Public/automatic
1
0
Fork 0
mirror of https://github.com/vladmandic/automatic synced 2026-08-31 17:41:06 +02:00
Code Issues Packages Projects Releases Wiki Activity
5,984 Commits 3 Branches 34 Tags
4b1df48d00a5ff1fed623f9a9cb199bd4383dcc2
Commit Graph

45 Commits

Author SHA1 Message Date
Vladimir Mandic 7ceb1df1f5 dml fix for sd 2.1 2023-09-26 17:50:42 -04:00
Vladimir Mandic 8a11a3a70f update changelog 2023-09-26 17:45:52 -04:00
Vladimir Mandic ff28ac35e0 add actual latent upscalers 2023-09-25 19:46:12 -04:00
Vladimir Mandic 0afcfe6097 logger early init 2023-09-23 23:44:34 -04:00
Vladimir Mandic ef91976165 switch to native r-esrgan and modelloader 2023-09-18 15:21:11 -04:00
Vladimir Mandic 496bdf7c55 fix backend switch 2023-09-15 08:39:25 -04:00
Vladimir Mandic f36c1eb476 jumbo patch 2023-09-08 13:01:20 -04:00
Vladimir Mandic 8fd96d0f30 catch directml and ipex initialization errors 2023-09-07 07:27:54 -04:00
Hameer Abbasi 4c7792ed01 Add pre-commit. 2023-09-04 13:57:47 +02:00
Seunghoon Lee 7e81355741 Fix pdh.dll not found. (WSL+DirectML) 2023-08-13 15:40:15 +09:00
Seunghoon Lee 1524365284 Update Korean localization & DirectML bug fix. 2023-08-02 02:32:11 +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
Seunghoon Lee 42c6147ac8 cleanup 2023-07-29 13:48:28 +09:00
Seunghoon Lee 7017a4a2a9 Fix UniPC sampler issue on DirectML. 2023-07-29 13:38:41 +09:00
Seunghoon Lee 813eb48bf7 Restore Python 3.9 compatibility. (DirectML) 2023-07-29 12:10:41 +09:00
Seunghoon Lee 47f2f50574 Restore Python 3.9 compatibility. (DirectML) 2023-07-29 12:08:22 +09:00
Seunghoon Lee 77de9cd093 Fix medvram with DirectML. 2023-07-28 23:18:28 +09:00
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
Seunghoon Lee 43b9c52bd4 Fix image corruption in half mode with embeddings. 
(DirectML)
 2023-07-25 17:02:55 +09:00
Seunghoon Lee 33d814e3e7 Fix DirectML tensor behavior. 2023-07-25 00:03:07 +09:00
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
Seunghoon Lee 6b4b863fd0 simplify get_device. 2023-07-15 19:03:10 +09:00
Seunghoon Lee 0a52c44e73 DirectML rework & provide GPU memory usage (AMD only). 2023-07-15 18:55:38 +09:00
Seunghoon Lee 578f206bf7 DirectML rework. 2023-07-15 16:19:38 +09:00
Seunghoon Lee 6b63893348 Fix terminal hang up with TI on DirectML. 2023-07-09 15:47:38 +09:00
Vladimir Mandic 2a21196061 Merge branch 'master' into dev 2023-07-08 13:35:25 -04:00
Seunghoon Lee 99c7f23c89 remove useless methods. 2023-07-09 01:29:04 +09:00
Seunghoon Lee 47c96e34d4 Stringify tensor instead of printing. 2023-07-07 19:11:18 +09:00
Seunghoon Lee 1d36e19996 Fix PNDMScheduler for DirectML. 2023-07-07 18:52:04 +09:00
Seunghoon Lee a076ff1b43 Use backend enum on diffusers check. 2023-07-06 01:45:12 +09:00
Seunghoon Lee 993de932ab Add an opts override for DirectML. 2023-07-06 01:35:00 +09:00
Seunghoon Lee a9fa014e31 Fix image corruption of RESRGAN upscaler in DirectML. 2023-06-29 11:10:48 +09:00
Vladimir Mandic cb307399dd jumbo merge 2023-06-13 11:59:56 -04:00
Vladimir Mandic 5134471bc8 dml autocast 2023-05-14 13:24:59 -04:00
Vladimir Mandic c46f0dbdeb fix 2023-05-13 12:55:50 -04:00
Vladimir Mandic d96ab6a1ae update directml 2023-05-13 11:21:11 -04:00
Vladimir Mandic 1360c6422a add fp16 test 2023-05-08 09:27:50 -04:00
Seunghoon Lee 9e214b32d7 remove NotImplementedError. 2023-05-02 09:04:35 +09:00
Seunghoon Lee 93d638d8b8 Approx NN works fine. 2023-04-30 11:15:09 +09:00
Seunghoon Lee e65d74100f Move/Remove hijacks. Add warning. 2023-04-30 11:12:47 +09:00
Seunghoon Lee c128c0770b Load libatiadlxx.so on Linux systems. 2023-04-30 01:15:47 +09:00
Seunghoon Lee c9dde03fc5 Move realesrgan fallback to dml/hijack. 2023-04-26 18:54:24 +09:00
Seunghoon Lee d2d5011bd3 Implement memory estimation for AMDGPUs. 
Stable.
 2023-04-26 17:44:32 +09:00
Seunghoon Lee df0e89be48 fix. 
Unstable & need more test.
 2023-04-26 12:45:44 +09:00
Seunghoon Lee 09ae33cdf7 Implement torch.dml. 
VERY UNSTABLE & NOT TESTED.
 2023-04-26 12:21:44 +09:00