Change a video into a slightly or very different video while staying true to the original movement and composition of the original.

Video2Video_Hunyuan.json

Key Inputs

Load Video: Use any Mp4 that you would like to create from

Frame load cap: how many desired frames in the output video (for Hunyuan, it must be a multiple of 4, plus 1. for example, 65, or 101)

Skip first frames: Start the AI process somewhere in further into the video's timeline

Select every nth frame: Only process every other Nth frame in the generated video

Width & height: In Pixels

Prompt: as descriptive a prompt as possible

Guidance Scale: Higher numbers follow the prompt more strictly

Flow Shift: For temporal consistency, adjust to tweak video smoothness.

Denoise Strength: The amount of variance in the new image. Higher has more variance.

File Format: H.264 and more

Output Path

../outputs/Video2Video_Hunyuan/

Examples