any other model answers400whenthinkingLevelis set.reference_1toreference_10are optional, usemediaGenerationIdfrom POST /assets/emailfor reference images. All models support up to 10 references.character_1tocharacter_7are optional, character reference-ids from POST /characters. Characters mix freely withreference_*— they share the same per-model image-ref budget on Google’s side (per-character image counts roll into the total).replyUrlis optional, webhook URL for job status callbacks. Receives POST requests with job status updates (created,completed,failed). The JSON payload shape matches GET /jobs/jobIdresponse. Callbacks timeout after 5 seconds.replyRefis optional, custom reference string passed back in webhook callbacks. Useful for tracking jobs on your end.captchaToken,captchaRetry,captchaOrderare optional, mutually exclusive captcha parameters. See Captcha Parameters for details.
When model is not specified the API uses nano-banana-2-lite — it handles both text-to-image and reference-to-image, so the right variant is picked automatically from the presence of reference_* / character_* parameters.
Inline @-mention markers (optional)
You can place @-markers inside prompt that resolve to the body parameters you supply. Markers are case-insensitive and opt-in — a prompt with no markers behaves exactly like before.
Supported markers:
| Marker | Resolves to |
|---|---|
@character_1..7 | matching character_N body param |
@reference_1..10 | matching reference_N body param |
Rules:
- Each marker MUST have a matching body slot supplied. Otherwise the API returns 400 with
'character_N' was not provided in the request body. - A slot referenced inline still goes into the upstream reference array — markers are positional/grounding info, not a replacement for the body params.
- Same slot may be inlined multiple times; the upstream reference array de-duplicates by id.
- Body params supplied but NOT inlined still flow to the upstream reference array (unchanged behavior).
- Unknown strings like
@gmail.comor@anyword_1(no_<digit>after a recognized slot name) pass through as literal prompt text.
Example:
{
"model": "nano-banana-pro",
"prompt": "@character_1 standing next to @reference_1, golden hour light",
"character_1": "user:123-email:...-character:...-imgs:1",
"reference_1": "user:123-email:...-image:..."
}
Responses
-
Images generated successfully. Returns job ID and media array with generated image data.
{ "jobId": "j1117123545678193846i-u12345-email:john@gmail.com-bot:google-flow", "media": [ { "name": "…redacted…", "workflowId": "…redacted…", "image": { "generatedImage": { "seed": 123456, "mediaGenerationId": "user:12345…redacted…", "mediaVisibility": "", "prompt": "A serene mountain landscape at sunset with vibrant colors", "modelNameType": "HARBOR_SEAL", "workflowId": "…redacted…", "fifeUrl": "https://flow-content.google/image/…redacted…?Expires=…&KeyName=labs-flow-prod-cdn-key&Signature=…", "aspectRatio": "IMAGE_ASPECT_RATIO_LANDSCAPE", "requestData": { "promptInputs": [ { "textInput": "A serene mountain landscape at sunset with vibrant colors" } ], "imageGenerationRequestData": { "backend": "flow", "referencesApplied": { "media": [], "entities": [] }, "aspectEnum": 3, "modelEnum": 31 } } }, "dimensions": { "width": 1376, "height": 768 } } } ], "captcha": { "service": "AntiCaptcha", "taskId": "540913782", "durationMs": 3500, "attempts": [ { "service": "AntiCaptcha", "taskId": "540913782", "durationMs": 3500, "success": true } ] } } -
Invalid request (validation error, reference count exceeded, email mismatch, or content policy violation).
General error:
{ "error": "Parameter prompt is required", "code": 400 }Content policy error:
{ "jobId": "j1117123545678193846i-u12345-email:john@gmail.com-bot:google-flow", "error": "PUBLIC_ERROR_UNSAFE_GENERATION (HTTP 400)", "code": 400, "response": { "error": { "code": 400, "message": "flow.google.com ogiZ0b failed", "status": "INVALID_ARGUMENT", "details": [ { "@type": "type.googleapis.com/google.rpc.ErrorInfo", "reason": "PUBLIC_ERROR_UNSAFE_GENERATION" } ] }, "captcha": { "service": "CapSolver", "taskId": "14af1dbb-885c-4e25-8121-7a79489dfd0e", "durationMs": 3500, "attempts": [ { "service": "CapSolver", "success": true, "durationMs": 3500, "taskId": "14af1dbb-885c-4e25-8121-7a79489dfd0e" } ] } } } -
Invalid API token.
