Nano Banana Pro Text-to-Image API by Google
Nano Banana Pro is the next-generation Nano Banana image model, delivering sharper detail, richer color control, and faster diffusion for production-ready visuals.
程式碼範例
import requests
import time
# Step 1: Start image generation
generate_url = "https://api.atlascloud.ai/api/v1/model/generateImage"
headers = {
"Content-Type": "application/json",
"Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
"model": "google/nano-banana-pro/text-to-image",
"prompt": "A beautiful landscape with mountains and lake",
"width": 512,
"height": 512,
"steps": 20,
"guidance_scale": 7.5,
}
generate_response = requests.post(generate_url, headers=headers, json=data)
generate_result = generate_response.json()
prediction_id = generate_result["data"]["id"]
# Step 2: Poll for result
poll_url = f"https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}"
def check_status():
while True:
response = requests.get(poll_url, headers={"Authorization": "Bearer $ATLASCLOUD_API_KEY"})
result = response.json()
if result["data"]["status"] == "completed":
print("Generated image:", result["data"]["outputs"][0])
return result["data"]["outputs"][0]
elif result["data"]["status"] == "failed":
raise Exception(result["data"]["error"] or "Generation failed")
else:
# Still processing, wait 2 seconds
time.sleep(2)
image_url = check_status()安裝
為您的程式語言安裝所需的套件。
pip install requests驗證
所有 API 請求都需要透過 API 金鑰進行驗證。您可以從 Atlas Cloud 儀表板取得 API 金鑰。
export ATLASCLOUD_API_KEY="your-api-key-here"HTTP 標頭
import os
API_KEY = os.environ.get("ATLASCLOUD_API_KEY")
headers = {
"Content-Type": "application/json",
"Authorization": f"Bearer {API_KEY}"
}切勿在客戶端程式碼或公開儲存庫中暴露您的 API 金鑰。請改用環境變數或後端代理。
提交請求
import requests
url = "https://api.atlascloud.ai/api/v1/model/generateImage"
headers = {
"Content-Type": "application/json",
"Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
"model": "your-model",
"prompt": "A beautiful landscape"
}
response = requests.post(url, headers=headers, json=data)
print(response.json())提交請求
提交非同步生成請求。API 會傳回一個預測 ID，您可以用它來檢查狀態並取得結果。
/api/v1/model/generateImage請求主體
import requests
url = "https://api.atlascloud.ai/api/v1/model/generateImage"
headers = {
"Content-Type": "application/json",
"Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
"model": "google/nano-banana-pro/text-to-image",
"input": {
"prompt": "A beautiful landscape with mountains and lake"
}
}
response = requests.post(url, headers=headers, json=data)
result = response.json()
print(f"Prediction ID: {result['id']}")
print(f"Status: {result['status']}")回應
{
"id": "pred_abc123",
"status": "processing",
"model": "model-name",
"created_at": "2025-01-01T00:00:00Z"
}檢查狀態
輪詢預測端點以檢查請求的當前狀態。
/api/v1/model/prediction/{prediction_id}輪詢範例
import requests
import time
prediction_id = "pred_abc123"
url = f"https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}"
headers = { "Authorization": "Bearer $ATLASCLOUD_API_KEY" }
while True:
response = requests.get(url, headers=headers)
result = response.json()
status = result["data"]["status"]
print(f"Status: {status}")
if status in ["completed", "succeeded"]:
output_url = result["data"]["outputs"][0]
print(f"Output URL: {output_url}")
break
elif status == "failed":
print(f"Error: {result['data'].get('error', 'Unknown')}")
break
time.sleep(3)狀態值
processing請求仍在處理中。completed生成完成。輸出已可取得。succeeded生成成功。輸出已可取得。failed生成失敗。請檢查錯誤欄位。完成回應
{
"data": {
"id": "pred_abc123",
"status": "completed",
"outputs": [
