Commit Graph

1131 Commits

Author SHA1 Message Date
m68k-fr
b661656c03 [Web] Fix custom model path for upscaler (#1199) 20230316.607 20230316.606 2023-03-16 15:57:23 -07:00
Gaurav Shukla
0225434389 [SD] Add sendTo Upscaler
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
2023-03-16 20:49:19 +05:30
Gaurav Shukla
7ffe20b1c2 [SD] Release memory used by upscaler when not in use
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
2023-03-16 20:49:19 +05:30
Gaurav Shukla
d8f0c4655d [SD] Add Upscaler web
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
2023-03-16 20:49:19 +05:30
Gaurav Shukla
7e8d3ec0df [SD] Add upscalar pipeline
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
2023-03-16 20:49:19 +05:30
jinchen62
9c08eec565 Clear memory cache when switching model and mode (#1194) 20230315.605 2023-03-15 22:18:26 -07:00
m68k-fr
2d2c523ac5 [Web] Upgrade Gradio to v3.21.0 (#1188)
Co-authored-by: powderluv <powderluv@users.noreply.github.com>
20230315.604 20230315.603 20230315.602
2023-03-15 10:14:49 -07:00
Abhishek Varma
f17b3128c0 [SD] Add LoRA inference to SD pipeline (#1189)
-- This commit adds LoRA inference to SD pipeline.
-- It also modifies txt2img to incorporate the new feature.
   img2img, inpaint, outpaint, etc using Unet can also be extended in a
   similar way.

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
Co-authored-by: Abhishek Varma <abhishek@nod-labs.com>
2023-03-15 10:13:45 -07:00
Abhishek Varma
7c7e630099 [SD] Add fix for using latest diffusers + add scribble variant to Stencil (#1191)
* [SD] Add Scribble variant in Stencil

-- This commit adds scribble variant in Stencil.

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>

* [SD] Use latest diffusers

-- This commit points back to the latest diffusers and updates the
   processing script to tackle the Pix2Pix import issue.

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>

---------

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
Co-authored-by: Abhishek Varma <abhishek@nod-labs.com>
2023-03-15 10:13:20 -07:00
m68k-fr
2dd1491ec1 [Web] Add clear queue button (#1192) 2023-03-15 10:12:59 -07:00
Daniel Garvey
236357fb61 add missing import for shark_sd.spec (#1190)
L
2023-03-15 09:23:29 -05:00
Phoenix Meadowlark
7bc38719de Add benchmark artifacts to .gitignore (#1186) 2023-03-14 15:19:06 -07:00
Daniel Garvey
bdbe992769 Add IREE_SAVE_TEMPS for import_debug command (#1184)
based on hf_model_id. Works on windows
2023-03-14 11:40:23 -07:00
Abhishek Varma
e6b925e012 [SD] Add Openpose to Stencil + image size issue fix (#1181)
-- This commit adds openpose model variant to stencil.
-- Fixes image size issue.
-- Also includes fix for the .exe bug introduced by https://github.com/nod-ai/SHARK/pull/1175

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
Co-authored-by: Abhishek Varma <abhishek@nod-labs.com>
2023-03-14 10:30:52 -07:00
cstueckrath
771120b76c workaround Gradio issue (#1183)
https://discord.com/channels/973663919757492264/975522729564446740/1085109774758191164
20230314.599
2023-03-14 01:27:24 -07:00
Boian Petkantchin
a8ce7680db Add flag to augment the device allocator (#1182)
Example:
$ python my_app.py --device_allocator caching debug
This will wrap the device allocator with first caching allocator then
debug allocator.

$ python my_app.py --device_allocator caching
Only wrap with caching allocator.

Co-authored-by: Boian Petkantchin <boian@nod-labs.com>
20230313.598
2023-03-13 15:49:26 -07:00
Phaneesh Barwaria
b6dcf2401b Stencil perf improvement (#1179)
* remove conditioning strength multiplier

* mod diffusers lib to v0.14.0
20230313.597
2023-03-13 14:37:38 -07:00
Daniel Garvey
62b5a9fd49 generate sharktank for apps dir (#966)
* merge confix resolution

* add support to other scripts

---------

Co-authored-by: dan <dan@nod-labs.com>
2023-03-13 10:54:15 -07:00
m68k-fr
2f133e9d5c Fix png metadata (#1178) 2023-03-12 22:43:39 -07:00
powderluv
f898a1d332 Update README.md 2023-03-12 16:54:42 -07:00
m68k-fr
b94266d2b9 [Web] Randomize seed to -1 (#1176) 2023-03-12 12:42:31 -07:00
m68k-fr
1b08242aaa [Web] Improve dropdowns ux (#1175) 2023-03-12 12:41:51 -07:00
Abhishek Varma
691030fbab [SD] Improve Stencil feature to handle general image sizes
-- Currently stencil feature works with 512x512 images only.
-- This commit relaxes this constraint and adds support for various
   image sizes.

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
20230311.595
2023-03-11 21:48:31 +05:30
m68k-fr
16ad7d57a3 [WebUi] txt2img_ui: Import png metadata (#1147) 20230310.594 20230310.593 2023-03-10 16:26:34 -08:00
Anush Elangovan
c561ebf43c Drop the torch-mlir pin
Seems to work now with top of master
2023-03-10 15:39:04 -08:00
Prashant Kumar
97fdff7f19 Add instructions how to run the LLaMA model. (#1168)
* Add instructions how to run the LLaMA model.

