minimax/video-01 📝✓🖼️ → 🖼️

⭐ Official ▶️ 643.7K runs 📅 Nov 2024 ⚙️ Cog 0.16.8 ⚖️ License
image-to-video text-to-video video-consistent-character-generation

About

Generate 6s videos with prompts or images. (Also known as Hailuo). Use a subject reference to make a video with a character and the S2V-01 model.

Example Output

Prompt:

"a woman is walking through a busy Tokyo street at night, she is wearing dark sunglasses"

Output

Performance Metrics

156.86s Prediction Time
156.88s Total Time
All Input Parameters
{
  "prompt": "a woman is walking through a busy Tokyo street at night, she is wearing dark sunglasses",
  "prompt_optimizer": true
}
Input Parameters
prompt (required) Type: string
Text prompt for generation
prompt_optimizer Type: booleanDefault: true
Use prompt optimizer
first_frame_image Type: string
First frame image for video generation. The output video will have the same aspect ratio as this image.
subject_reference Type: string
An optional character reference image to use as the subject in the generated video (this will use the S2V-01 model)
Output Schema

Output

Type: stringFormat: uri

Example Execution Logs
Generating video...
Still generating...
Still generating...
Still generating...
Still generating...
Generated video in 153.4sec
Retrieving file...
Downloading 1901912 bytes
Downloaded 1.81MB in 2.69sec
Version Details
Version ID
5aa835260ff7f40f4069c41185f72036accf99e29957bb4a3b3a911f3b6c1912
Version Created
November 7, 2025
Run on Replicate →