Set a seed for reproducibility. Random by default.

Image to use as a starting frame for image to video generation.

The number of frames to generate (1 to 5 seconds)

Default

81

Text prompt for video generation

Speed up generation with different levels of acceleration. Faster modes may degrade quality somewhat. The speedup is dependent on the content, so different videos may see different speedups.

Default

"Balanced"

The resolution of the video. 720p is not supported for 1.3b.

Default

"480p"

The aspect ratio of the video. 16:9, 9:16, 1:1, etc.

Default

"16:9"

Sample shift factor

Default

8

Maximum

10

Number of generation steps. Fewer steps means faster generation, at the expensive of output quality. 30 steps is sufficient for most prompts

Default

30

Minimum

1

Maximum

60

Things you do not want to see in your video

Strength of the LORA applied to the CLIP model. 0.0 is no LORA.

Default

1

Higher guide scale makes prompt adherence better, but can reduce variation

Default

5

Maximum

10

Strength of the LORA applied to the model. 0.0 is no LORA.

Default

1