"https://storage.atlascloud.ai/outputs/result.png"
],
"metrics": {
"predict_time": 8.3
},
"created_at": "2025-01-01T00:00:00Z",
"completed_at": "2025-01-01T00:00:10Z"
}
}上傳檔案
上傳檔案至 Atlas Cloud 儲存空間並取得 URL，可用於您的 API 請求。使用 multipart/form-data 上傳。
/api/v1/model/uploadMedia上傳範例
import requests
url = "https://api.atlascloud.ai/api/v1/model/uploadMedia"
headers = { "Authorization": "Bearer $ATLASCLOUD_API_KEY" }
with open("image.png", "rb") as f:
files = {"file": ("image.png", f, "image/png")}
response = requests.post(url, headers=headers, files=files)
result = response.json()
download_url = result["data"]["download_url"]
print(f"File URL: {download_url}")回應
{
"data": {
"download_url": "https://storage.atlascloud.ai/uploads/abc123/image.png",
"file_name": "image.png",
"content_type": "image/png",
"size": 1024000
}
}輸入 Schema
以下參數可在請求主體中使用。
無可用參數。
範例請求主體
{
"model": "google/nano-banana-pro/text-to-image"
}輸出 Schema
API 傳回包含生成輸出 URL 的預測回應。
範例回應
{
"id": "pred_abc123",
"status": "completed",
"model": "model-name",
"outputs": [
"https://storage.atlascloud.ai/outputs/result.png"
],
"metrics": {
"predict_time": 8.3
},
"created_at": "2025-01-01T00:00:00Z",
"completed_at": "2025-01-01T00:00:10Z"
}Atlas Cloud Skills
Atlas Cloud Skills 將 300 多個 AI 模型直接整合至您的 AI 程式碼助手。一鍵安裝，即可使用自然語言生成圖片、影片，以及與 LLM 對話。
支援的客戶端
安裝
npx skills add AtlasCloudAI/atlas-cloud-skills設定 API 金鑰
從 Atlas Cloud 儀表板取得 API 金鑰，並設為環境變數。
export ATLASCLOUD_API_KEY="your-api-key-here"功能
安裝完成後，您可以在 AI 助手中使用自然語言存取所有 Atlas Cloud 模型。
MCP Server
Atlas Cloud MCP Server 透過 Model Context Protocol 將您的 IDE 與 300 多個 AI 模型連接。支援任何 MCP 相容的客戶端。
支援的客戶端
安裝
npx -y atlascloud-mcp設定
將以下設定新增至您 IDE 的 MCP 設定檔中。
{
"mcpServers": {
"atlascloud": {
"command": "npx",
"args": [
"-y",
"atlascloud-mcp"
],
"env": {
"ATLASCLOUD_API_KEY": "your-api-key-here"
}
}
}
}可用工具
API Schema
Schema 不可用Nano Banana - Google 革命性視覺 AI
新功能又稱 Gemini 2.5 Flash Image
Google 最新的多模態 AI 技術突破，提供前所未有的圖像生成和編輯功能，具有閃電般的速度和卓越的品質。
- 多圖融合技術
- 跨生成的角色一致性
- 風格保留轉換
- 高達 4K 的高分辨率輸出
- 基於文本的智能編輯
- 對象添加和移除
- 背景替換
- 風格轉移和藝術效果
Prompt Examples & Templates
Explore curated prompt templates to unlock the full potential of Nano Banana AI. Click to copy any prompt and start creating immediately.
Photo to Character Figure
Transform any photo into a realistic character figure with packaging and displayturn this photo into a character figure. Behind it, place a box with the character's image printed on it, and a computer showing the Blender modeling process on its screen. In front of the box, add a round plastic base with the character figure standing on it. set the scene indoors if possible
Anime to Cosplay
Transform anime illustrations into realistic cosplay photographyGenerate a highly detailed photo of a girl cosplaying this illustration, at Comiket. Exactly replicate the same pose, body posture, hand gestures, facial expression, and camera framing as in the original illustration. Keep the same angle, perspective, and composition, without any deviation
Person to Action Figure
Transform people from photos into collectible action figures with custom packagingTransform the the person in the photo into an action figure, styled after [CHARACTER_NAME] from [SOURCE / CONTEXT]. Next to the figure, display the accessories including [ITEM_1], [ITEM_2], and [ITEM_3]. On the top of the toy box, write "[BOX_LABEL_TOP]", and underneath it, "[BOX_LABEL_BOTTOM]". Place the box in a [BACKGROUND_SETTING] environment. Visualize this in a highly realistic way with attention to fine details.
