Peter Sdobnov

Results 27 comments of Peter Sdobnov

> if you want, you can try out https://github.com/vladmandic/sd-extension-steps-animation, simply don't save video, set intermediate images to be left on disk and skip n initial steps. Not exactly what I'm...

Can confirm, it only complains about no ffmpeg if "Create animation" is checked

> requested steps vs executed steps is not the same So when you interrupt image generation and it turns out good, there is no easy way to reproduce it because...

> I am able to train both textual inversion and LoRA's (unet only) in 4gb, using https://github.com/kohya-ss/sd-scripts does it actually work on 4 Gb VRAM, or you mean CPU? how...

would be even better if there was some sort of syntax highlighting on invalid parts of the prompt

> I was still able to run generations at 800x450 or 480x600 and upscale them at x2. Now I can only upscale the 480x600 at x1.5 and I can't upscale...

> The UI saves every image generated in %TEMP%/tmpXXXXXXXX/, regardless of your folder and save settings. Not just that, it creates *multiple copies* of generated files, and not like 2-3...

Yeah this it is quite annoying. If only we could view these graphs inside the actual program window, instead of having to use a whole web browser just to view...

> it would be a nice feature to have all generated loras in one path Not sure why this isn't the default - if the whole point of making backups...

> Backups are for the trainer and training. Saves are for testing intermediate steps in your inference tool of choice. Oh I see, somehow I got them confused. Btw the...