* Update README.md
2023-03-10 12:36:37 -08:00
Anush Elangovan
ce6d82eab2 Fix bloom lint 20230310.592 2023-03-10 11:53:08 -08:00
Abhishek Varma
b8f4b18951 [SD] Use dynamic stencil HF repo id
-- This commit removes the hardcoded HF ID for Stencil and instead
   utilizes a dynamic instantiation of HF model.

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
2023-03-10 23:31:45 +05:30
Eliasj42
b23d3aa584 added more memory efficient method to run large bloom models with sharded blooms (#1165)
Co-authored-by: Elias Joseph <elias@nod-labs.com>
2023-03-10 09:32:56 -08:00
Vivek Khandelwal
495670d9b6 Fix SD fine tuning script device arg usage 2023-03-10 18:37:53 +05:30
Boian Petkantchin
815e23a0b8 Update iree-compile flags --iree-llvm-xxx -> --iree-llvmcpu-xxx (#1164) 20230310.591 20230309.590 2023-03-09 11:31:50 -08:00
Boian Petkantchin
783538fe11 Move linting opts from github workflow to config files
This helps development where you can be sure that running locally

black .
flake8 .

will do the same as in the github job.
2023-03-09 10:46:30 -08:00
Boian Petkantchin
996c645f6a In SD don't include device path in vmfb filename
Include only the driver name instead.
2023-03-09 10:45:32 -08:00
m68k-fr
1f7d249a62 Use utf-8 format for imgs_details.csv 2023-03-09 16:15:58 +05:30
jinchen62
7f6c9a2dc2 Add an inpainting option for only masked area (#1154) 20230307.586 20230308.589 20230308.588 2023-03-07 09:46:05 -08:00
Eliasj42
93891984f3 made sharded bloom example more user friendly (#1153)
Co-authored-by: Elias Joseph <elias@nod-labs.com>
20230306.584
2023-03-06 10:23:48 -08:00
Vivek Khandelwal
cc0ef54e0e Fix Stable diffusion fine tuning script 2023-03-06 17:52:16 +05:30
Daniel Garvey
812152485d temporarily xfail tiny convnext macos (#1142) 20230305.583 20230304.582 20230304.581 20230303.580 2023-03-03 13:30:56 -06:00
Vivek Khandelwal
0816fb403a Add Stable diffusion fine tuning script
This commit adds the sd fine tuning script which runs through the
torchdynamo path.
2023-03-03 21:59:00 +05:30
Gaurav Shukla
4f171772be [SD] Fix SD web flags
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
2023-03-03 21:55:40 +05:30
mariecwhite
a52331d4aa Install IREE pre-releases (#1139) 2023-03-02 23:17:56 -06:00
yzhang93
ad821a1fc8 Use old torch-mlir package to avoid crash on rdna2 (#1137) 20230302.579 20230302.578 2023-03-02 18:16:58 -08:00
Ean Garvey
116b128802 Use nightly shark_tank for test-models (#1133)
* Use nightly shark_tank for test-models

* Update all_models.csv
2023-03-02 12:33:36 -06:00
Gaurav Shukla
b118f183d1 [SD] Fix few things in sendTo feature (#1132) 20230302.577 2023-03-02 09:11:55 -08:00
Gaurav Shukla
911dff16f1 [SD] Add sendTo feature in stable diffusion (#1131)
Signed-off-by: Gaurav Shukla <gaurav@nod-labs.com>
20230302.576
2023-03-02 08:42:38 -08:00
Abhishek Varma
de59a66ae4 [SD] Update diffusers to point to the fix for Stencil + add opencv-python (#1130) 2023-03-02 08:19:29 -08:00
Daniel Garvey
23f1468cc6 disable most models on windows pytest (#1125) 2023-03-02 01:37:50 -06:00
jinchen62
080350d311 Make loading custom inpainting models general (#1126) 2023-03-01 22:14:04 -08:00
Phaneesh Barwaria
7f3f92b9d5 remove extra return arg (#1123)
* remove extra return arg

txt2img expects only 3 mlirs

* add venv reqs for stencils
20230301.574
2023-03-01 11:45:24 -08:00
Abhishek Varma
be3cdec290 [SD] Add Stencil feature to SD pipeline (#1111)
* [WIP] Add ControlNet to SD pipeline

-- This commit adds ControlNet to SD pipeline.

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>

* [SD] Add ControlNet to img2img + fix bug for img2img scheduler

-- This commit adds ControlNet execution to img2img.
-- It restructures the addition of ControlNet variants.
-- It also fixes scheduler selecting bug for img2img pipeline.

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>

* add shark models for stencilSD

* Add Stencil controlled SD in img2img pipeline (#1106)

* use shark stencil modules

* adjust diffusers change

* modify to use pipeline

* remove control from unet

* pump stencils through unet

* complete integration in img2img

* fix lint and comments

* [SD] Add ControlNet pipeline + integrate with WebUI + add compiled flow execution

-- This commit creates a dedicated SD pipeline for ControlNet.
-- Integrates it with img2img WebUI.
-- Integrates the compiled execution flow for ControlNet.

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>

* [SD] Stencil execution

* Remove integration setup

* [SD] Fix args.use_stencil overriding bug + vmfb caching issue

-- This commit fixes args.use_stencil overriding issue which caused
   img2img pipeline to pick wrong set of modules.
-- It also fixes vmfb caching issue to speed up the loading time
   and pick right set of modules based on a mask.

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>

---------

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
Co-authored-by: Abhishek Varma <abhishek@nod-labs.com>
Co-authored-by: PhaneeshB <b.phaneesh@gmail.com>
2023-03-01 10:44:40 -08:00