AI Image Generator (no API key)
Pricing
Pay per usage
AI Image Generator (no API key)
Generate AI images from a text prompt. No API key, no account, no card. Returns a hosted image URL.
Pricing
Pay per usage
Rating
0.0
(0)
Developer
ohan he
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
a day ago
Last modified
Categories
Share
Turn a list of text prompts into images. No API key, no account, no card — this Actor calls a public anonymous endpoint, so you can run it the minute you land here.
Most image Actors and workflow nodes need an OpenAI, fal, or Replicate key before they produce a single pixel. This one doesn't.
What you get
| Input | A list of prompts + one aspect ratio |
| Output | One dataset row per prompt: prompt, aspectRatio, imageUrl, watermarked |
| Image hosting | A permanent CDN URL — nothing to download or re-upload |
| Speed | ~25–40s per square image; 16:9 can take longer when the free queue is busy |
| Cost to you | Apify platform usage only. The generation itself is free. |
Input
{"prompts": ["a paper boat on a calm lake at sunrise, soft light","an isometric cutaway of a tiny bookshop, warm lamps"],"aspectRatio": "16:9","timeoutSecs": 240}
aspectRatio accepts 1:1, 16:9, 9:16, 4:3, 3:4.
Output
{"prompt": "a paper boat on a calm lake at sunrise, soft light","aspectRatio": "16:9","imageUrl": "https://cdn.kavel.ai/uploads/kie/image/81c21156-....webp","watermarked": true}
A prompt that fails or times out still produces a row, with imageUrl: null and an
error field, so a long run never silently drops entries.
Good to know
- The free tier is metered per run. Each run starts a fresh anonymous identity with a small grant of credits, which covers a handful of images. Feed it a 200-prompt list and the tail of the list will come back with an error row rather than an image.
- Free output carries a watermark and lands at 1K. If you need it clean, that is what an account is for — see Kavel pricing. If you are trying to strip a watermark from something else entirely, that is a different job: how watermark removers actually work.
- One model, chosen for throughput. The free lane runs a fast text-to-image model. For the frontier ones, compare Nano Banana Pro vs Nano Banana 2 and Gemini 3 Pro Image.
Recipes
- Bulk product mockups — feed one prompt per SKU, pull
imageUrlstraight into a sheet. - Blog headers — one prompt per post title,
16:9. - Portrait sets —
9:16plus a prompt list; see AI selfie generator for prompt patterns that hold a face steady. - Seasonal batches — e.g. AI Christmas card generator.
Who makes this
Built on Kavel, an AI image and video studio that shows the credit cost before every generation. There is also a n8n template running the same endpoint if you prefer that over Apify.