FreePik, explained: where your AI images and video come from

Text AI writes captions. FreePik makes the images and the short videos. Here's what it is, why we use it, and how to get set up.

·5 min read·Chelle Honiker
Flat illustration of a small camera with motion trails next to a palette of color swatches

OpenAI, Claude, and Gemini are text AI. They write. They don't make images or videos.

For images, video, and music — the visual side of social content — we use FreePik. Here's the short version of what it is and how it fits into your workflow.

What FreePik is

FreePik is a separate AI service that specializes in visual content. It runs several image and video generation models under one account:

  • Nano Banana Pro — Google's image model, best for flat illustrations and editorial scenes
  • Mystic — FreePik's house model, good for photographic-style content
  • Flux — high-quality image generation
  • Seedream — clean, contemporary aesthetic
  • Kling — short video generation (5-10 seconds from a still image)
  • Music generation — 15-second clips from a text prompt

You don't pick models manually most of the time — the tool picks a sensible default based on what you're generating. You can override in Settings if you have a preference.

Why FreePik instead of DALL-E or Midjourney?

Three reasons:

1. Best-in-class for flat-illustration editorial content. For author-audience imagery (book aesthetics, scene illustrations, social-post backgrounds), FreePik's Nano Banana Pro beats the alternatives on consistency and style-control. Midjourney is stronger for hyper-realistic, moody work; OpenAI DALL-E is weaker on composition.

2. Video + music in one place. Most image AIs don't generate video. FreePik does, cheaply. Combining still-image → short-video → music all in one API keeps the workflow clean.

3. Pricing. FreePik's API is priced significantly below Midjourney for comparable volume. For authors generating a 30-post campaign, the difference is meaningful.

What FreePik costs

FreePik pricing works on credits. You buy credits, each generation consumes credits. Approximate costs:

  • Image generation (Nano Banana Pro): ~5-10 credits per image
  • Short video (Kling): ~30-50 credits per video
  • Music: ~10 credits per clip

Credits are cheap. A hundred images of typical author use is maybe $5-10 in credit usage. A full launch campaign with 30 AI images and 4 short reels is usually under $15.

You buy credits as you need them; no monthly subscription required. Most authors top up $10-20 at a time.

How to get a FreePik API key

  1. Go to freepik.com/api
  2. Sign up (or sign in)
  3. Add billing information (credits are prepaid, so you're not charged until you use them)
  4. Copy your API key from the dashboard
  5. Paste into Settings → AI → FreePik key

Same pattern as OpenAI/Claude/Gemini. The API keys explainer applies here too — your key is encrypted, isolated, and only used when you're actively generating.

What FreePik produces, and what to review

FreePik's images are consistently good. Not flawless. Things you still have to review:

Wrong era. If you asked for a contemporary scene, sometimes you'll get something subtly Victorian. Catch it, regenerate.

Wrong mood. A horror-cover-aesthetic prompt can come back cozier than you wanted, or vice versa. Regenerate with stronger adjectives.

Text artifacts. AI image models hallucinate text. Even when you ask for "no text," occasional fake-latin letters sneak in. The "no text, no typography, no watermarks" prompt prefix helps, but review anyway.

Character implications. If your book is diverse, make sure the generated characters reflect that. Left unspecified, AI models default to white/Western. Specify in the prompt if that matters.

Where FreePik fits in the workflow

When you generate an AI campaign via /dashboard/create, every post that needs an image has the FreePik generation happening in the background. The prompt for each image is derived from:

  • The caption being generated
  • Your brand voice guides (especially the "imagery style" field if you've filled it out)
  • Sensible defaults for the platform (vertical for TikTok/Reels, square for Instagram)

You see the generated image in the campaign review screen. If you don't like it, click Regenerate. If you want a completely different style, edit the image prompt directly and regenerate.

Imagery style prompts that work

In Settings → AI there's an optional "imagery style" field. This is the standing instruction FreePik gets for every image it generates for you.

Good examples:

  • Flat illustration style, warm editorial palette (terracotta, cream, navy), minimal composition, no photorealism
  • Photographic, soft-focus morning light, shallow depth of field, autumnal palette, no text, no logos
  • Watercolor style, coastal New England tones, hand-drawn sketch quality, literary-cozy aesthetic

The style field tells FreePik "every image I generate should look like this, regardless of the subject." This is what gives a 30-post campaign visual cohesion.

What to do next