You'll need to download ComfyUI-LTX-Reframe nodes from my repo:<a target="_blank" rel="ugc" href="https://github.com/exportAnything/ComfyUI-LTX-Reframe">https://github.com/exportAnything/ComfyUI-LTX-Reframe</a>The node pack includes:<code>LTX Reframe Layout</code>- Selects a source video, previews and serializes its placement, optionally selects an LTX-compatible frame range, and outputs padded frames, masks, audio, FPS, video, target dimensions, and placement metadata.<code>LTX Reframe Target Fit</code>- Center-fits an image batch to the exact target canvas dimensions.<code>LTX Reframe Rectilinear Correction</code>- Applies a deterministic, mask-aware barrel-to-rectilinear correction to a generated frame batch.<code>LTX Reframe Custom Audio Loader</code>- Loads optional custom audio only when its lazy workflow branch executes.The models needed for this workflow are linked in the repo.***UPDATE*** Users experiencing magenta output is caused by substituting the workflow’s expected 3K LoRA with the 10K version; those weights are not interchangeable in this workflow. Thank you EKKIVOK for figuring this out.

Files with SHA256: 332dd892d1993481150481a4ed1ccabb7689c50b59a6e137bc4b40bd9293baf1