AI Image Generator — Nano Banana Pro | 4K

Generate photorealistic 4K AI images from text prompts using Nano Banana Pro. Describe what you want in plain English — pick a style, set an aspect ratio, and get stunning results in seconds. No API key, no credits, no setup.

No API key needed · 4K resolution · 8 style presets · Negative prompts · Seed for reproducibility · Multiple variants · Image-to-image · Permanent storage · Bulk up to 50 images

---

Features

• 🎨 Nano Banana Pro — fast, photorealistic AI image generation at 4K
• 🎭 8 style presets — Photorealistic, Anime, Oil Painting, 3D Render, Watercolor, Cinematic, Flat Illustration, Pixel Art. One click, no prompt engineering.
• 🚫 Negative prompts — tell the AI what to avoid (blurry, watermark, extra fingers, etc.)
• 🎲 Seed control — fix the seed for reproducible results; increment for controlled variations
• 🔢 Multiple variants — generate 1–4 versions of each prompt to pick the best one
• 🖼️ Image-to-image — provide a reference photo and re-style it with your prompt
• 💾 Permanent storage — optionally save images to Apify's KV store (never expires)
• 📐 7 aspect ratios — Portrait, Landscape, Square, 4:3, 3:4, 3:2, 2:3
• 📦 Bulk generation — up to 50 images per run with parallel processing
• 💰 No API key — runs immediately, no accounts or tokens to set up

---

Use cases

Use case	Example
Product mockups	"Skincare bottle on marble, studio lighting" + style: Photorealistic
Social media content	"Flat lay workspace, coffee and plants" + ratio: 1:1
YouTube thumbnails	"Epic space battle with explosions" + ratio: 16:9 + style: Cinematic
Marketing banners	"Abstract gradient with floating shapes" + ratio: 16:9
Game assets	"Medieval sword with glowing runes" + style: 3D Render
Anime characters	"Warrior girl with katana, cherry blossoms" + style: Anime
Art prints	"Countryside landscape at golden hour" + style: Oil Painting
App icons	"Minimalist brain logo, neon glow" + ratio: 1:1
A/B testing	Same prompt × 4 variants → pick the winner
Consistent series	Fix the seed → same style across a set of images

---

Input

Parameter	Type	Default	Description
prompts	string[]	—	Required. Text descriptions of the images you want.
negativePrompt	string	—	What to avoid: "blurry, watermark, text, low quality"
style	select	none	Style preset to auto-apply to all prompts
aspectRatio	select	9:16	Output shape
numImages	integer	1	Variants per prompt (1–4)
seed	integer	-1	Random seed for reproducibility (-1 = random)
referenceImageUrl	string	—	Reference photo URL for image-to-image
saveToStore	boolean	false	Save images permanently in Apify KV store
maxConcurrency	integer	3	Parallel generations (1–5)

---

Style presets

Style	What it adds
Photorealistic	Ultra detailed natural lighting, 8K photograph look
Anime	Cel shading, vibrant colors, Japanese illustration style
Oil Painting	Visible brushstrokes, rich textures, classical art feel
3D Render	Octane render, volumetric lighting, CGI quality
Watercolor	Soft washes, wet-on-wet technique, paper texture
Cinematic	Film grain, anamorphic lens, dramatic lighting
Flat Illustration	Clean vectors, minimal shading, modern design
Pixel Art	Retro gaming, limited palette, 16-bit aesthetic

---

Examples

Simple text-to-image

{
    "prompts": ["A cozy cabin in the mountains during snowfall, warm light from windows"],
    "style": "cinematic"
}

Multiple variants for A/B testing

{
    "prompts": ["Professional headshot, confident woman, blurred office background"],
    "style": "photorealistic",
    "numImages": 4,
    "aspectRatio": "1:1"
}

Reproducible results with seed

{
    "prompts": ["Cyberpunk samurai in neon-lit Tokyo alley"],
    "seed": 42,
    "style": "cinematic",
    "aspectRatio": "9:16"
}

Negative prompt to avoid common issues

{
    "prompts": ["Beautiful portrait of a young woman in a garden"],
    "negativePrompt": "blurry, watermark, text, extra fingers, distorted face, low quality",
    "style": "photorealistic"
}

Image-to-image (style transfer)

{
    "prompts": ["Same scene reimagined as a Studio Ghibli animation"],
    "referenceImageUrl": "https://example.com/my-photo.jpg",
    "style": "anime"
}

Permanent storage

{
    "prompts": ["Logo design: abstract phoenix in gold and black, minimalist"],
    "aspectRatio": "1:1",
    "saveToStore": true
}

---

Output

{
    "success": true,
    "prompt": "A cozy cabin in the mountains during snowfall..., cinematic still, anamorphic lens, dramatic lighting, film grain, color grading",
    "negativePrompt": "blurry, watermark",
    "aspectRatio": "9:16",
    "imageUrl": "https://api.apify.com/v2/key-value-stores/.../records/img-abc123.png",
    "referenceUrl": null,
    "seed": 42,
    "variant": 1
}

Field	Description
imageUrl	Permanent download link to your generated image (Apify-hosted, never expires)
seed	The seed used (for reproduction)
variant	Which variant this is (1, 2, 3, or 4)

---

Prompt writing tips

1. Be specific — "Golden retriever puppy running through autumn leaves, backlit by sunset" > "dog"
2. Use a style preset — saves you from typing style keywords in every prompt
3. Add the negative prompt — "blurry, watermark, text, extra fingers, low quality" prevents common AI artifacts
4. Describe lighting — "golden hour", "neon glow", "soft diffused light", "dramatic shadows"
5. Set the mood — "cozy", "epic", "minimalist", "dark", "vibrant"
6. Fix the seed — run the same prompt twice with the same seed to get the exact same result; increment by 1 for controlled variations

---

How it works

1. Your prompt (+ style suffix + negative prompt) is sent to Nano Banana Pro
2. The model generates a 4K image (typically 30–90 seconds)
3. The result URL is returned — download it or use it directly
4. If saveToStore is on, the image is also saved permanently on Apify
5. For bulk runs, images are generated in parallel

No queue, no waitlist, no credits. Each run processes your prompts and delivers results.

---

Pricing

Volume	Price
Per image	$0.018
100 images	$1.80
1,000 images	$18

The cheapest AI image generation on Apify. You only pay for successfully generated images — failed generations are free. Platform compute is included.

---

FAQ

How long does one image take? 30–90 seconds depending on complexity. The actor polls automatically.

Can I get the same image twice? Yes — set a fixed seed. Same prompt + same seed = same output.

What if I need higher resolution? The output is already 4K. For even higher, chain this with an upscaler actor.

Do style presets override my prompt? No — they append style keywords to your prompt. Your description stays intact.

What happens if generation fails? The record is saved with "success": false and an error. You're not charged for fails.

Will my images expire? No — all images are hosted on a permanent Apify URL that never expires. Download them anytime.

---

Integration ideas

• Content pipelines — auto-generate blog hero images
• A/B creative testing — 4 variants per ad concept, pick the winner
• Social scheduling — bulk-generate a week of visual content
• E-commerce — lifestyle product shots without a photographer
• Zapier / Make / n8n — trigger generation from a workflow
• Consistent branding — fix seed + style for a unified visual series