Public/automatic
1
0
Fork 0
mirror of https://github.com/vladmandic/automatic synced 2026-08-27 07:31:01 +02:00
Code Issues Packages Projects Releases Wiki Activity
5,682 Commits 4 Branches 34 Tags
4bfa2ee877ab0d7318e32500a8bdbb359690bc38
Commit Graph

776 Commits

Author SHA1 Message Date
Vladimir Mandic 348943fcee revert defaults changes 2023-08-29 11:03:21 -04:00
Aptronymist 90afba372c Default Settings Update 
Modified default settings to enable some often unused features, changed default image output to png, various performance increasing options on by default at moderate settings. Upscaling and background removal enabled by default so they're visible on the image options panel. Changed default extra networks view to cover with 100% height, sidebar changed to 60% width by default from 35%.
 2023-08-28 13:59:06 -04:00
Vladimir Mandic 48c0ce9b2b fix model lookups 2023-08-27 08:01:29 +00:00
Vladimir Mandic c4263da0e6 fix refiner reload/unload 2023-08-26 13:35:59 +00:00
Vladimir Mandic 0512e2973c refactor settings ui 2023-08-24 10:01:39 +02:00
Disty0 863fa38c24 OpenVINO fix model reloading 2023-08-23 00:31:43 +03:00
Vladimir Mandic 6a4d4ea5b7 update logging and model hashinh 2023-08-22 18:28:09 +00:00
Disty0 80d2cc46e8 Add precompile as an option 2023-08-22 13:21:25 +03:00
Disty0 374307dd8a Cleanup 2023-08-22 10:39:38 +03:00
Disty0 e70520efa9 Add --use-openvino 2023-08-22 03:02:19 +03:00
Vladimir Mandic 464810be9f fix unknown settings 2023-08-21 06:06:01 +00:00
Vladimir Mandic 4826197d5b Merge pull request #2047 from vladmandic/master 
update dev
 2023-08-20 14:43:09 +02:00
Disty0 1666ee68ad IPEX change default dtype to BF16 2023-08-19 19:44:58 +03:00
Vladimir Mandic 87bb354f4c implement hires for diffusers 2023-08-19 12:25:41 +00:00
Vladimir Mandic 5eac99d3f5 optimize diffusers memory handling 2023-08-18 20:41:34 +00:00
Vladimir Mandic 3d914688cc update metadata 2023-08-15 05:50:15 +02:00
Disty0 66394c8cd9 IPEX add OpenVINO as compile backend 2023-08-14 21:54:21 +03:00
Vladimir Mandic f52249d5a8 fix prompt parser for sdxl and enable offloading 2023-08-10 21:20:56 +00:00
Vladimir Mandic 0b5dd46d79 Merge pull request #1976 from tcmaps/master 
pip --no-cache-dir
 2023-08-10 08:28:02 +02:00
Vladimir Mandic e2b0d981ac quick taesd vae decode 2023-08-09 09:34:59 +00:00
Disty0 6760fd1525 Add TAESD VAE option for base image outputs 2023-08-07 21:37:58 +03:00
Vladimir Mandic 0a3e821067 diffuser auto-pipeline and fix vae 2023-08-07 17:19:30 +00:00
Disty0 9d17cf4c12 IPEX Diffusers fix can't allocate 4GB+ with SDP 2023-08-07 19:50:39 +03:00
Vladimir Mandic 5fd3c5ba01 update lora methods 2023-08-07 14:52:19 +02:00
Vladimir Mandic 9be641d431 Merge pull request #1952 from AI-Casanova/kohya 
Enable side loading of multiple Kohya-style LoRA for SDXL
 2023-08-07 14:42:30 +02:00
Vladimir Mandic dc739b9f50 fix taesd for original backend 2023-08-06 07:07:00 +00:00
AI-Casanova df18ad4eb1 Enable side loading of multiple Kohya-style LoRA for SDXL 2023-08-05 14:54:50 +00:00
Vladimir Mandic 4234555566 update 2023-08-05 14:37:09 +00:00
Disty0 489d0382cf IPEX Diffusers fix cannot allocate more than 4GB 2023-08-05 17:26:18 +03:00
Vladimir Mandic 7c4fdbff1b update taesd 2023-08-05 08:56:45 +02:00
Disty0 5f5a564d41 Update compile settings 2023-08-03 22:38:43 +03:00
Disty0 44b17b7418 Add compile type option 2023-08-03 17:51:29 +03:00
Disty0 4535a99fff Model compile support for IPEX 2023-08-03 17:25:15 +03:00
Disty0 80b834054b CPU offload mode check & Enable compile for IPEX 2023-08-01 02:51:50 +03:00
Seunghoon Lee 8787f36b2c Merge branch 'master' of https://github.com/vladmandic/automatic 2023-08-01 02:03:51 +09:00
Seunghoon Lee d711880aa9 New option for DirectML: memory stats provider. 
1. Performance Counter.
    Get vram size allocated to & used by python.exe from pdh.dll.
    Generation can be slower than atiadlxx.
    Use memory less greedy then atiadlxx.
    Windows only.
2. atiadlxx.
    Get max vram size and available vram size from AMD GPU driver (atiadlxx.dll).
    Use memory more greedy than Performance Counter.
    Windows & WSL are supported.
3. None.
    Assume available vram size is 8GB.
    Use memory regardless of current vram usage.
 2023-08-01 01:58:04 +09:00
Disty0 8ffaea76ba Add Diffusers model and VAE variant loading option 2023-07-31 14:39:41 +03:00
Disty0 38ecfb6dff Add Move UNet to CPU option 2023-07-29 18:58:08 +03:00
Seunghoon Lee 0f44332e5c Make sequential CPU offload available for non-CUDA 
Add settings override for DirectML.
Move `devices.set_cuda_params()` to correct line.
 2023-07-28 23:11:57 +09:00
Vladimir Mandic ff9b8bc062 api endpoint refresh vaes 2023-07-26 15:51:19 -04:00
Vladimir Mandic 62bc9482e6 update themes 2023-07-26 12:47:04 -04:00
Vladimir Mandic 660c449e08 update themes 2023-07-26 12:17:49 -04:00
Vladimir Mandic c5b089cbb6 major ui simplification 2023-07-26 11:39:58 -04:00
Vladimir Mandic 7bee313bb3 rename 2023-07-24 19:52:50 -04:00
Seunghoon Lee d4aa840a77 DirectML update. 
DirectML reuses GPU memory instead of returning it.
So prints "practical" GPU memory utilization too.
 2023-07-24 16:10:01 +09:00
Vladimir Mandic 567faeb751 diffusers img2img and inpaint 2023-07-22 15:39:41 -04:00
Vladimir Mandic 4c2664dbc3 redesign diffuser vae handling 2023-07-21 14:30:57 -04:00
Vladimir Mandic b31fa98669 fixes... 2023-07-21 09:28:02 -04:00
Vladimir Mandic a3ab302f51 fix extensions reset 2023-07-20 09:52:21 -04:00
Vladimir Mandic debec28be6 rework settings, image-watermark, safe config handling 2023-07-18 14:41:27 -04:00