github/AMD-SHARK-Studio
1
1
Fork 0
mirror of https://github.com/nod-ai/AMD-SHARK-Studio.git synced 2026-04-03 03:00:17 -04:00
Code Issues Packages Projects Releases Wiki Activity
951 Commits 66 Branches 705 Tags
20230204.496
Commit Graph

951 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
powderluv
8115b26079 Revert pipelines (#948) 
* Revert "[SD] Modify the flags to use --iree-preprocessing-pass-pipeline (#914)"

This reverts commit a783c089a9.

* Revert "Fix iree flags due to the change in shark-runtime (#944)"

This reverts commit 1d38d49162.
20230204.495 20230204.496 		2023-02-04 07:09:51 -08:00
powderluv
820586ac68 Update README.md 2023-02-04 01:01:11 -08:00
powderluv
4a7441ed07 Update profiling_with_iree.md 2023-02-04 00:47:57 -08:00
powderluv
383741f284 Update stable_diffusion_amd.md 2023-02-04 00:40:47 -08:00
powderluv
2bbc4e0e9f Update README.md 2023-02-04 00:35:40 -08:00
powderluv
a7237244b0 Send users to the .exe file first 2023-02-04 00:30:32 -08:00
yzhang93
1d38d49162 Fix iree flags due to the change in shark-runtime (#944) 2023-02-03 21:34:02 -08:00
yzhang93
a783c089a9 [SD] Modify the flags to use --iree-preprocessing-pass-pipeline (#914) 
* [SD] Modify the flags to use --iree-preprocessing-pass-pipeline

* Fix flags in sd_annotation
20230203.494 		2023-02-03 15:08:02 -08:00
powderluv
e7907dc532 Disable tuned models for sm_89 (#943) 
Looks like tuning on A100 doesn't necessarily translate to 40xx.
 2023-02-03 14:30:46 -08:00
powderluv
394413679d Fix ckpt_dir (#939) 20230203.493 2023-02-03 12:54:19 -08:00
powderluv
37189f14cb roll to 492 2023-02-03 11:59:18 -08:00
powderluv
0b1ee81901 Minor webui changes (#938) 20230203.492 2023-02-03 11:26:45 -08:00
Gaurav Shukla
00cf73f9b8 [SD] Merge model id dropdown and .ckpt dropdown (#936) 
- use_tuned is set to False for custom checkpoints.

Signed-off-by: Gaurav Shukla <gaurav@nod-labs.com>
20230203.491 		2023-02-03 10:43:33 -08:00
Abhishek Varma
5a5f285493 [apps-SD] Prepone loading of vmfbs + restructure the SD pipeline 
-- This commit prepones loading of vmfbs, if present, for all sub-models.
-- It also involves restructuring the SD pipeline to achieve the loading
   of vmfbs smoothly and postpones processing of checkpoint files only when
   required.

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
20230203.490 		2023-02-03 20:21:24 +05:30
powderluv
7f2ea454b6 revert /base variants as they are different (#929) 
sd2_1base is different from VAE base (for older cards)
20230203.489 		2023-02-03 01:27:32 -08:00
Daniel Garvey
7c14002118 Map 2_1 to 2_1_base (#927) 
* fix broken paths for older models

* adds a mapping from sd_2_1 to sd_2_1_base

we only have models in models_db for 2_1_base.
now that diffusers is fixed we can actually generate
2_1 itself, but until we add support for that in the tank
we should fetch 2_1_base for no-import_mlir

