Closed RainehDaze closed 1 year ago
Looking over the code I think the behavior is undefined for that case. It depends on the order in which the files are read, and whether or not it reads the X.pt or X-neg.pt file first. What would be a good way to handle that case? should it just ignore "-neg.pt" files?
Ignoring them would probably be best; these are technically just two entirely separate embeddings, which can have different numbers of vectors per embedding (they just train at the same time).
I don't have the DreamArtist extension installed so let me know if that update fixes the issue and ignores the -neg.pt files. I just manually renamed some to end with -neg.pt for testing on my side.
Looks good, skips the appropriate files. Only thing that'd help with DreamArtist embeddings more is the ability to specify the loss file manually--it's got a different name than the textual inversion one, so it has to be renamed for graphing. xD
Can you upload a screenshot of what the training folder looks like with the differently named .csv file?
Same structure, it's just called prompt_tuning_loss.csv instead.
As long as it has the same data format, that update should load it.
Yup, that works (although, as usual, the loss over time tells me pretty much nothing--are the blue and purple the trend over time or something? And why so short? xD)
The colored lines require more data points to work properly. You'd need to increase the rate at which the loss is saved in the A1111 settings, I set mine to 1.
Interesting little thing I observed when I was looking at DreamArtist-generated embeddings: both the positive (embedding-XXXX.pt) and negative (embedding-XXXX-neg.pt) files are read and loaded. I'm not quite sure what gets done with the negatives.