Video Generation With Audio

Wan 2.6 I2V Flash

Convert images into high-quality videos with multi-shot support and auto dubbing.

Typical generation time: 60-120 seconds

Model

Detailed description of the desired video content and motion (max 1500 characters)

Base Image

  • Uploaded image

URL or base64 of the first frame image to animate

Upload Audio

URL of audio file for automatic dubbing (wav/mp3, 3-30 seconds, mono/stereo, ≤10MB)

Video resolution. Higher resolution = higher cost.

Video duration in seconds (2-15). Longer duration = higher cost.

Content to exclude from the video (max 500 characters)

Enable AI-powered prompt enhancement using LLM

Single: coherent single scene | multi: multi-shot narrative with transitions

Generate video with audio (true) or silent (false). Silent = lower cost.

Enable prompt enhancement for better results

Explore example prompts and their results.

  • Example 1Video
  • Example 2Video
  • Example 3Video

Similar Models

Community