Edit: I've tried both lora's recently, and I will argue that <a target="_blank" rel="ugc" href="https://civarchive.com/models/2088559/cinematic-hard-cut">https://civarchive.com/models/2088559/cinematic-hard-cut</a> is better, for fast cutting, too. Especially for maintaining likeness. I will integrate these training clips in the next version of Hard cut and hopefully improve it even more."Fast cutting" is apparently the correct term: <a target="_blank" rel="ugc" href="https://en.wikipedia.org/wiki/Fast_cutting">https://en.wikipedia.org/wiki/Fast_cutting</a>This lora is trained on "quick cuts", an editing technique that tells the story of a whole scene in a couple of seconds. I figured it would be suitable for the constrained context window local video producers have to work with.Consider it experimental, as the dataset is quite limited at the moment. It may collapse completely on unseen data.It's trained on shot concepts like "wide-angle shot", "mid-shot", "close-up shot" and (which is often used for quick cuts, "extreme close-up shot".The format is:A series of quick cuts:<ol><li>[shot one]</li><li>[shot two]</li><li>[shot three]</li></ol>...Each cut has (about) one sentence description. You may specify angle, too.It's trained on between 3 and 5 shots, over a very short time. Going for the full 81 frames might make it lose strength.Tested both with T2V and I2V (but trained on I2V).Only high noise required.

Cinematic Fast Cutting (previously Quick Cuts)

Larger dataset, slightly larger resultion. Less epochs.

Files with SHA256: d9077681dc4540b49d9716531050c915524d64cff138bf2aa33f3bdcce94d6e9