runwayml/gen-4.5 🔢🖼️📝❓ → 🖼️

⭐ Official ▶️ 13.7K runs 📅 Feb 2026 ⚙️ Cog 0.16.11
image-to-video text-to-video

About

State-of-the-art video motion quality, prompt adherence and visual fidelity

Example Output

Prompt:

"A dense, verdant jungle world made up of small lego-like pieces. We see a rainbow chameleon running through the 3D world, the camera in and out of focus."

Output

Performance Metrics

228.65s Prediction Time
228.66s Total Time
All Input Parameters
{
  "prompt": "A dense, verdant jungle world made up of small lego-like pieces. We see a rainbow chameleon running through the 3D world, the camera in and out of focus.",
  "duration": 10,
  "aspect_ratio": "16:9"
}
Input Parameters
seed Type: integer
Random seed. Set for reproducible generation
image Type: string
Optional initial image for video generation (first frame). If not provided, video will be generated from text only.
prompt (required) Type: string
Text prompt for video generation
duration Default: 5
Duration of the output video in seconds
aspect_ratio Default: 16:9
Video aspect ratio
Output Schema

Output

Type: stringFormat: uri

Example Execution Logs
Using seed: 1708253727
Generating text-to-video with ratio 1280:720 (16:9), duration 10s
Warning: No OID set
Generating video...
0%
2%
4%
6%
7%
9%
11%
14%
16%
19%
22%
25%
27%
30%
33%
35%
38%
41%
43%
46%
50%
52%
63%
75%
86%
Generated video in 227.0sec
Downloading 7440244 bytes
Downloaded 7.10MB in 0.24sec
Version Details
Version ID
2e10d5ae08888b39ed31c828003f4a5ddc89a7cdec3bc7a9926661e0d22cb034
Version Created
February 18, 2026
Run on Replicate →