🎬 AI Video Ads Generator

This actor generates AI-powered video ads for your products, brands, or services. You can create professional-quality videos for social media platforms like Instagram, TikTok, YouTube, and Facebook in minutes.

The latest version supports 1–15 video variants per run, customizable according to your product, audience, ad goal, brand tone, and visual style. Instead of a single model, you can now select from a curated list of industry-leading AI models categorized into Basic, Standard, and Premium tiers.

Whether you need a quick draft using Wan 2.7, high-performance social media clips via Seedance 1.0 Pro or Kling, or cinematic-grade production with Google Veo 3.1, this Actor scales to meet your budget and quality requirements.

---

🆕 Version 0.2: The Multi-Model Update

Version 0.2 marks a significant upgrade in flexibility, quality, and cost-efficiency. We’ve moved beyond a single model to give you access to the entire landscape of 2026’s top AI video generators.

🆕 Version 0.3: Simpler pricing model, price reduction and longer video Ad

Version 0.3 marks a significant upgrade. Prices are slashed up to %30. Simpler pricing model is introduced and longer video Ads can be generated using veo 3.1 models.

🚀 Key Improvements

• Cheaper model run: Prices are slashed up to %30 for Basic, Standard and Premium models. Quality and Resolution paying events are removed and are free now. AdDuration prices are reduced.

• Three-Tier Pricing Matrix: We’ve introduced a new Pay-Per-Event billing system. You now have the power to choose between Basic, Standard, and Premium tiers to match your project’s budget and quality needs.

• More variants per run: Now users can generate 1-15 different or similar variants per run. As most users are generating 8-12 videos, therefore this change will save API call, Actor start and finish charges.

• Duration-Based Billing: Now you will pay $0.30 for 3-second, $0.60 for 5-second, and $0.90 for 10-second video generation for models other than Google Veo 3.1.

• Model Removed: Open AI premium model Sora is removed because it is going to be deprecated in September 2026.

• Success-First Billing: We’ve updated our core logic—the bulk of your credits are now only charged upon successful video generation. If the AI fails, you don't pay the tier or duration fees.

• Longer Video Ads: Now you can generate longer video Ads using Veo 3.1 models. You can now generate 8s, 16s, 32s, 40s, 48s, 56s and 64s of video. 8s video Ad generation costs approx $7.

Features

• Generate multiple video ad variants in a single run.
• Generate high performing ads for your social media campaigns.
• Customize video format, resolution, and duration.
• Supports optional reference images for visual guidance.
• Logs progress during video generation so users know to be patient.
• Pushes full metadata to Apify dataset for tracking and billing.

---

What kind of data can be collected?

We do not collect any personal user data. All inputs, generated videos, and metadata belong to the user running the actor. Each user only has access to their own dataset.

---

💰 Why Choose This Actor? (Pay-for-Success)

Most AI video generators charge a high flat fee regardless of whether the AI "hallucinates" or fails to render. We believe you should only pay for cinematic value.

Zero Risk Entry: We charge a minimal "Handshake Fee" ($0.10) to initiate the GPU. If the API fails or times out, you aren't stuck with a full bill.

Dynamic Tiers: Using an advanced "Resource Ladder," our Actor calculates costs based on your specific settings. Want a quick 3-second preview? You pay significantly less than a full 10-second HD production.

High-Fidelity Assurance: The "Success Surcharge" only triggers when a valid video URL is generated and stored for you. Stop paying for AI "errors" and start paying for results.

---

💰 Estimated Run Costs

Pricing is transparent and based on a Base Tier Fee (depending on the AI model selected) plus a Duration Fee. You are only charged the primary fees upon successful video generation.

Tier	3 sec	5 sec	10 sec
Basic	~$2.30	~$2.60	~$3.30
Standard	~$4.30	~$4.60	~$5.30
Premium	~$7.30	~$7.60	~$8.30

Veo pricing

Google Veo 3.1 uses a different pricing model because longer videos require multiple AI generation requests. The estimated cost for an 8-second Premium Veo video starts at approximately $7.40. Longer videos (16–64 seconds) require additional generation steps and are priced accordingly.

How it works:

1. Orchestration Fee ($0.40): Includes orchestration, start-up, tier-basic, and dataset storage fees.

2. Base Tier Surcharge:

• Basic: $2.00

• Standard: $4.00

• Premium: $7.00

3. Duration Credits:

• 3 Seconds: $0.30

• 5 Seconds: $0.60

• 10 Seconds: $0.90

Example 1: Generating a 8-second video using Veo 3.1 & Kling Master(Premium) would cost: $0.40 (Fee) + $7.00 (Premium Tier) = ~$7.40 total.