---------

Co-authored-by: dan <dan@nod-labs.com>
20230202.488 		2023-02-02 19:03:19 -08:00
powderluv
3e9554f0a1 roll to 487 2023-02-02 19:02:39 -08:00
Daniel Garvey
e11ffec544 fix broken paths for older models (#926) 
Co-authored-by: dan <dan@nod-labs.com>
 2023-02-02 15:48:19 -08:00
powderluv
8a47ddbe99 Update models/ location in UI (#925) 
default to png metadata on
20230202.487 		2023-02-02 15:28:39 -08:00
powderluv
821108c7bd Fix models path (#924) 20230202.486 2023-02-02 15:16:00 -08:00
Gaurav Shukla
339738f8a3 [SD][web] Populate checkpoints as dropdown UI (#918) 
Signed-off-by: Gaurav Shukla <gaurav@nod-labs.com>
20230202.485 		2023-02-02 13:59:50 -08:00
powderluv
9b90672f63 Fix LLPC env var (#920) 2023-02-02 11:45:08 -08:00
Ean Garvey
ba07e94a5e disable Torch Inductor autotuner in benchmarks (#919) 2023-02-02 13:25:43 -06:00
aldesilv
b3fc0f29cc enable additional flags for tank test models (#866) 
Co-authored-by: Alex <alexander@nod-labs.com>
 2023-02-02 11:19:33 -08:00
Gaurav Shukla
5c7deb3611 [SD] Fix output image location (#917) 
Signed-off-by: Gaurav Shukla <gaurav@nod-labs.com>
 2023-02-02 09:50:37 -08:00
Daniel Garvey
15604e374f change bytecode model paths (#913) 
Co-authored-by: dan <dan@nod-labs.com>
 2023-02-02 11:12:13 -06:00
Abhishek Varma
7cfc0fa55b [APPS-SD] Fix a few bugs and bring it up to speed with SD CLI (#908) 2023-02-02 07:12:01 -08:00
Ean Garvey
a90812133b Enable pytests on Windows (#901) 20230201.484 2023-02-01 18:36:41 -06:00
powderluv
e26a70aa4f Drop old cli and webui (#911) 2023-02-01 13:13:46 -08:00
Daniel Garvey
6a32a4e26c move ci sd stuff to apps (#912) 
Co-authored-by: dan <dan@nod-labs.com>
Co-authored-by: powderluv <powderluv@users.noreply.github.com>
 2023-02-01 12:15:07 -08:00
powderluv
e853abf98b Update stable_diffusion_amd.md 2023-02-01 11:11:58 -08:00
powderluv
51e81e6ef8 update main readme 2023-02-01 11:09:00 -08:00
powderluv
e355000ceb Drop torchvision 2023-02-01 10:26:37 -08:00
Daniel Garvey
e374074013 Windows test (#896) 
* add generate_sharktank for stable_diffusion model defaults

* add windows test for sd

---------

Co-authored-by: dan <dan@nod-labs.com>
 2023-02-01 12:03:54 -06:00
powderluv
81e3d1c2c6 switch to apps/ 20230201.483 2023-02-01 06:54:20 -08:00
powderluv
ab0cbb4475 Add PyInstaller for apps/ webui and cli (#909) 
tested webui, cli and webui exe and cli exe
 2023-02-01 06:51:27 -08:00
powderluv
1c64e40722 Add PyInstaller for apps/ (#907) 
Build with pyinstaller.exe .\apps\stable_diffusion\web\shark_sd.spec

normal flow works. exe is missing a few json files
 2023-02-01 06:04:49 -08:00
Evan Guan
8cafe56eb4 Added flags for metadata information. (#894) 2023-02-01 05:16:11 -08:00
Eliasj42
3eceeb7b23 fixed a bug that would sometimes cause intel-gpu to appear unsupported (#899) 
Co-authored-by: Elias Joseph <elias@nod-labs.com>
 2023-01-31 22:32:05 -08:00
powderluv
1a37675435 Revert "move beta to release (#898)" (#905) 
This reverts commit 7edcaf5a06.
20230131.482 		2023-01-31 20:31:41 -08:00
powderluv
198ebede8d Revert "replace new model_db.json (#902)" (#904) 
This reverts commit 842adef29c.
 2023-01-31 20:29:40 -08:00
Ean Garvey
a504903dd5 Fix formatting issues. (#903) 2023-02-01 09:12:45 +05:30
Daniel Garvey
842adef29c replace new model_db.json (#902) 2023-01-31 18:55:22 -08:00
Daniel Garvey
7edcaf5a06 move beta to release (#898) 
Co-authored-by: dan <dan@nod-labs.com>
 2023-01-31 17:14:08 -06:00
Gaurav Shukla
c124b76328 [SD] Reorganize the stable diffusion model. (#806) 
The stable diffusion codebase has been reorganized to make it more
modular so that the same script can be used for web as well as cli,
instead of duplicating the whole codebase.

Signed-off-by: Gaurav Shukla <gaurav@nod-labs.com>
 2023-01-31 14:42:41 -08:00
aldesilv
e9c744ee5d find rocm arch used in rocminfo (#893) 
Co-authored-by: Alex <alexander@nod-labs.com>
 2023-01-31 10:22:31 -08:00
Ean Garvey
83302930d8 Update generate_sharktank.py (#897) 2023-01-31 10:21:22 -08:00
Daniel Garvey
a4634632ba add generate_sharktank for stable_diffusion model defaults (#742) 
Co-authored-by: dan <dan@nod-labs.com>
Co-authored-by: powderluv <powderluv@users.noreply.github.com>
 2023-01-31 09:44:54 -08:00
Abhishek Varma
d17e8dc5ad [NFC] Rename SD negative_prompts flag 
-- This commit renames SD `negative-prompts` -> `negative_prompts` flag.

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
 2023-01-31 21:38:59 +05:30
powderluv
9fe63de4d4 Pin macOS SDK to 216 2023-01-31 01:09:44 -08:00