{ "error": "useapi.net ⁝ Unauthorized", "code": 401 } -
Subscription expired or insufficient credits.
{ "error": "useapi.net ⁝ Your account has no subscription, please subscribe to our services before submitting requests", "code": 402 } -
Google rejected the captcha on every try. We retry with a fresh captcha as many times as you allow (
captchaRetry, default 5, or the providers incaptchaOrder) and return this403only when all of them were rejected. The top-levelerrorstarts withcaptcha_quality:, for example"captcha_quality: PUBLIC_ERROR_UNUSUAL_ACTIVITY after 5 attempts. Google refused all 5 captcha tokens for user@example.com, so nothing was generated and no Google Flow credits were used (5 captcha solves were spent). Google is flagging this account's requests as unusual activity. If it keeps happening, use another account, or leave out email so the API picks one. See GET /accounts/captcha-stats summary.by_account". A429withPUBLIC_ERROR_UNUSUAL_ACTIVITY_TOO_MUCH_TRAFFICreads the same way.Two
403s are not a captcha problem, and we answer them after one try instead of retrying.PUBLIC_ERROR_MODEL_ACCESS_DENIEDin the response means Google refused the model on that account, so raisingcaptchaRetryor adding providers will not help. Check that the account’s plan includes the model. Since 2026-09-23 Google no longer offersveo-3.1-lite-low-priorityto invited members of an Ultra $199 family plan — only the family manager’s account keeps it.PUBLIC_ERROR_USER_MINORmeans Google treats the Google account as belonging to someone under 18, and Google Flow is not available to such accounts. Theerrorsays so in plain words. No captcha or retry changes it: use another Google account, or have this one’s age verified with Google first. Withemailomitted, the load balancer sets such an account aside for 1 hour, then tries it again.Nothing was created when this happens. Google checks the captcha before it starts generating, so no Google credits were used and you can resubmit straight away. Your captcha provider still bills each solve.
The usual cause is the Google account, not the captcha provider. Google gives each account its own trust level. On a trusted account it accepts about 9 in 10 captchas, on a distrusted one about 3 in 10, whichever provider solved them. Most customers have a few distrusted accounts among many good ones.
To see which accounts are affected, use GET /accounts/captcha-stats. Its
summary.by_accountshows, for each of your Google accounts, how many captchas were tried and what share Google accepted. GET account/stats withbot=google-flowalso shows how many requests each account finished with each response code.- If one or a few accounts are far below the others, the API already sends them less work: when you leave out
email, each captcha Google rejected on an account in the last 15 minutes lowers its chance of being picked, for generations and for image uploads. They still get some work, so an account that recovers gets its full share back. If you pin requests withemail, move them to your other accounts yourself. Replace an account that stays low for more than a day or two. - If all your accounts drop at the same time, it’s the captcha provider. Configure at least two providers with POST /accounts/captcha-providers, and the API will start with whichever one Google accepts best.
A higher
captchaRetrygets more requests through on a distrusted account, but every extra try is another paid solve. - If one or a few accounts are far below the others, the API already sends them less work: when you leave out
-
Account not found or not configured.