Person to Funko Pop Figure
Transform photos into Funko Pop style collectible figures with custom packagingTransform the person in the photo into the style of a Funko Pop figure packaging box, presented in an isometric perspective. Label the packaging with the title 'ZHOGUE'. Inside the box, showcase the figure based on the person in the photo, accompanied by their essential items (such as cosmetics, bags, or others). Next to the box, also display the actual figure itself outside of the packaging, rendered in a realistic and lifelike style.
Product Design to Photorealistic Render
Transform product design sketches into photorealistic rendersturn this illustration of a perfume into a realistic version, Frosted glass bottle with a marble cap
Transform to Q-Version Character
Create cartoon characters with face shape reference controlTransform the person from image 1 into a Q-version character design based on the face shape from image 2
Building to 3D Architecture Model
Convert architectural photos into detailed physical modelsconvert this photo into a architecture model. Behind the model, there should be a cardboard box with an image of the architecture from the photo on it. There should also be a computer, with the content on the computer screen showing the Blender modeling process of the figurine. In front of the cardboard box, place a cardstock and put the architecture model from the photo I provided on it. I hope the PVC material can be clearly presented. It would be even better if the background is indoors.
技術亮點
優化速度，大多數任務的生成時間不到 2 秒，非常適合實時應用和快速原型開發工作流。
利用 Google 先進的 AI 架構生成高度詳細、逼真的圖像，具有精確的照明、紋理和構圖。
革命性的 2D 到 3D 轉換功能，可從單個圖像創建多個視點，為內容創作開闢新可能性。
使用案例
為什麼選擇 Nano Banana？
無需設置
無需複雜配置或安裝即可立即開始創建精密控制
通過直觀的文本命令微調創作的每個方面一致的結果
在多代生成中保持角色和風格的一致性技術規格
體驗 Nano Banana AI 的力量
加入數千名已經使用 Google 最先進的圖像 AI 技術改變視覺內容的創意人和企業。
Nano Banana Pro : A state-of-the-art, multimodal reasoning and image generation model by Google DeepMind
Model Card Overview
| Field | Description |
|---|---|
| Model Name | Nano Banana Pro (also known as Gemini 3 Pro Image) |
| Developer | Google DeepMind |
| Release Date | November 20, 2025 |
| Model Type | Multimodal Reasoning and Image Generation |
| Related Links | Official Product Page, Model Card (PDF) |
Introduction
Nano Banana Pro, officially designated as Gemini 3 Pro Image, represents the next generation in Google's series of highly-capable, natively multimodal models. It is designed for professional asset production, integrating the advanced reasoning capabilities of the Gemini 3 Pro foundation model with a sophisticated image generation engine. The primary goal of Nano Banana Pro is to provide users with studio-quality precision and control, enabling the creation of complex, high-fidelity visuals from textual and image-based prompts. Its core contribution lies in its ability to understand and execute intricate instructions, maintain character and scene consistency, and render legible text directly within generated images, setting a new standard for professional creative workflows.
Key Features & Innovations
Nano Banana Pro introduces several technical breakthroughs that distinguish it from prior models:
- Superior Text Rendering: The model excels at generating images that contain clear, accurate, and stylistically coherent text, making it ideal for creating posters, diagrams, and marketing materials.
- Advanced Creative Controls: Users can exercise fine-grained control over image outputs, including camera angles, lighting transformations (e.g., day to night), color grading, depth of field, and localized editing.
- High-Fidelity Consistency: It can maintain the consistency of up to 14 input images and blend up to 5 distinct characters seamlessly into complex compositions, ensuring visual coherence across a series of generated images.
- Deep Real-World Knowledge: Built on Gemini 3 Pro, the model leverages a vast understanding of the world to generate contextually rich and factually grounded visuals, from detailed infographics to historically accurate scenes.
- Multilingual Capabilities: The model can accurately render and translate text across multiple languages within an image, facilitating the localization of visual content.
- Complex Composition from Multiple Inputs: Nano Banana Pro can synthesize elements from multiple source images and text prompts to create a single, cohesive scene, enabling complex creative concepts.
