0x1355

I am trying out deforum. Will take a look at this. Seems an epic. But maybe we can do this piece by piece.

Back from deforum land. Will put my thoughts in words tomorrow.

**TL;DR** Low impact. High effort. Personally I would prioritize for something else for now. **Low impact** deforum has 2D, 3D, video_input, and interpolation animation modes. In comparison, sd-videos only does...

Same issue on 4090. IPAdapter part of the workflow:  `--gpu-only` doesn't change this behavior.

Interesting. Why don't the example videos have watermarks then?

Thanks @bonlime . You are fast! @guoyww How much compute was used to trained each motion model? I couldn't seem to find that in the paper or in the repo?...

Having similar issue on main branch, but when training SDXL lora, I can see:  So Text Encoder LR displays as expected but UNET LR not.

> > Having similar issue on main branch, but when training SDXL lora, I can see: > > [snip] > > So Text Encoder LR displays as expected but UNET...

A Prodigy default setting run, using cosine with hard restart, single cycle. Stopped early:  The whole setting or just the optimizer part? run settings ```JSON { "__version": 4, "training_method":...

I was expecting the LR to be more 'rough' and not 'smooth', due to adaptive optimizer modifying LR throughout the run, like this example shown on the Optimizer wiki page:...