{ "error": "Google Flow account john@gmail.com not found", "code": 404 } -
Google returns several
RESOURCE_EXHAUSTED429 variants. Check thereasonfield and respond accordingly:Reason Meaning Scope What to do Cooldown PUBLIC_ERROR_USER_REQUESTS_THROTTLEDGoogle is throttling the account (the token was fine). Uploads and generation are metered separately All models on the account — or uploads only, when POST /assets triggered it Run fewer parallel requests, or switch accounts. From POST /assets, retrying the same one rarely clears it ~30 min. From POST /assets, treat it as a minimum — it can persist PUBLIC_ERROR_USER_QUOTA_REACHEDAccount’s overall Flow quota cap All models on the account Add accounts, or omit emailto load-balance~30 min PUBLIC_ERROR_PER_MODEL_DAILY_QUOTA_REACHEDPer-model daily quota Only that model, on that account Switch model, or wait Next UTC midnight PUBLIC_ERROR_UNUSUAL_ACTIVITY_TOO_MUCH_TRAFFICGoogle rejected the captcha on every try (we already retried). Usually a distrusted Google account, sometimes the provider Per request Check which accounts are affected in captcha-stats. Rest or replace those accounts. Add a second provider if all accounts drop together 60s Every
429returns the cooldown two ways — an HTTPRetry-After: <seconds>header and a bodyretryAfter: <ISO timestamp>field. Honor it before retrying.When
emailis omitted, the first three reasons quarantine the account and the load balancer routes around it. If every account is quarantined for the model you get429witherror: "no_eligible_account". Routing details: GET /jobs › Load Balancing Algorithm.Captcha-quality failures prefix the top-level
errorwithcaptcha_quality:(e.g."captcha_quality: PUBLIC_ERROR_UNUSUAL_ACTIVITY_TOO_MUCH_TRAFFIC after 3 attempts") so you can detect them without parsing the nested body. -
One or more generated images were moderated by Google’s content policy. Try one of the following:
- Switch to a different model —
nano-banana-2-lite,nano-banana-2, andnano-banana-proeach have different content-moderation behavior - Modify your prompt or remove/change reference images
- Retry the same request (moderation decisions can vary between attempts)
{ "jobId": "j1117123545678193846i-u12345-email:john@gmail.com-bot:google-flow", "error": "API error: 500", "code": 500, "response": { "error": { "code": 500, "message": "flow.google.com ogiZ0b failed", "status": "INTERNAL", "details": [] }, "captcha": { "service": "CapSolver", "taskId": "14af1dbb-885c-4e25-8121-7a79489dfd0e", "durationMs": 3500, "attempts": [ { "service": "CapSolver", "success": true, "durationMs": 3500, "taskId": "14af1dbb-885c-4e25-8121-7a79489dfd0e" } ] } } } - Switch to a different model —
-
503has two distinct causes — check the response body to tell them apart.A transient Google-side outage. Wait 5-10 seconds and retry.
{ "error": { "code": 503, "message": "Service temporarily unavailable.", "status": "UNAVAILABLE" } }A captcha-provider failure — the top-level
erroris prefixedCaptcha service failed:. The problem is your captcha provider (check its API key and balance), not Google. Don’t retry until the provider is back.{ "error": "Captcha service failed: ERROR_ZERO_BALANCE", "code": 503 } -
596 Session Error
Google rejected the account’s session, and the API is re-verifying the account on its own: retry in about a minute. If Google signed the account out, the account keeps answering
596and you get a reconnect email: add it again by following Setup Google Flow.{ "error": "Google Flow account john@gmail.com Google rejected this account session (HTTP 401). We are automatically re-verifying it — please retry in about a minute. If the account was signed out, you will receive a reconnect email.", "code": 596 }
Model
The images made, each with a signed link and its mediaGenerationId, and the captcha used.
The images, field by field, and the type it uses (FlowCaptcha)
jobId- Unique job identifier (for use with GET /jobs/jobId)media- Array of generated images (1-4 images based oncount)media[].image.generatedImage- Generated image data objectgeneratedImage.fifeUrl- Direct signed URL to access the generated image (valid for ~6 hours). An empty string when Google’s answer had no URL, see belowgeneratedImage.seed- Seed used for this generation (for reproducibility)generatedImage.mediaGenerationId- mediaGenerationId for use in subsequent API callsgeneratedImage.prompt- The prompt used for generationgeneratedImage.modelNameType- Model variant used (HARBOR_SEAL,GEM_PIX_2,BELUGA,NARWHAL).BELUGAis Nano Banana 2.1.generatedImage.aspectRatio- Generated image aspect ratio (IMAGE_ASPECT_RATIO_LANDSCAPE,IMAGE_ASPECT_RATIO_LANDSCAPE_FOUR_THREE,IMAGE_ASPECT_RATIO_SQUARE,IMAGE_ASPECT_RATIO_PORTRAIT_THREE_FOUR,IMAGE_ASPECT_RATIO_PORTRAIT, orIMAGE_ASPECT_RATIO_UNSPECIFIEDforauto)generatedImage.mediaVisibility- Always an empty string (Google Flow does not report it for images)generatedImage.workflowId- Unique workflow identifiergeneratedImage.requestData- What the image was made from: the prompt, and the references Google appliedmedia[].image.dimensions- The image’s width and height in pixelsmedia[].name- Internal identifier for the media itemmedia[].workflowId- Unique workflow identifier for this generationcaptcha- Captcha metadata for debugging/researchcaptcha.service- Provider that returned the successful tokencaptcha.taskId- Task ID from the captcha servicecaptcha.durationMs- Total time for all captcha attemptscaptcha.attempts- Array of all captcha attempts (including failures)
