AI Image Generator – Text to Image, No API Key

Generate images from text prompts with FLUX.2 [klein], the compact image model from Black Forest Labs, running on Cloudflare Workers AI. Write one prompt or a hundred, pick a size, get up to 4 variations per prompt, and optionally give reference images for image-to-image. Download the results as PNG, JPEG or WebP. No API key, no account with an AI provider: you pay per image on Apify.

How it works

1. Write your prompts. One prompt per line, for example "A watercolor illustration of a lighthouse on a rocky coast at sunrise". English prompts give the best results.
2. Pick the size and the number of images per prompt. If you want, add up to 4 reference images, a seed or a guidance value.
3. Run. Every image is saved in the run's key-value store, and the dataset gets one row per image with a link to it. The Images view shows the pictures right in the table.

Sizes

Option	Pixels	Good for
Square HD (default)	1024 × 1024	social posts, product shots, avatars
Square	768 × 768	quick drafts
Landscape 4:3	1152 × 864	blog images, slides
Landscape 16:9	1344 × 768	banners, video thumbnails, headers
Portrait 3:4	864 × 1152	posters, Pinterest
Portrait 9:16	768 × 1344	stories, phone wallpapers

Every size costs the same per image.

Image-to-image (reference images)

Add up to 4 links to images in Reference images: direct links to PNG, JPEG or WebP files (max 20 MB each), or share links from Google Drive, Dropbox or OneDrive set to "Anyone with the link". The model uses them as a reference for style, composition or subject, for example "the same room, but in winter" or "this product on a marble table".

• The reference images are used for every prompt in the run.
• They are scaled down to fit inside 511 × 511 pixels before they are sent (a limit of the service); the generated image still has the size you picked.
• Links to pages on social media or other platforms are not supported.
• If a reference image cannot be used, the run stops before anything is generated, and nothing is charged.
• Only use images you have the right to use.

Seeds and variations

• Images per prompt (1–4) gives you several variations of the same prompt. Each one is a separate image and is charged separately.
• Without a seed, every image gets a random one. The seed is in every row, so you can repeat a result you like.
• With a seed, image 1 uses that seed, image 2 uses seed + 1, and so on. The same prompt, size, reference images and seed should give the same image again.

Pricing

Pay per event: $0.004 per generated image, on every Apify plan.

You generate	You pay
1 image	$0.004
10 prompts × 1 image	$0.04
25 prompts × 4 variations = 100 images	$0.40
100 prompts × 4 variations = 400 images	$1.60

What you are not charged for

• Prompts that are refused under the acceptable-use rules below
• Images that fail (for example when the image service has an error, or does not answer in time)
• Prompts whose safety check could not be completed
• Images skipped because of a limit: your maximum cost per run, Maximum images per run, or the daily capacity of this actor
• Runs that stop because of a wrong input or a reference image that cannot be used

Before an image is generated, the actor checks that it fits within your maximum cost per run. If it doesn't, the image is skipped and you pay nothing for it.

Apify free plan: at most 4 images per run and 10 images per day (enough to try it out). Images beyond that are skipped and not charged. On a paid Apify plan these limits do not apply.

Input example

{
  "prompts": [
    "A watercolor illustration of a lighthouse on a rocky coast at sunrise",
    "Flat vector icon of a coffee cup, pastel colors, white background"
  ],
  "imageSize": "landscape_16_9",
  "numImages": 2,
  "seed": 1234,
  "outputFormat": "webp",
  "maxImages": 20
}

Output

One row per image:

{
  "prompt": "A watercolor illustration of a lighthouse on a rocky coast at sunrise",
  "promptNumber": 1,
  "imageNumber": 2,
  "imageUrl": "https://api.apify.com/v2/key-value-stores/<store>/records/001-2.webp",
  "width": 1344,
  "height": 768,
  "seed": 1235,
  "format": "webp",
  "referenceImages": 0,
  "status": "ok",
  "statusMessage": "Generated."
}

status	Meaning	Charged
ok	The image was generated and saved	yes
refused_content	The prompt was refused under the acceptable-use rules	no
failed	Something went wrong (see statusMessage)	no
not_processed_limit	Skipped because of a limit (your budget, maxImages, free plan)	no
quota_exhausted	The daily capacity of this actor is used up; try again after 00:00 UTC	no

The image files are named <prompt number>-<image number>.<png|jpg|webp>, for example 003-1.png. The run summary (record OUTPUT) lists how many images were generated, refused, failed and charged.

Acceptable use

To keep this actor safe, every prompt is checked before an image is generated: first by a fixed word filter, then by the safety model Llama Guard 3. A prompt that may break these rules is refused. Refused prompts cost nothing. Do not use this actor for:

• sexual or sexually suggestive content of any kind;
• anything involving minors in a sexual, violent or otherwise harmful way;
• images of real people without their consent, including public figures, and anything that could defame or mislead about a real person;
• famous characters, logos, brands or other protected works of others;
• hate, harassment, violence, weapons of mass harm or self-harm.

The safety check is automatic and can be wrong in both directions. You remain responsible for the prompts you send, for the reference images you use, and for how you use the results.

Privacy

• Your prompts and reference images are sent to Cloudflare Workers AI to check and generate the images. They are not used for anything else by this actor.
• The prompts are not written to the run log.
• Nothing is kept after the run, except what is in your own run storage (the dataset and key-value store), which follows your Apify data retention settings.

Terms for the generated images

The images are made with FLUX.2 [klein] by Black Forest Labs, run by Cloudflare. You must follow Black Forest Labs' terms (bfl.ai/legal/terms-of-service) and Cloudflare's terms for Workers AI. Check those terms yourself before you use the images, in particular for commercial use. This actor is not affiliated with or endorsed by Black Forest Labs or Cloudflare.

Limits

• Up to 100 prompts per run, each up to 2,000 characters; up to 4 images per prompt; at most 400 images per run (maxImages, default 20).
• Up to 3 images are generated at the same time.
• Text inside images (lettering, logos) is often imperfect with compact models.
• During busy times the service can be slower; an image that takes longer than 3 minutes is marked failed and not charged.

FAQ

Do I need an API key or an account with an AI provider? No. The actor uses its owner's Cloudflare account; you only pay the price per image on Apify.

Why was my prompt refused? The safety check found that it may conflict with the acceptable-use rules. Refused prompts are free. Rephrase the prompt if you believe it was a mistake.

Can I use the API? Yes: start the actor through the Apify API with the input above and read the dataset items; imageUrl points to the image file.