drhead

Changed it to copy the conds to device before applying repeat, and I also changed memory pinning so that it should only happen once and avoids unnecessary copies every step...

I don't know the exact details, but I'm fairly certain you shouldn't be using min-snr-gamma on Flux anyways. Flux has its own system of weighted timestep sampling which should be...

I have not trained anything on Flux, but larger loss values for some timesteps sounds normal for Flux's timestep sampling. Min-snr-gamma is a timestep weighting strategy. It simply is a...

currently finding that this breaks interrupting due to the extra thread, will have to find a way to fix that before this is merged.

> What do you think of this: #6124 There's still a few issues that I have to chase down but I can tell that this code isn't safe because it...

A notable discrepancy:  ("pillow (linear)" is applying the resize after a manual conversion to linear sRGB space, "reference (sRGB)" is the reference resizer run with `--no-gamma-handling`.) The correct behavior...

~~Another discrepancy I am noticing is a number of spots with relatively large differences along the edges of images, this might indicate that there's a problem with conv padding. Comparisons...

I have updated this to include Magic Kernel Sharp 2013 (at the suggestion of the creator -- it should have the same effects in combatting moire/blockiness while being slightly faster...

Yes, this is a magnetic HDD. The severely fragmented files are indeed much slower to read, and having these files written out in chunks further ends up breaking up the...

So, the intent of min-snr-gamma is to balance how important each timestep is, so that they are treated as equally important. Min-snr-gamma attempts to do this with a fixed formula,...