If image_cfg_scale is =1 then the original image is not used for the output. We can then use the original CFGDenoiser to get the same result to support AND functionality.

Maybe in the future AND can be supported with "Image CFG Scale"

Uses separate denoiser for edit (instruct-pix2pix) models

No impact to txt2img or regular img2img

"Image CFG Scale" will only apply to instruct-pix2pix models and metadata will only be added if using such model

Allows instruct-pix2pix

This reverts commit 26983306.

X/Y/Z plot now saves sub grids if opts.grid_save and honors draw_legend

Fixes switch height/width btn unbound error

[Prompt Matrix] Support for negative prompt + delimiter selector

Fix missing tooltip for 'Clear prompt' button

Changes use_original_name_batch to default to True

Refactor MPS PyTorch fixes, add fix still required for PyTorch nightly builds back

Apparently I did not test with large enough images to trigger the bug with torch.narrow on MPS

Adding default true to use_original_name_batch as images should by default hold the same name to help keep sequenced images in their correct order

disable EMA weights for instructpix2pix model, whcih should get memory usage as well as image quality to what it was before d2ac95fa