Fooocus/modules
xhoxye db7d2018ca
fix: change synthetic refiner switch from 0.5 to 0.8 (#2165)
* fix problem

1. In partial redrawing, when refiner is empty, enable use_synthetic_refiner. The default switching timing of 0.5 is too early, which is now modified to SDXL default of 0.8.
2. When using custom steps, the calculation of switching timing is wrong. Now it is modified to calculate "steps x timing" after custom steps are used.

* fix: parse width and height as int when applying metadata (#2452)

fixes an issue with A1111 metadata scheme where width and height are strings after splitting resolution

* fix: do not attempt to remove non-existing image grid file (#2456)

image grid is actually not an image here but a numpy array, as the grid isn't saved by default

* feat: add troubleshooting guide to bug report template again (#2489)

---------

Co-authored-by: Manuel Schmid <9307310+mashb1t@users.noreply.github.com>
Co-authored-by: Manuel Schmid <manuel.schmid@odt.net>
2024-03-10 14:42:03 +01:00
..
anisotropic.py 1.0.45 (#313) 2023-09-02 06:00:20 -07:00
async_worker.py fix: change synthetic refiner switch from 0.5 to 0.8 (#2165) 2024-03-10 14:42:03 +01:00
auth.py Blocked remote access to auth.json 2023-10-24 21:55:29 +02:00
config.py feat: add performance lightning with 4 step LoRA (#2415) 2024-03-10 14:34:48 +01:00
constants.py Blocked remote access to auth.json 2023-10-24 21:55:29 +02:00
core.py feat: add ability to load checkpoints and loras from multiple locations (#1256) 2024-02-25 12:47:14 +01:00
default_pipeline.py feat: add ability to load checkpoints and loras from multiple locations (#1256) 2024-02-25 12:47:14 +01:00
flags.py feat: add performance lightning with 4 step LoRA (#2415) 2024-03-10 14:34:48 +01:00
gradio_hijack.py try fix #815 2023-10-29 22:03:59 -07:00
html.py feat: adjust width of lora_weight for firefox (#2431) 2024-03-03 21:15:42 +01:00
inpaint_worker.py [enhance]: use opencv to rewrite morphological_open(), achieve a 40x speed increase in morphological_open opporation, for inpanting images size smaller than 3k (#2016) 2024-01-27 05:12:34 -08:00
launch_util.py fix: replace regexp to support unicode chars (#1424) 2024-02-10 19:15:57 +01:00
localization.py 2.1.808 2023-11-14 14:06:12 -08:00
lora.py 2.1.826 2023-12-12 11:38:05 -08:00
meta_parser.py feat: use jpeg instead of jpg, use enums instead of strings (#2453) 2024-03-09 16:00:25 +01:00
model_loader.py 2.0.80 (#520) 2023-10-03 10:36:42 -07:00
ops.py (requested) support AMD 8GB GPUs via Windows DirectML 2023-12-30 06:30:59 -08:00
patch_clip.py (requested) support AMD 8GB GPUs via Windows DirectML 2023-12-30 06:30:59 -08:00
patch_precision.py Fix many precision problems 2023-12-16 15:55:53 -08:00
patch.py feat: advanced params refactoring + prevent users from skipping/stopping other users tasks in queue (#981) 2024-02-24 19:01:06 +01:00
private_logger.py feat: use jpeg instead of jpg, use enums instead of strings (#2453) 2024-03-09 16:00:25 +01:00
sample_hijack.py (requested) support AMD 8GB GPUs via Windows DirectML 2023-12-30 06:30:59 -08:00
sdxl_styles.py feat: match anything in array syntax, not only words and whitespace (#2438) 2024-03-04 11:22:24 +01:00
style_sorter.py Add Marc K3nt3L's styles 2023-12-18 19:01:52 -08:00
ui_gradio_extensions.py feat: adds preview overlay for styles (#1762) 2024-01-07 15:10:42 -08:00
upscaler.py 2.1.826 2023-12-12 11:38:05 -08:00
util.py feat: add docker files (#1418) 2024-02-26 17:30:05 +01:00