Zorq AI makes images, videos and audio. You write what you want, pick a model, and it is made in seconds. You can add your own images to guide it. There is nothing to install and you do not need to know design or code.
Go to zorqai.com and click Sign In. You can use your Google account or Apple ID — no separate registration, email verification, or password needed. Your account is created automatically on first sign-in.
No. Zorq AI is a web application that runs entirely in your browser. It works on desktop (Chrome, Safari, Firefox, Edge) and mobile devices. There's nothing to download or install.
There's no free tier, but the Beginner plan at $14.99/month gives you 200 credits which is enough to generate around 100 images or 10-20 videos. You can also earn free credits by sharing your creations in the Community (5-100 credits per approved post) or uploading video tutorials (500-1,000 credits per approved tutorial).
Every generation uses credits. The cost depends on the model and quality settings. Images typically cost 2-6 credits. Videos cost 5-80 credits depending on the model, duration, and resolution. Audio (text-to-speech) costs 2-4 credits. Your credits refresh at the start of each billing cycle on subscription plans.
Monthly plans: Starter $14.99/mo (200 credits), Creator $49/mo (800 credits), Unlimited $249.99/mo (5,000 credits + unlimited image generation). Annual saves 40-67%: Starter $108/yr ($9/mo), Creator $294/yr ($24.50/mo), Unlimited $990/yr. You can also buy one-time credit top-ups: 100 credits for $9.99, 300 for $24.99, 600 for $49.99.
No — subscription credits reset each billing cycle. If you have 150 credits left and your plan renews, you'll get your full plan credits (not 150 + plan credits). However, credits from one-time top-up purchases never expire as long as your account is active.
The Unlimited plan ($249.99/mo) gives you 5,000 credits per month plus unlimited image generation — meaning images don't use any credits at all, including Ultra (4K). You also get priority support and all other features. The 5,000 credits are for videos and audio only.
Creator ($49/mo) and Unlimited ($249.99/mo). On Creator, standard-quality images are free: Seedream 4.5, Seedream 5.0 Lite, Seedream 5.0 Pro at 1K, Nanobanana 2 below 4K, and GPT Image 2 at low quality. Anything above those settings — 4K, GPT Image 2 at medium or high — uses credits as normal. On Unlimited every image is free at every quality. Videos always use credits, on every plan.
We accept all major credit and debit cards, Apple Pay, Google Pay, and more. Payments are processed securely through Whop. You can manage your subscription and billing from your Profile page.
Go to your Profile page and click Manage Subscription. You can cancel at any time. Your credits remain active until the end of your current billing period — you won't lose access immediately.
We offer refunds on a case-by-case basis. If you're unsatisfied, contact us through the Support page within 7 days of purchase. See our full Refund Policy for details. Credits used for generation are non-refundable, but failed generations are always automatically refunded.
It depends on what you're creating. For photorealistic portraits and people: Seedream 4.5 or Kling Image V3. For creative edits and combining multiple images: Nanobanana Pro. For fast, cheap generation: Seedream 4.0 or 5.0 Lite (2 credits). For maximum quality and detail: Nanobanana 2 or WAN 2.7 Pro. Each model has its strengths — try a few with the same prompt to see which style you prefer.
Be specific in your prompts. Instead of 'a woman', write 'a 30-year-old woman with auburn hair, wearing a navy blazer, sitting at a modern desk, soft natural lighting from a window, shot on Canon R5, 85mm lens, f/1.8'. Include details about lighting, camera angle, mood, and style. Use reference images when possible — uploading an example of the style you want dramatically improves results.
Yes. Use Kling O3 Edit to modify existing images with text instructions (e.g., 'change her dress to red' or 'remove the background'). Nanobanana Pro can also combine and edit images — upload your source image(s) and describe what you want changed.
You can generate images in multiple aspect ratios: 1:1 (square), 3:4 (portrait), 4:3 (landscape), 9:16 (phone/stories), and 16:9 (widescreen). Quality tiers: Basic (1K), High (2K), and Ultra (4K — Unlimited plan only). All images are generated as high-quality JPEGs and can be downloaded directly.
Reference images are photos you upload alongside your text prompt to guide the AI. For example, upload a photo of a person and write 'same person sitting on a beach at sunset' — the AI will maintain the person's appearance in the new scene. You can upload up to 5 reference images. They're especially powerful with Nanobanana Pro which can combine elements from multiple references.
MultiGen lets you generate multiple images or videos simultaneously with different prompts, models, or settings. It's perfect for creating variations, testing different models side-by-side, or batch-producing content. You can queue up to 20 generations at once and they all process in parallel.
For best quality: Google Veo 3.1 or Kling 3.0 (premium, 16-80 credits). For cinematic motion and people: Seedance v1.5 Pro or Kling V2.6 Pro. For best value: WAN 2.6 (cheapest, 5-24 credits). For creative/artistic: Sora 2. For fast results: Google Veo 3.1 Fast. Each model handles different content types differently — test with your specific use case.
Most models generate 5-10 second clips. WAN 2.6 can go up to 10 seconds. Motion Control can go up to 30 seconds. For longer content, you can generate multiple clips and edit them together, or use the Storyboard feature to plan multi-scene projects.
Yes — this is called image-to-video (I2V). Upload a source image and the AI will animate it. This works with all Create-tab models. It's especially powerful for product shots, character animation, and bringing still photos to life. The AI maintains the visual content of your image while adding natural motion.
Motion Control lets you transfer movement from any video onto a character image. Upload a photo of a person (the character) and a video (the motion reference) — the AI will animate your character with the same movements from the video. Great for dance videos, presentations, or any content where you want a specific person performing specific movements. Costs 2.4 credits/second.
