Untitled Workflow
Asynchronous AI processing pipeline designed for high-performance automation.
This workflow has no configurable inputs. Check the visual builder to add task inputs.
Overview
About this workflow
This workflow is an asynchronous AI processing pipeline. Submit your inputs and receive results when the pipeline completes.
Quick Integration
Use via REST API
Submit inputs to POST /workflow/product-video-ad-maker-flux-2-pro-wan2-5/api-execute and poll GET /workflow/run/{run_id}/status until the run completes. Switch to the for full code examples.
About Product Video Ad Maker with Flux 2 Pro + Wan2.5 I2V Fast
This workflow converts a static product image into a ready-to-publish video advertisement in a single automated pipeline. A Vision AI step analyses your product and generates an optimised prompt, which Flux 2 Pro uses to produce a high-fidelity product image. Wan2.5 Image-to-Video then animates that image into fluid motion video.
The result is a short-form video ad suitable for Instagram Reels, TikTok, and paid social — produced in minutes rather than days. The LLM reasoning step fine-tunes the prompt to match the product category and brand tone before any image generation occurs.
Models Used
How It Works
- 1
Vision analysis
Vision AI reads your product image and extracts key attributes — shape, colour, material, and style.
- 2
Prompt refinement
LLM reasoning builds a detailed generation prompt tailored to the product category and ad format.
- 3
Image generation
Flux 2 Pro renders a clean, high-fidelity product image from the refined prompt.
- 4
Video animation
Wan2.5 I2V animates the image with smooth, natural motion suitable for social video ads.
Use Cases
- Generate video ads for new product launches
- Produce animated social content from existing product photography
- A/B test different visual styles for the same SKU
- Create short-form content for paid social campaigns
- Automate video production for large product catalogues
Who Is This For
Frequently Asked Questions
- What image format should I upload?
- Any standard JPEG or PNG product image works. A clean background improves output consistency.
- How long is the output video?
- Wan2.5 I2V produces clips typically between 3–6 seconds — ideal for social ad formats.
- Can I run this for multiple products?
- Yes. Submit each product image separately, or batch them via the Muapi API.
- Do I need to write prompts?
- No — the Vision AI and LLM steps generate the prompt automatically from your product image.