Model Architecture & Technical Details
Nano Banana Pro's architecture is fundamentally based on the Gemini 3 Pro model. While specific architectural details are not fully disclosed, the following technical information is available:
- Foundation Model: Gemini 3 Pro
- Inputs: The model accepts text strings and images as input, with a large context window of up to 1 million tokens.
- Outputs: It generates high-resolution images (up to 4K) with a 64K token output capacity for handling complex generation tasks.
- Training Infrastructure:
- Hardware: The model was trained on Google's custom-designed Tensor Processing Units (TPUs), which are optimized for large-scale machine learning computations and high-bandwidth memory access.
- Software: The training process utilized JAX and ML Pathways, Google's high-performance frameworks for machine learning research.
- Knowledge Cutoff: The model's internal knowledge base has a cutoff date of January 2025.
Intended Use & Applications
Nano Banana Pro is intended for professional and creative applications that require a high degree of precision, control, and visual fidelity. It is well-suited for a variety of downstream tasks and application scenarios:
- Professional Content Creation: Generating production-ready assets for marketing campaigns, advertising, and branding.
- Design and Prototyping: Creating detailed product mockups, storyboards for film and animation, and architectural visualizations.
- Informational Graphics: Designing complex and accurate infographics, educational diagrams, and data visualizations.
- Artistic and Creative Expression: Enabling artists and designers to explore novel visual styles and create complex, multi-element compositions.
Performance
Nano Banana Pro's performance has been evaluated through extensive human evaluations and benchmarked against other leading image generation models. The results, measured in Elo scores, demonstrate its strong capabilities across a wide range of tasks.
A technical report also notes a performance dichotomy: while the model produces subjectively superior visual quality by hallucinating plausible details, it can lag behind specialist models in traditional quantitative metrics due to the stochastic nature of generative models.
Existing Capabilities (Elo Score Comparison)
| Capability | Gemini 3 Pro Image | Gemini 2.5 Flash Image | GPT-Image 1 | Seedream v4 4k | Flux Pro Kontext Max |
|---|---|---|---|---|---|
| Text Rendering | 1198 ± 18 | 997 ± 10 | 1150 ± 14 | 1019 ± 13 | 854 ± 13 |
| Stylization | 1098 ± 11 | 933 ± 7 | 1069 ± 9 | 991 ± 9 | 908 ± 11 |
| Multi-Turn | 1186 ± 19 | 1045 ± 24 | 1079 ± 32 | 990 ± 32 | 889 ± 37 |
| General Image Editing | 1127 ± 13 | 996 ± 8 | 1011 ± 13 | 965 ± 12 | 902 ± 13 |
| Character Editing | 1176 ± 16 | 1075 ± 8 | 1016 ± 10 | 889 ± 10 | 843 ± 10 |
| Object/Env. Editing | 1102 ± 19 | 1025 ± 9 | 930 ± 12 | 983 ± 13 | 961 ± 10 |
| General Text-to-Image | 1094 ± 16 | 1037 ± 8 | 1025 ± 9 | 1011 ± 9 | 907 ± 9 |
New Capabilities (Elo Score Comparison)
| Capability | Gemini 3 Pro Image | Gemini 2.5 Flash Image | GPT-Image 1 | Seedream v4 4k | Flux Pro Kontext Max |
|---|---|---|---|---|---|
| Multi-character Editing | 1213 ± 16 | 950 ± 10 | 997 ± 13 | 840 ± 19 | - |
| Chart Editing | 1209 ± 18 | 971 ± 10 | 994 ± 16 | 934 ± 16 | 893 ± 15 |
| Text Editing | 1202 ± 23 | 1001 ± 10 | 996 ± 14 | 860 ± 15 | 943 ± 12 |
| Factuality - Edu | 1169 ± 25 | 1050 ± 11 | 1084 ± 25 | 969 ± 22 | 884 ± 26 |
| Infographics | 1268 ± 17 | 1162 ± 11 | 1087 ± 12 | 1049 ± 12 | 824 ± 15 |
| Visual Design | 1104 ± 16 | 1083 ± 7 | 1028 ± 11 | 1038 ± 12 | 907 ± 11 |
