Age | Commit message (Collapse) | Author |
|
torch.manual_seed() already sets a CPU generator, so there is no reason to create a CPU generator manually. torch.randn_like also needs a MPS fix for k-diffusion, but a torch hijack with randn_like already exists so it can also be used for that.
|
|
|
|
Clip skip + ENSD to parameters
|
|
#3449 - VRAM leak when switching to/from inpainting checkpoint
|
|
|
|
|
|
|
|
|
|
|
|
sampler index
|
|
|
|
|
|
|
|
|
|
with hires fix
|
|
* Save image/s before doing highres fix.
|
|
Add mid-kdiffusion cfgdenoiser script callback - access latents, conditionings and sigmas mid-sampling
|
|
|
|
|
|
|
|
|
|
|
|
added an option to always only show one image in previews
removed duplicate code
|
|
|
|
|
|
|
|
|
|
highres_fix generation.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
https://energy-based-model.github.io/Compositional-Visual-Generation-with-Composable-Diffusion-Models/
|
|
Unexpected behavior when using eta = 0 in something like XY, but your default eta was set to something not 0.
|
|
disabled printing prompts to console by default, enabled by --enable-console-prompts
|
|
|
|
|
|
|
|
|
|
|