cjwbw/videocrafter 🔢📝 → 🖼️

▶️ 127.4K runs 📅 Apr 2023 ⚙️ Cog 0.9.4 🔗 GitHub 📄 Paper ⚖️ License
text-to-video

About

VideoCrafter2: Text-to-Video and Image-to-Video Generation and Editing

Example Output

Prompt:

"With the style of van Gogh, A young couple dances under the moonlight by the lake."

Output

Performance Metrics

58.33s Prediction Time
212.63s Total Time
All Input Parameters
{
  "prompt": "With the style of van Gogh, A young couple dances under the moonlight by the lake.",
  "save_fps": 10,
  "ddim_steps": 50,
  "unconditional_guidance_scale": 12
}
Input Parameters
seed Type: integer
Random seed. Leave blank to randomize the seed
prompt Type: stringDefault: With the style of van gogh, A young couple dances under the moonlight by the lake.
Prompt for video generation.
save_fps Type: integerDefault: 10
Frame per second for the generated video.
ddim_steps Type: integerDefault: 50
Number of denoising steps.
unconditional_guidance_scale Type: numberDefault: 12
Classifier-free guidance scale.
Output Schema

Output

Type: stringFormat: uri

Example Execution Logs
Using seed: 33170
Seed set to 33170
DDIM scale True
ddim device cuda:0
/root/.pyenv/versions/3.11.7/lib/python3.11/site-packages/torch/utils/checkpoint.py:31: UserWarning: None of the inputs have requires_grad=True. Gradients will be None
warnings.warn("None of the inputs have requires_grad=True. Gradients will be None")
/root/.pyenv/versions/3.11.7/lib/python3.11/site-packages/torch/utils/checkpoint.py:31: UserWarning: None of the inputs have requires_grad=True. Gradients will be None
warnings.warn("None of the inputs have requires_grad=True. Gradients will be None")
Version Details
Version ID
02edcff3e9d2d11dcc27e530773d988df25462b1ee93ed0257b6f246de4797c8
Version Created
January 30, 2024
Run on Replicate →