{
jobId: string // Job identifier
media: Array<{ // the images made, up to count
name: string // Internal media identifier
workflowId: string // Unique workflow ID (an empty string when Google reports none)
image: { // the generated image
generatedImage: { // the image file and how it was made
seed: number // the seed Google used
mediaGenerationId: string // Format: user:{userid}-email:{hex}-image:{id}
mediaVisibility: '' // always an empty string
prompt: string // the prompt as Google ran it
modelNameType: string // HARBOR_SEAL, GEM_PIX_2, BELUGA or NARWHAL
workflowId: string // same as media[].workflowId
fifeUrl: string // Direct signed URL to the generated image, valid ~6 hours. An empty string when Google's answer had none
aspectRatio: string // IMAGE_ASPECT_RATIO_LANDSCAPE, IMAGE_ASPECT_RATIO_LANDSCAPE_FOUR_THREE, IMAGE_ASPECT_RATIO_SQUARE, IMAGE_ASPECT_RATIO_PORTRAIT_THREE_FOUR, IMAGE_ASPECT_RATIO_PORTRAIT or IMAGE_ASPECT_RATIO_UNSPECIFIED (auto)
requestData: { // what the image was made from
promptInputs: Array<{ // the prompt sent to Google
textInput: string // the prompt text
}>
imageGenerationRequestData: { // what Google applied
backend: 'flow' // the image was made on `flow.google.com`
referencesApplied: { // the references Google echoed back as applied
media: string[] // Google's media ids of the reference images applied
entities: string[] // the entity ids of the characters applied
}
aspectEnum: number | null // Google's raw aspect number (3 landscape, 1 square, 2 portrait, 4 3:4, 5 4:3, 0 auto)
modelEnum: number | null // Google's raw model number (25 GEM_PIX_2, 29 NARWHAL, 31 HARBOR_SEAL, 36-39 BELUGA)
}
}
}
dimensions?: { // the image's size, when Google reports it
width: number // width in pixels
height: number // height in pixels
}
}
}>
captcha: FlowCaptcha // the captcha solved for this request (described below)
}
When the request fails:
{
jobId?: string // the job id, when the request got as far as Google
error: string // what went wrong, e.g. "PUBLIC_ERROR_UNSAFE_GENERATION (HTTP 400)" or "No images generated"
code?: number // the HTTP status (left out on "No images generated", a 500)
retryAfter?: string // ISO 8601 time to retry after, on a 429 (the Retry-After header carries the same in seconds)
response?: { // Google's answer, when Google or the captcha refused the request
error?: { // Google's error
code: number // HTTP status Google answered
message: string // the error message, e.g. "flow.google.com ogiZ0b failed"
status: string // Google's status name, e.g. "RESOURCE_EXHAUSTED"
details: Array<{ // Google's error details
'@type': string // the type name of the detail
reason: string // Google's reason code, e.g. "PUBLIC_ERROR_USER_QUOTA_REACHED"
}>
}
captcha: FlowCaptcha // the captcha tried or used
}
captcha?: FlowCaptcha // on "No images generated" only: the captcha used
message?: string // on the load-balancer 429 only (error no_eligible_account: every account is quarantined for this model): the explanation
skipReasons?: Array<{ // on the load-balancer 429 only: why each account was left out
email: string // the account left out
reason: string // Google reason that triggered the quarantine (a 429 reason, or the MODEL_ACCESS_DENIED or USER_MINOR 403)
model: string // Quarantined model, or "*" for account-wide
}>
}
The type used above:
FlowCaptcha: the captcha in the answer above.
{
service?: string // the provider whose token Google accepted: `CapSolver`, `AntiCaptcha`,
// `YesCaptcha`, `CapMonster`, `SolveCaptcha`, `2Captcha`, `EzCaptcha` or
// `UserProvided`. Always on a success answer
taskId?: string // that provider's task id (none for `UserProvided`)
durationMs?: number // ms from the first solve to the token used. Always on a success answer
error?: string // why no captcha token could be had, on a failed request
attempts: Array<{ // every solve tried, in order, failed ones included
service: string // the provider asked
taskId?: string // that provider's task id
durationMs: number // how long this solve took, in ms
success: boolean // true when the provider returned a token (Google may still have refused it)
error?: string // why the solve failed
userAgent?: string // the browser user agent the provider solved with, when it reports one
secChUa?: string // the Sec-CH-UA value the provider solved with, when it reports one (may be empty)
cost?: string // the provider's price for this solve, as the provider reports it
ip?: string // the IP address the provider reports for this solve
createTime?: number // Unix time the provider started the solve, as it reports it
endTime?: number // Unix time the provider finished the solve, as it reports it
solveCount?: number // the provider's own solve counter for this task
}>
}
If fifeUrl is missing
Once in a while Google’s generation response comes back without a URL for an image, and fifeUrl is then an empty string. The image itself is unaffected and no credits are lost.
