wan-video/wan-2.2-5b-fast 🔢🖼️📝✓❓ → 🖼️

⭐ Official ▶️ 201.4K runs 📅 Aug 2025 ⚙️ Cog 0.15.9

image-to-video text-to-video

About

The fastest Wan 2.2 text-to-image and image-to-video model

Example Output

Prompt:

"a car is driving at speed along a runway, it leaves us in the dust"

Output

Performance Metrics

12.99s Prediction Time

13.00s Total Time

All Input Parameters

{
  "image": "https://replicate.delivery/pbxt/NUHxZDgAgbYuAihJY7P9LBb7Qjcqxf5VHxRMErQAYmW5S27r/image.png",
  "prompt": "a car is driving at speed along a runway, it leaves us in the dust",
  "go_fast": true,
  "num_frames": 121,
  "resolution": "720p",
  "aspect_ratio": "16:9",
  "sample_shift": 12,
  "frames_per_second": 24
}

Input Parameters

seed Type: integer: Random seed. Leave blank for random
image Type: string: Input image to generate video from.
prompt (required) Type: string: Prompt for video generation
go_fast Type: booleanDefault: true: Go fast
num_frames Type: integerDefault: 121Range: 81 - 121: Number of video frames. 81 frames give the best results
resolution Default: 720p: Resolution of video. 16:9 corresponds to 832x480px, and 9:16 is 480x832px
aspect_ratio Default: 16:9: Aspect ratio of video. 16:9 corresponds to 832x480px, and 9:16 is 480x832px
sample_shift Type: numberDefault: 12Range: 1 - 20: Sample shift factor
frames_per_second Type: integerDefault: 24Range: 5 - 30: Frames per second. Note that the pricing of this model is based on the video duration at 16 fps
disable_safety_checker Type: booleanDefault: false: Disable safety checker for generated video.

Output Schema

Output

Type: string • Format: uri

Example Execution Logs

initial image size: (1344, 768)
processed image size: (1248, 704)
Inference took 11.27 seconds

Version Details

Version ID: c92ab4265c9b3b5ea9ac9a87df839ebfd662ee3a820d62c21305bf6501a73fe1
Version Created: August 8, 2025

Run on Replicate →