Public/automatic
1
0
Fork 0
mirror of https://github.com/vladmandic/automatic synced 2026-09-19 01:04:32 +02:00
Code Issues Packages Projects Releases Wiki Activity

flag backend=original

Browse Source
This commit is contained in:
Vladimir Mandic
2024-09-14 10:38:06 -04:00
parent 1b97e62121
commit c07e7c765d
2 changed files with 16 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CHANGELOG.md
+12 -11
View File
@@ -2,20 +2,21 @@
## Update for 2024-09-14
- hf force logout/login on token change
- flux avoid unet load if unchanged
- flux mark specific unet as unavailable if load failed
- xyz grid full refactor
- xyz grid multi-mode: *selectable-script* and *alwayson-script*
- xyz grid allow usage combined with other scripts
- xyz grid allow **unet** selection
- hf force logout/login on token change
- flux avoid unet load if unchanged
- flux mark specific unet as unavailable if load failed
- xyz grid full refactor
- xyz grid multi-mode: *selectable-script* and *alwayson-script*
- xyz grid allow usage combined with other scripts
- xyz grid allow **unet** selection
- xyz grid allow passing **model args** directly:
allowed params will be checked against models call signature
example: `width=768; height=512, width=512; height=768`
example: `width=768; height=512, width=512; height=768`
- xyz grid allow passing **processing args** directly:
params are set directly on main processing object and can be known or new params
example: `steps=10, steps=20; test=unknown`
- minor ui fixes
params are set directly on main processing object and can be known or new params
example: `steps=10, steps=20; test=unknown`
- backend=original is now marked as in maintenance-only mode
- minor ui fixes
## Update for 2024-09-13
modules/shared.py
+4
View File
@@ -1060,6 +1060,10 @@ if cmd_opts.use_xformers:
opts.data['uni_pc_lower_order_final'] = opts.schedulers_use_loworder # compatibility
opts.data['uni_pc_order'] = opts.schedulers_solver_order # compatibility
log.info(f'Engine: backend={backend} compute={devices.backend} device={devices.get_optimal_device_name()} attention="{opts.cross_attention_optimization}" mode={devices.inference_context.__name__}')
if not native:
log.warning('Backend=original is in maintainance-only mode')
opts.diffusers_offload_mode = 'none'
try:
log.info(f'Device: {print_dict(devices.get_gpu_info())}')
except Exception as ex: