wan-video/wan2.6-i2v-flash 🔢🖼️📝❓✓ → 🖼️
About
Image-to-video generation with optional audio, multi-shot narrative support, and faster inference
Example Output
Prompt:
"A female race car driver pulls down the shade of her helmet as the camera zooms out. White letters show up in the center that reads: "Wan 2.6 Flash""
Output
Performance Metrics
50.16s
Prediction Time
50.18s
Total Time
All Input Parameters
{
"image": "https://replicate.delivery/pbxt/OX33CxoszBgDjIyUp9f4qIcU8A4fwFyg2nxHeTzg7pSPyB1l/replicate-prediction-an1ppfzqynrmt0cw59stqd909c.jpg",
"prompt": "A female race car driver pulls down the shade of her helmet as the camera zooms out. White letters show up in the center that reads: \"Wan 2.6 Flash\"",
"duration": 5,
"resolution": "720p",
"multi_shots": false,
"audio_enabled": true,
"negative_prompt": "",
"enable_prompt_expansion": true
}
Input Parameters
- seed
- Random seed for reproducible generation
- audio
- Audio file (wav/mp3, 3-30s, ≤15MB) for voice/music synchronization
- image (required)
- Input image for video generation
- prompt (required)
- Text prompt for video generation
- duration
- Duration of the generated video in seconds
- resolution
- Video resolution
- multi_shots
- Enable intelligent multi-shot segmentation (only active when enable_prompt_expansion is enabled). True enables multi-shot segmentation, false generates single-shot content.
- audio_enabled
- Whether to generate video with audio. When enabled, the model will auto-generate audio or use provided audio file. Disable for silent video output.
- negative_prompt
- Negative prompt to avoid certain elements
- enable_prompt_expansion
- If set to true, the prompt optimizer will be enabled
Output Schema
Output
Example Execution Logs
Using seed: 1449367419 Generating video with Wan 2.6 I2V Flash... Generated video in 46.9sec Downloading 4417823 bytes Downloaded 4.21MB in 2.67sec
Version Details
- Version ID
735e10a03f2576105c76169aa10afc22179ce07c94001ec7aaaaf9c6b99af47f- Version Created
- February 4, 2026