YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

Locomotion v1 LCM

Important!! - Install in Amuse using the Locomotion LCM template.

Supports:

  • TextToVideo
  • ImageToVideo
  • VideoToVideo

Settings & Controls

Name Default Description
Resolution 512×512 Sets the output video size from a fixed list of supported resolutions. Higher resolutions take longer to process.
Input FPS 24 FPS For Text-to-Video and Image-to-Video, this sets how many frames per second are created. Higher FPS results in smoother motion but requires more processing.
Output FPS 24 FPS Sets the final playback framerate. A higher FPS speeds up the motion, while a lower FPS slows it down.
Key Frames 16 Locomotion processes 16 key frames per batch. To create longer videos, multiple batches are blended together during each iteration of the StableDiffusion process.
The total must be a multiple of 16 (e.g., 32, 48, 64). More key frames result in longer animations but require more steps and blending for consistency.
Noise Repeat 16 Repeating the same noise pattern helps maintain consistency across extended animations. The value must be divisible by Key Frames.
Strides 0 Adjusts how frames are strided in long videos. Higher values refine frame transitions and improve motion consistency.
Overlap 3 frames Defines how many frames overlap during blending. Overlapping improves motion consistency by smoothing transitions.
HQ Off Enables experimental video resampling, boosting output resolution by 2×, but increases processing time.
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.