Example 2: A 10-second cinematic ad using Seedance 1.0 & Veo 3.1 Fast (Standard) would costs: $0.40 (Fixed) + $4.00 (Standard Tier) + $0.90 (Duration) = ~$5.30 total.

Example 3: A 10-second cinematic ad using Wan 2.7, PixVerse and others (Basic) would costs: $0.40 (Fixed) + $2.00 (Basic Tier) + $0.90 (Duration) = ~$3.30 total.

Note: These are estimates based on a successful run. You are only charged the bulk of the fee upon successful video generation. You are charged very little for a failed response that is a requirement and impossible to ignore.

Actor's Input

There are required and optional inputs.

Required Inputs:

Input	Type	Description
model	string.	Name of the model. Example: "Basic (Wan 2.7)"
productName	string	Name of your product. Example: "Organic Green Tea"
targetAudience	array	Target audience. Example: "Women 18-35, Fitness Enthusiasts"
platform	string	Target platform for the ad. Options: "instagram", "tiktok", "youtube", "facebook"
videoFormat	string	Video format. Options: "auto", "portrait", "landscape_hd", "landscape", "square", "low"
adDuration	string	Duration of the ad in seconds. Other Models: "3", "5", "10". Google Veo 3.1: "8", "16", "24", "32", "40", "48", "56" or "64" seconds
basePrompt	string	Base prompt to guide AI video generation. Example: "Create an engaging ad for our organic green tea..."

Optional Inputs:

Input	Type	Description
adGoal	string	Goal of your ad. Example: "Increase brand awareness"
referenceImages	string	Upload 1-3 reference images of your product
brandTone	string	Tone of your brand. Example: "Luxury", "Fun"
brandStory	string	Describe your brand story in 10–40 words. Example: "Our brand started with a passion for organic tea..."
visualStyle	string	Video style. Options: "Cinematic", "Animated", "UGC", "Artistic", "Normal"
keySellingPoints	string	Key product features, separated by commas. Example: "No Sugar, Organic, Vegan"
colors	array	Up to 3 hex colors to match brand identity. Example: "#87CEFA\n#C2C2C2\n#000000"
variants	string	Video variants mode. Options: "similar", "different"

---

Actor's Output

The actor generates video ad variants and pushes them to the Apify dataset. Each dataset row contains the following fields:

Field	Description
model	Name of the model used
productName	Name of the product
referenceImages 1-3	Upload Reference Images
targetAudience	List of target audience segments
adGoal	Goal of the ad
platform	Target platform
videoFormat	Selected video format
width / height	Resolution of the generated video
adDurationSeconds	Duration of the ad video in seconds
brandTone	Brand tone
brandStory	Brand story text
visualStyle	Selected visual style
keySellingPoints	Comma-separated key selling points
colors	Brand colors
basePrompt	Base prompt used for AI generation
variantsMode	Selected variant mode (similar, different)
variant	Variant index (1-15)
apifyVideoUrl	Apify KV-hosted video URL
createdAt	Timestamp of video creation

---

Example Inputs

{
    "adDuration": "10",
    "adGoal": "Promote warmth, comfort, and cozy relaxation for everyday home wear",
    "basePrompt": "Create a high-energy promotional video showing Nike No-Show Socks in action. Highlight comfort, style, and performance for runners. Please create a motion video from reference image, show product from reference image if available and do not hallucinate.",
    "brandStory": "Nike has been creating innovative and comfortable athletic wear for decades. These no-show socks are designed to provide maximum comfort, performance, and style for runners and fitness enthusiasts alike.",
    "brandTone": "Energetic",
    "colors": "#87CEFA",
    "keySellingPoints": "comfortable, anti-bacterial",
    "model": "Basic (PixVerse)",
    "outputQuality": 30,
    "platform": "tiktok",
    "productName": "Nike No-Show Socks",
    "referenceImage1": "https://api.apify.com/v2/key-value-stores/3ThfcQvgdhXHI8JSb/records/nike-no-show.png",
    "targetAudience": "Athletes, Fitness Enthusiasts, Runners",
    "variantCount": 5,
    "variants": "similar",
    "videoFormat": "portrait",
    "visualStyle": "UGC"
}

🚀 Prompting Guide

Better prompts lead to cinematic results.

If you want to generate short video of your product from reference image, then it is good to provide only one clear reference image. Image should show your product clearly with white background and good lighting. Image urls must be publicly accessible and direct links to image files (e.g., ending in .jpg, .png). In base prompt, you can write "Use the reference image as the exact base frame. Do not change the person’s face, body, clothing, or product. Preserve identity, pose, background, and proportions. Do not hallucinate, etc." Please note that better prompting leads to better results.

