camenduru/dynami-crafter-576x1024 🔢📝🖼️ → 🖼️

▶️ 17.7K runs 📅 Feb 2024 ⚙️ Cog 0.9.0-beta11 🔗 GitHub 📄 Paper ⚖️ License
image-to-video motion-control video-generation

About

Create a video from an image

Example Output

Output

Performance Metrics

228.04s Prediction Time
456.78s Total Time
All Input Parameters 
{
  "i2v_eta": 1,
  "i2v_seed": 123,
  "i2v_steps": 50,
  "i2v_motion": 4,
  "i2v_cfg_scale": 7.5,
  "i2v_input_text": "rocket launches",
  "i2v_input_image": "https://replicate.delivery/pbxt/KLre7ADFhbmP9FJh3soDttYBSeyNdE4dPmR8G2TL0YFRqk6L/girl07.png"
}
Input Parameters
i2v_eta Type: numberDefault: 1Range: 0 - 1
ETA
i2v_seed Type: integerDefault: 123Range: 0 - 10000
Random Seed
i2v_steps Type: integerDefault: 50Range: 1 - 60
Sampling steps
i2v_motion Type: integerDefault: 4Range: 1 - 20
Motion magnitude
i2v_cfg_scale Type: numberDefault: 7.5Range: 1 - 15
CFG Scale
i2v_input_text Type: stringDefault: man fishing in a boat at sunset
i2v_input_image (required) Type: string
Input image
Output Schema

Output

Type: string • Format: uri

Example Execution Logs 
Seed set to 123
start: rocket launches 2024-02-06 03:52:52
/root/.pyenv/versions/3.10.13/lib/python3.10/site-packages/torchvision/transforms/functional.py:1603: UserWarning: The default value of the antialias parameter of all the resizing transforms (Resize(), RandomResizedCrop(), etc.) will change from None to True in v0.17, in order to be consistent across the PIL and Tensor backends. To suppress this warning, directly pass antialias=True (recommended, future default), antialias=None (current default, which means False for Tensors and True for PIL), or antialias=False (only works on Tensors - PIL will still use antialiasing). This also applies if you are using the inference transforms from the models weights: update the call to weights.transforms(antialias=True).
warnings.warn(
Version Details
Version ID
e79ff8d01e81cbd90acfa1df4f209f637da2c68307891d77a6e4227f4ec350f1
Version Created
February 5, 2024
Run on Replicate →