master-ce1bcc7

feat: add AYS(Align Your Steps) scheduler (#241)

Added NVIDEA's new "Align Your Steps" style scheduler in accordance with their
quick start guide. Currently has handling for SD1.5, SDXL, and SVD, using the
noise levels from their paper to generate the sigma values. Can be selected
using the --schedule ays command line switch. Updates the main.cpp help
message and README to reflect this option, also they now inform the user
of the --color switch as well.

---------

Co-authored-by: leejet <[email protected]>

master-760cfaa

fix: ignore tensors with the particular dim while loading (#233)

master-6d16f68

fix: correct upscale progressbar (#232)

master-ec82d52

refector: remove some useless code

master-036ba9e

feat: enable controlnet and photo maker for img2img mode

master-afea457

fix: support more SDXL LoRA names (#216)

* apply pmid lora only once for multiple txt2img calls

* add better support for SDXL LoRA

* fix for some sdxl lora, like lcm-lora-xl

---------

Co-authored-by: bssrdf <[email protected]>
Co-authored-by: leejet <[email protected]>

master-646e776

fix: fix tiles_ctx not freed in sd_tiling (#219)

master-3ac48ea

fix: use static implementation of stb_image_resize

master-90e9178

fix: apply pmid lora only once for multiple txt2img calls (#208)

Co-authored-by: bssrdf <[email protected]>

master-48bcce4

fix: avoid double free and fix sdxl lora naming conversion

* Fixed a double free issue when running multiple backends on the CPU, eg: CLIP
and the primary backend, as this would result in the *_backend pointers both
pointing to the same thing resulting in a segfault when calling the
StableDiffusionGGML destructor.

* Improve logging to allow for a color switch on the command line interface.
Changed the base log_printf function to not bake the log level directly into
the log buffer as that information is already passed the logging function via
the level parameter and it's easier to add in there than strip it out.

* Added a fix for certain SDXL LoRAs that don't seem to follow the expected
naming convention, converts over the tensor name during the LoRA model
loading. Added some logging of useful LoRA loading information. Had to
increase the base size of the GGML graph as the existing size results in an
insufficient graph memory error when using SDXL LoRAs.

* small fixes

---------

Co-authored-by: leejet <[email protected]>