For longer videos, use 3 high resolution reference images with different camera angles. You can write your brand story, Ad goal and other inputs. You can choose "similar" or "different" variants. For better results, try different inputs to check, which one gives you best results.

Pro Tip

Some models work only with reference image and some can work without it. If you do not want to provide reference image and want Image-to-Video to behave like Text-to-Video model, then a pro tip is that you upload reference image with white or transparent background. You can also guide the model through prompt to ignore background reference image.

📸 Image Upload Guidelines

To ensure the best video quality and avoid "Invalid Frame" errors, please follow these requirements for your reference images

1. Match Your Aspect Ratio

The most common cause of failure is a mismatch between your Image Shape and your Target Platform.

For TikTok / Instagram Reels: Upload Vertical (9:16) images.

For YouTube / Cinematic: Upload Horizontal (16:9) images.

For Facebook / Feed Posts: Upload Square (1:1) images.

Tip: If you upload a Square image but select "Instagram (9:16)" as the platform, the generation may fail because the AI cannot "fill in" the missing top and bottom of the frame.

2. Supported Formats & Size

Formats: .jpg, .jpeg, .png, or .webp.

Max Size: Keep image files under 5MB for faster processing.

Resolution: Aim for at least 720px on the shortest side. Low-resolution "thumbnails" will result in blurry, pixelated videos.

3. Subject Placement

The AI uses the first image as the "anchor." Ensure your product is:

Centered: Keep the main subject in the middle of the frame.

Unobstructed: Avoid heavy text overlays or watermarks on the reference images, as the AI will try to "melt" or animate the text.

Workflow automation

Integrate AI Video Ads Generator with any app and automate your workflow such as "Make" [https://www.make.com/en], "Zapier" [https://zapier.com/], "n8n" [https://n8n.io/], etc."

If you’re looking to weave this into a larger tech stack or automate your content pipeline, you can bypass the manual interface and interact with the AI Video Ads Generator via the Apify API.

Developer Integration

You can get started quickly by installing the official client libraries for your preferred environment:

Node.js: Add the apify-client package via NPM.

Python: Grab the apify-client package from PyPI.

Check this API documentation: [https://docs.apify.com/api/v2]

You can use it with other actors too. One actor that you can use it with is:

(This actor generates AI based audio voiceovers for your video Ads) [https://apify.com/peaceful_pushpins/ai-video-to-voiceover-generator]

Retention policy

The retention policy of data for this actor is 31 days. However, there is also a video url generated by third-party service and they wrote that url link is valid for 7 days. However, links can be broken for several reasons before this. Therefore, this actor also downloads and save video in Apify store. You can access that link through "apifyVideoUrl" output. Still it is best for you you download a video on local device and export data.

Error Handling & Support

The actor can fail due to many reasons because it rely on third party services. We tested it and always trying to improve it's performance. It is good to wait for actor to complete it's job. However, if you found any technical issue or bug you can create an issue on the Actor'sIssues tab.

💸 Payment Structure

This Actor uses a Pay-Per-Event (PPE) monetization model to give you maximum flexibility and control over your budget. Instead of a flat fee, you only pay for the specific AI "brain power" and video length you choose.

• Entry-Level Pricing: Standard 3-second generations using our Basic Tier models (like Wan 2.7) start as low as $2.00.

• Professional Tiering: Intermediate models (Seedance 1.0, Kling Pro) offer a balance of quality and cost, while Premium Tiers (Kling Master, Google Veo 3.1) provide cinematic-grade results for high-stakes campaigns.

• Maximum Efficiency: Most high-definition, 8-10 second cinematic videos are capped around $8.30, offering a 50%-60% saving compared to the industry average of $30.00.

✨ Latest Update?

Due to the sudden backend provider changes, Seedance 1.0 lite, "Wan 2.2" and "OpenAI Sora" models became unavailable. Therefore, I updated these models to Seedance 2.0 and Wan 2.7 models. Please note that for Wan 2.7, you can upload up to 1-2 images. i.e. First frame image or Second frame image. Third reference image will be automatically ignored or used as a second image. Added Google Veo 3.1 with support for longer videos up to 64 seconds.

License

This actor is provided as-is. The user who generates content using this tool owns the resulting video outputs. By using this actor, you agree to comply with the individual usage policies and terms of service of the underlying model providers (including but not limited to OpenAI, Google, Alibaba Wan, Kling, and MiniMax). You claim full rights over your generated content and you are fully accountable for your use of the models. You must not generate or share content that violates applicable laws, causes harm to individuals or groups, disseminates private personal information, spreads misinformation, or targets vulnerable populations.