github/SHARK-Studio
1
1
Fork 0
mirror of https://github.com/nod-ai/SHARK-Studio.git synced 2026-05-12 03:00:11 -04:00
Code Issues Packages Projects Releases Wiki Activity
897 Commits 66 Branches 705 Tags
20230128.477
Commit Graph

120 Commits

Author SHA1 Message Date
powderluv
9bbffa519e Add an option to respect LLPC env var (#875) 
Also add OSX paths
 2023-01-25 13:56:55 -08:00
powderluv
e5d5acbf1f Remove torchvision requirements from web (#860) 2023-01-23 13:48:53 -08:00
xzuyn
2a1d1c1001 make jpeg optimized and progressive (#820) 
* GUI make jpeg optimized and progressive

* CLI make jpeg optimized and progressive
 2023-01-17 16:35:36 -08:00
Fraser Humphries
b9d947ce6f style: 🎨 Restore whitespace 2023-01-17 17:45:32 +05:30
Fraser Humphries
e6589d2454 fix: 🏗️ Add demo.css to spec file datas 2023-01-17 17:45:32 +05:30
Fraser Humphries
0f5ac6afcf fix: 🐛 resolve css file path relative to __file__ 
issues-816
 2023-01-17 17:45:32 +05:30
PhaneeshB
48137ced19 add png as default format 2023-01-16 18:37:36 +05:30
PhaneeshB
f0dd48ed2a remaining disk space warning 2023-01-13 19:34:05 +05:30
Gaurav Shukla
15e2df0db0 [SD][web] Add a UI textbox to show the output location 
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
 2023-01-13 19:33:04 +05:30
Fraser Humphries
4ad0109769 fix: 🐛 Extract demo css string to css file 
fix: 🐛 Extract demo css string to css file

issues/807

fix: 🐛 Revert background colors
 2023-01-13 16:42:05 +05:30
xzuyn
5d117af8ae Increase JPEG output quality & disable subsampling (#801) 
* Increase JPEG output quality & disable subsampling

Increased to JPEG95 from the default JPEG75 which is way too compressed. Output image size is now ~100kb. Previously was ~20kb.

* Increase JPEG output quality & disable subsampling

Add jpeg quality increase on cli

* line length changes

* line length changes
 2023-01-11 23:06:11 -08:00
Gaurav Shukla
3b2bbb74f8 [SD][web] Add support for saving generated images 
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
 2023-01-11 22:47:32 +05:30
fokin33
dbc0f81211 Add simple telegram bot (#787) 2023-01-11 09:20:23 -06:00
Gaurav Shukla
472185c3e4 [SD][web] Fix device key error 
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
 2023-01-10 20:51:01 +05:30
Gaurav Shukla
f94a571773 [SD] Update spec file to include model_config.json 
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
 2023-01-10 20:38:10 +05:30
Gaurav Shukla
ee56559b9a [SD][web] Add a json file for model configuration 
This cleans model_wrappers.py file.

Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
 2023-01-10 00:05:46 +05:30
Gaurav Shukla
00e594deea [SD][web] Add version number in performance details 
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
 2023-01-09 21:32:34 +05:30
Prashant Kumar
fea1694e74 Delete the cached objects explicitly. 2023-01-06 23:04:52 +05:30
Gaurav Shukla
b604f36881 [SD][web] Add flags for global URL and server port 
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
 2023-01-05 15:30:30 +05:30
Abhishek Varma
e60b4568c6 [SharkInference] Make SharkInference compile the entire module (#708) 
* [SharkInference] Make SharkInference compile the entire module

-- Previously SharkInference was compiling and providing run APIs
   for a harcoded function with function name "forward".
-- This commit makes the compiling functionality generic and now
   any function being defined within the module can be run.
-- It also creates an API to fetch all the function names defined
   within the compiled module.
-- This commit updates both web and command-line execution of Stable
   Diffusion to use new API of  SharkInference.

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
 2023-01-03 23:25:23 +05:30
jinchen62
f6064a2b84 Add a prototype of the model compilation configs for SD (#734) 2022-12-28 15:14:36 -08:00
Quinn Dawkins
2e90cb7b95 Set default warmup count to 0 (#736) 2022-12-28 12:27:43 -06:00
Gaurav Shukla
45af40fd14 [SD][web] Add openjourney and dreamlike in SD web UI 
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
 2022-12-26 01:59:36 +05:30
Gaurav Shukla
c3c1e3b055 [SD] Add bucket info in the model_db.json 
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
 2022-12-25 20:38:33 +05:30
Gaurav Shukla
7c5e3b1d99 [SD] Fix flags for cuda devices 
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
 2022-12-25 19:03:02 +05:30
Gaurav Shukla
ed6cec71e7 [SD] Fix clip inference time 
Fix clip inference time by adding default warmup_count to 5.

Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
 2022-12-25 18:16:53 +05:30
Tobby "GTD-Carthage" Ong
d6bcdd069c - Added missing double linebreak from linting 2022-12-25 12:07:43 +05:30
Tobby "GTD-Carthage" Ong
a26347826d - Revised code to also use get_schedulers function instead 2022-12-25 12:07:43 +05:30
Tobby "GTD-Carthage" Ong
5d1c099b31 [SD] Add Euler Ancestral scheduler as option to WebUI 2022-12-25 12:07:43 +05:30
Gaurav Shukla
220bee1365 [SD][web] Add device support in the SD web UI 
1. Now device selection is available through UI.
2. Models reloading will only happen when there will be a change in the
   settings(variant + device).

Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
 2022-12-25 01:45:07 +05:30
Stanley Winata
136021424c [SD] Change default VMA large heap block size for windows perf. (#715) 
Windows perform can boost from 2.67s/image to 2.4523s/image.
While Linux stays the same.
 2022-12-24 01:40:58 +07:00
Gaurav Shukla
a5b70335d4 [SD][web] Add variant support in the web UI 
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
 2022-12-23 23:18:27 +05:30
Daniel Garvey
b01f29f10d add support for clear_all (#691) 2022-12-22 11:25:03 -06:00
Gaurav Shukla
7eeb7f0715 [SD] Update all the utilities to make web and CLI codebase closer (#707) 
At this point, all the utilities of SD web and CLI are exactly same.

Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>

Signed-off-by: Gaurav Shukla <gaurav@nod-labs.com>
 2022-12-22 02:49:48 -08:00
powderluv
37262a2479 Remove spurious characters 2022-12-21 19:23:54 -08:00
Gaurav Shukla
de6e304959 [SD] Fix the resource location in shark_sd.spec (#706) 2022-12-21 14:41:56 -08:00
Quinn Dawkins
234475bbc7 Add base_vae entries for variant models (#705) 2022-12-21 14:35:08 -08:00
Quinn Dawkins
abbd9f7cfc [SD] Set unet flags for cuda (#704) 2022-12-21 13:22:04 -08:00
Gaurav Shukla
dfd6ba67b3 [SD] Update SD CLI to use model_db.json 
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
 2022-12-22 02:13:04 +05:30
Gaurav Shukla
726c062327 [SD] Update spec files 
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
 2022-12-21 14:16:04 +05:30
Gaurav Shukla
9083672de3 [SD][web] Tuned models only for stablediffusion/fp16 and rdna3 cards 
Currently tuned models are only available for stablediffusion/fp16 and
rdna3 cards.

Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
 2022-12-21 14:15:39 +05:30
Quinn Dawkins
cdbaf880af [SD] [web] Add model variants to web 2022-12-21 13:42:22 +05:30
Gaurav Shukla
0d5173833d [SD] Add a json file for model names information. (#687) 
This commit simplifies the code to identify the model name for a
particular set of flags. This is achieved by introducing a json file
that stores the model names information. The models are uploaded in
gcloud with these names.

Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>

Signed-off-by: Gaurav Shukla <gaurav@nod-labs.com>
 2022-12-20 11:47:31 -08:00
yzhang93
abcd3fa94a [SD] Set model max length 64 as default (#681) 2022-12-19 21:13:04 -08:00
Quinn Dawkins
62aa1614b6 [SD] Add --use_base_vae flag to do conversion to pixel space on cpu (#682) 2022-12-19 21:09:39 -08:00
yzhang93
5ebe13a13d Add Unet len 64 tuned model (#679) 2022-12-19 16:24:08 -08:00
Gaurav Shukla
c3bed9a2b7 [SD][web] Add flag to disable the progress bar animation 
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
 2022-12-20 02:50:04 +05:30
yzhang93
f865222882 Update VAE 19dec tuned model (#676) 2022-12-19 12:42:28 -08:00
Gaurav Shukla
097d0f27bb [SD][web] Add 64 max_length support in SD web 
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
 2022-12-20 00:00:58 +05:30
Gaurav Shukla
7986b9b20b [SD][WEB] Update VAE model and wrapper 
This commit updates VAE model which significantly improves performance
by an order of ~300ms.

Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
 2022-12-19 22:32:05 +05:30