ali-vilab/i2vgen-xl 🔢🖼️📝 → 🖼️

▶️ 128.0K runs 📅 Aug 2023 ⚙️ Cog 0.8.6 🔗 GitHub 📄 Paper

image-to-video

About

RESEARCH/NON-COMMERCIAL USE ONLY: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models

Example Output

Prompt:

"A blonde girl in jeans"

Output

Performance Metrics

115.80s Prediction Time

115.82s Total Time

All Input Parameters

{
  "image": "https://replicate.delivery/pbxt/KA6KcZp2UhselAqryBuWaIV2w3KPKYJpVM9cQtqSctlhwdK5/img_0002.png",
  "prompt": "A blonde girl in jeans",
  "max_frames": 16,
  "guidance_scale": 9,
  "num_inference_steps": 50
}

Input Parameters

seed Type: integer: Random seed. Leave blank to randomize the seed
image (required) Type: string: Input image.
prompt (required) Type: string: Describe the input image.
max_frames Type: integerDefault: 16Range: 2 - ∞: Number of frames in the output
guidance_scale Type: numberDefault: 9Range: 1 - 20: Scale for classifier-free guidance
num_inference_steps Type: integerDefault: 50Range: 1 - 500: Number of denoising steps

Output Schema

Output

Type: string • Format: uri

Example Execution Logs

Using seed: 25382
GPU Memory used 36.12 GB

Version Details

Version ID: 5821a338d00033abaaba89080a17eb8783d9a17ed710a6b4246a18e0900ccad4
Version Created: January 4, 2024

Run on Replicate →