wan-video/wan-2.6-t2v 🔢❓🖼️📝✓ → 🖼️

⭐ Official ▶️ 3.3K runs 📅 Dec 2025 ⚙️ Cog 0.16.9

About

Alibaba Wan 2.6 text to video generation model

Example Output

Prompt:

"Slow-motion dolly zoom on a fearless warrior in ancient armor charging through a misty battlefield, sword raised high, rain pouring down, dramatic side lighting, epic orchestral swell in the background, high detail, realistic physics"

Output

Performance Metrics

243.30s Prediction Time

243.31s Total Time

All Input Parameters

{
  "size": "1280*720",
  "prompt": "Slow-motion dolly zoom on a fearless warrior in ancient armor charging through a misty battlefield, sword raised high, rain pouring down, dramatic side lighting, epic orchestral swell in the background, high detail, realistic physics",
  "duration": 10,
  "multi_shots": true,
  "negative_prompt": "",
  "enable_prompt_expansion": true
}

Input Parameters

seed Type: integer: Random seed for reproducible generation
size Default: 1280*720: Video resolution and aspect ratio
audio Type: string: Audio file (wav/mp3, 3-30s, ≤15MB) for voice/music synchronization
prompt (required) Type: string: Text prompt for video generation
duration Default: 5: Duration of the generated video in seconds
multi_shots Type: booleanDefault: false: Enable intelligent multi-shot segmentation (only active when enable_prompt_expansion is enabled). True enables multi-shot segmentation, false generates single-shot content.
negative_prompt Type: stringDefault:: Negative prompt to avoid certain elements
enable_prompt_expansion Type: booleanDefault: true: If set to true, the prompt optimizer will be enabled

Output Schema

Output

Type: string • Format: uri

Example Execution Logs

Using seed: 1344585636
Generating video with Wan 2.6 T2V...
Generated video in 241.7sec
Downloading 5671704 bytes
Downloaded 5.41MB in 0.80sec

Version Details

Version ID: e26da39f3adc03385c49adb156263148660557d28f3e26bcdb331b174a794077
Version Created: December 15, 2025

Run on Replicate →