RuneXX

/

LTX-2.3-Workflows

like 574

V2V - Extend Any Video towards Last Frame reference image

By request, a variant of extend any video, where you can input a last frame image to guide the extend towards.

The workflow comes with 2 types of end target:

• Guider: End frame image as guide, but with freedom for the model to give a natural result (might not always end exactly on end frame)
• Frame Injection: Inject last frame as image in the video, forcing the model to end on the exact image
  (but since the image is made in other models, sometimes a little flicker at end (that you can edit out)

With both single pass and 2-pass option.
Single pass will always be the most faithful to the input image, 2-pass is faster, and can add more details and enhance your input image.
Up to you ;-)

Can try it out here:
https://huggingface.co/RuneXX/LTX-2.3-Workflows/tree/main/Video-2-Video