Scene Control is an advanced Motion Control feature. It swaps your character into the motion video while preserving the original background and environment. The AI first uses Nanobanana to merge your character with the video's first frame, then animates using the original motion. Costs an extra 2 credits on top of Motion Control.
Lip Sync takes a face image or video and an audio track, then animates the face to match the speech in the audio. Combined with Text-to-Speech, you can create talking-head videos entirely from AI — generate a face, generate a voiceover, then sync them together.
Typically 1-5 minutes depending on the model and duration. WAN 2.6 is the fastest (usually under 2 minutes). Google Veo 3.1 and Kling 3.0 take 3-5 minutes. Your video processes in the background — you can start new generations while waiting. The result appears in your Gallery when ready.
Three models: MiniMax Speech 2.6 HD (2 credits, great quality, multiple voices), ElevenLabs Eleven v3 (3 credits, premium naturalness), and Qwen3 Voice Design (2 credits, create custom voices from text descriptions). Each offers different voice presets and styles.
Upload a short audio sample (10-60 seconds) of any voice. The AI analyzes it and creates a voice clone. Then you can type any text and generate speech in that cloned voice. The result is surprisingly accurate even from short samples. Costs 5 credits to clone, then standard TTS rates for each generation.
Smart Mode is an AI creative director. Instead of manually choosing a model and writing a detailed prompt, you just describe what you want in plain language — like 'make me a cinematic product video of a perfume bottle' — and the AI agent figures out the best model, writes an optimized prompt, selects the right settings, and generates the result. It's the easiest way to use Zorq AI if you're not sure which model to pick.
AI Influencer lets you create a consistent virtual character. Upload 3+ reference photos of people you want the character to resemble, and the AI generates a new, unique face. Then it creates a reference sheet — a 2x2 grid showing your character's face and full body from every angle (front, sides, back). This reference sheet ensures your character looks the same across all future generations.
The Community is where users share their best AI-generated images and videos. You can browse, like, and comment on posts. To earn credits: go to your Gallery, select a creation you're proud of, and click 'Share to Community'. If approved by admins, you earn 5-100 credits depending on quality. Video tutorials earn 500-1,000 credits.
Refer new users to Zorq AI and earn commission on their subscriptions. You get a unique referral link from the Affiliate page. When someone signs up and subscribes through your link, you earn a percentage. Details and payout info are on the Affiliate Program page.
No. Failed generations are automatically refunded. The credits return to your balance within seconds. You can check your credit history in your Profile. If a generation gets stuck in 'processing' for more than 10 minutes, use the Recovery button in your Gallery — it will check with the provider and either deliver the result or refund your credits.
AI models have built-in safety filters that sometimes flag content they consider inappropriate. This can happen even with innocent prompts if they contain certain keywords. Try rephrasing your prompt, removing words that might trigger filters, or switching to a different model. Different models have different sensitivity levels. Credits are refunded for flagged generations.
Make sure your image is in JPG, PNG, or WebP format and under 10MB. If you're uploading from iPhone, HEIC files are automatically converted. If it still fails, try downloading the image and re-uploading it, or try a different browser. Our system validates and normalizes all uploaded images automatically.
Video generation typically takes 1-5 minutes. If it's been over 10 minutes, go to your Gallery and click the Recovery button. This checks the status with the AI provider and either delivers the completed video or refunds your credits. Videos process in the background — you don't need to keep the page open.
Yes. The platform is fully responsive and works on any modern smartphone browser. You can generate images, videos, and audio, manage your gallery, and share to the community — all from your phone. For the best experience, use Chrome or Safari.
Yes. All subscription plans include a commercial license. You can use generated images, videos, and audio for business, marketing, advertising, social media, client work, merchandise, print, YouTube, and any other commercial purpose. The content you generate is yours to use.
Yes. You can sell prints, use content in paid advertising, deliver to clients, put on merchandise, include in paid courses — there are no restrictions on commercial sale as long as you have an active subscription.
You do. Content generated on Zorq AI belongs to you. We don't claim ownership of your creations. When you share to the Community, you grant us permission to display it on the platform, but you retain ownership.
Your generated content is stored securely and only accessible to you (and public if you choose to share to Community). We don't sell your data or prompts. Reference images you upload are used only for your generation and not for model training. See our Privacy Policy for full details.
Only with that person's explicit consent. Uploading, processing or generating the likeness of a real person without permission is prohibited, and the same applies to their voice — cloning or imitating a real person's voice needs consent exactly as their face does. Public figures are not an exception.
Illegal, threatening, abusive, harassing, defamatory and discriminatory content; deepfakes or misleading content intended to deceive or harm; content depicting minors in any inappropriate context; images of real people used without their consent; and anything that infringes someone else's intellectual property. The full list is in the Prohibited Use section of the Terms of Service, and it is summarised at zorqai.com/safety.
Generating content that depicts minors in any inappropriate context is prohibited without exception. You must be at least 18 years old to create an account and use the service, and we may suspend or terminate any account used this way.
We may review, remove or restrict access to content that violates the Terms or applicable law, and we may suspend or terminate accounts that repeatedly violate our policies. This is set out in the Content Moderation section of the Terms of Service.
Email support@zorqai.com, or use the form at zorqai.com/support. Include the account, a link or description of the content, and what rule you believe it breaks. Those are our official support channels.
Yes. The models come from independent providers, each with its own safety requirements, and a provider can refuse or change what it will generate at any time. A request our Terms permit can still be declined by the model behind it.