Generate text, image, and video-to-video clips with WAN 2.6 via KIE.AI

This n8n template provides a comprehensive suite of WAN 2.6 video generation capabilities through the KIE.AI API. The workflow includes three independent video generation workflows: text-to-video, image-to-video, and video-to-video. Each workflow can be used independently to create videos from different input types, making it perfect for content creators, marketers, and video production teams.

Use cases are many: Create videos from text descriptions without any input media, transform static images into animated videos, enhance existing videos with new styles and effects, generate engaging video content for social media, automate video production workflows, create video variations from the same source, produce marketing videos at scale, repurpose content across different video formats, or streamline video creation pipelines for content teams!

Good to know

- The workflow includes three independent WAN 2.6 video generation capabilities via KIE.AI API: - Text-to-Video: Creates videos directly from text prompts without requiring input images or videos - Image-to-Video: Transforms static images into animated videos based on text prompts - Video-to-Video: Enhances or transforms existing videos with new styles and effects - Each workflow can be used independently based on your input type and needs - Supports two resolution options: 720p or 1080p - Supports three duration options: 5, 10, or 15 seconds - Text-to-video creates videos purely from text descriptions - no media input required - Image-to-video animates static images with customizable prompts for style and movement - Video-to-video allows you to transform existing videos with new visual styles and effects - KIE.AI pricing: Check current rates at https://kie.ai/ for video generation costs - Processing time: Varies based on video length and KIE.AI queue, typically 1-5 minutes for generation - Media requirements: Image and video files must be publicly accessible via URL (HTTPS recommended) - Supported image formats: PNG, JPG, JPEG, WEBP - Supported video formats: MP4, MOV, AVI, WEBM - Automatic polling system handles processing status checks and retries for all workflows

How it works

The template includes three independent workflows that can be used separately based on your input type:

1. Text-to-Video (Top Section): 1. Video Parameters Setup: Set prompt, duration (5, 10, or 15 seconds), and resolution (720p or 1080p) in 'Set Video Parameters' node 2. Video Generation Submission: Parameters are submitted to KIE.AI API using WAN 2.6 text-to-video model 3. Processing Wait: Workflow waits 5 seconds, then polls the generation status 4. Status Check: Checks if video generation is complete, queuing, generating, or failed 5. Polling Loop: If still processing, workflow waits and checks again until completion 6. Video URL Extraction: Once complete, extracts the generated video file URL from the API response 7. Video Download: Downloads the generated video file for local use

2. Image-to-Video (Middle Section): 1. Video Parameters Setup: Set prompt, image URL, duration, and resolution in 'Set Prompt & Image Url' node 2. Video Generation Submission: Parameters are submitted to KIE.AI API using WAN 2.6 image-to-video model 3. Processing Wait: Workflow waits 5 seconds, then polls the generation status 4. Status Check: Checks if video generation is complete, queuing, generating, or failed 5. Polling Loop: If still processing, workflow waits and checks again until completion 6. Video URL Extraction: Once complete, extracts the generated video file URL from the API response 7. Video Download: Downloads the generated video file for local use