Ask for its URL with GET /assets/mediaGenerationId, which answers { url, mediaGenerationId }. Every example below already does this, in all three languages.
Examples
-
curl -X POST \ -H "Authorization: Bearer YOUR_API_TOKEN" \ -H "Content-Type: application/json" \ -d '{ "prompt": "A serene mountain landscape at sunset with vibrant colors", "model": "nano-banana-2-lite", "aspectRatio": "16:9", "count": 4, "seed": 123456 }' \ "https://api.useapi.net/v1/google-flow/images" > response.json # Download each image. fifeUrl is normally set; when it is empty, ask # GET /assets/{mediaGenerationId} for the image's URL. for i in 0 1; do IMG=$(jq -r ".media[$i].image.generatedImage" response.json) URL=$(echo "$IMG" | jq -r '.fifeUrl // empty') if [ -z "$URL" ]; then ID=$(echo "$IMG" | jq -r '.mediaGenerationId | @uri') URL=$(curl -s -H "Authorization: Bearer YOUR_API_TOKEN" \ "https://api.useapi.net/v1/google-flow/assets/$ID" | jq -r '.url') fi curl -o "image_$((i+1)).jpg" "$URL" done # Continue for remaining images... -
const token = 'YOUR_API_TOKEN'; const apiUrl = 'https://api.useapi.net/v1/google-flow/images'; const response = await fetch(apiUrl, { method: 'POST', headers: { 'Authorization': `Bearer ${token}`, 'Content-Type': 'application/json' }, body: JSON.stringify({ prompt: 'A serene mountain landscape at sunset with vibrant colors', model: 'nano-banana-2-lite', aspectRatio: '16:9', count: 4, seed: 123456 }) }); const result = await response.json(); console.log('Generated images:', result.media.length); // Download and save images for (const [index, item] of result.media.entries()) { const img = item.image.generatedImage; console.log(`Image ${index + 1} seed:`, img.seed); console.log(`mediaGenerationId:`, img.mediaGenerationId); // fifeUrl is normally set. When it is empty, ask GET /assets/{mediaGenerationId} // for the image's URL. const imageUrl = img.fifeUrl || (await (await fetch( `https://api.useapi.net/v1/google-flow/assets/${encodeURIComponent(img.mediaGenerationId)}`, { headers: { 'Authorization': `Bearer ${token}` } })).json()).url; const imageBlob = await (await fetch(imageUrl)).blob(); // In Node.js with fs: // const buffer = Buffer.from(await imageBlob.arrayBuffer()); // require('fs').writeFileSync(`generated_image_${index + 1}.jpg`, buffer); // In browser: create download link or display in <img> element // const url = URL.createObjectURL(imageBlob); // document.querySelector('img').src = url; } -
import requests from urllib.parse import quote token = 'YOUR_API_TOKEN' api_url = 'https://api.useapi.net/v1/google-flow/images' headers = { 'Authorization': f'Bearer {token}', 'Content-Type': 'application/json' } data = { 'prompt': 'A serene mountain landscape at sunset with vibrant colors', 'model': 'nano-banana-2-lite', 'aspectRatio': '16:9', 'count': 4, 'seed': 123456 } response = requests.post(api_url, headers=headers, json=data) result = response.json() print(f"Generated {len(result['media'])} images") # Download and save images for index, item in enumerate(result['media']): img = item['image']['generatedImage'] print(f"Image {index + 1} seed:", img['seed']) print(f"mediaGenerationId:", img['mediaGenerationId']) # fifeUrl is normally set. When it is empty, ask GET /assets/{mediaGenerationId} # for the image's URL. image_url = img.get('fifeUrl') or requests.get( 'https://api.useapi.net/v1/google-flow/assets/' + quote(img['mediaGenerationId'], safe=''), headers={'Authorization': f'Bearer {token}'}).json()['url'] image_response = requests.get(image_url) with open(f'generated_image_{index + 1}.jpg', 'wb') as f: f.write(image_response.content)