Commit Graph

333 Commits

Author SHA1 Message Date
powderluv
1f72907886 Fix the pyinstaller for chatbots (#1631) 2023-07-06 23:30:01 -07:00
Daniel Garvey
06c8aabd01 remove local-sync from webui (#1629) 2023-07-06 13:58:59 -07:00
Phaneesh Barwaria
55a12cc0c4 cpu name in device (#1628)
* show cpu name in devices

* change device order for chatbot
2023-07-06 12:00:09 -07:00
Abhishek Varma
1b62dc4529 [Vicuna] Revert the formatting for Brevitas op (#1626)
-- This commit reverts the formatting for Brevitas op.
-- It also excludes vicuna.py script from `black` formatter.

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
2023-07-06 06:56:17 -07:00
Daniel Garvey
c5a47887f4 Revert revert negative prompt change (#1625)
* revert default flag changes

* revert revert negative prompt change

* revert revert negative prompt change
2023-07-05 22:09:06 -07:00
Daniel Garvey
c72d0eaf87 revert default flag changes (#1622) 2023-07-05 15:43:26 -05:00
xzuyn
043e5a5c7a fix a mistake I made, and more formatting changes, and add ++/Karras (#1619)
* fixed missing line break in `stablelm_ui.py` `start_message`
- also more formatting changes

* fix variable spelling mistake

* revert some formatting cause black wants it different

* one less line, still less than 79

* add ++, karras, and karras++ types of dpmsolver.

* black line length 79

---------

Co-authored-by: powderluv <powderluv@users.noreply.github.com>
2023-07-05 09:00:16 -07:00
Abhishek Varma
a1b1ce935c int8 e2e for WebUI (#1620) 2023-07-05 07:08:36 -07:00
jinchen62
bc6fee1a0c Add int4/int8 vicuna (#1598) 2023-07-05 07:01:51 -07:00
xzuyn
91ab594744 minor fix, some changes, some additions, and cleaning up (#1618)
* - fix overflowing text (a janky fix)
- add DEISMultistep scheduler as an option
- set default scheduler to DEISMultistep
- set default CFG to 3.5
- set default steps to 16
- add `xzuyn/PhotoMerge` as a model option
- add 3 new example prompts (which work nicely with PhotoMerge)
- formatting

* Set DEISMultistep in the cpu_only list instead

* formatting

* formatting

* modify prompts

* resize window to 81% & 85% monitor resolution instead of (WxH / 1.0625).

* increase steps to 32 after some testing. somewhere in between 16 and 32 is best compromise on speed/quality for DEIS, so 32 steps to play it safe.

* black line length 79

* revert settings DEIS as default scheduler.

* add more schedulers & revert accidental DDIM change
- add DPMSolverSingleStep, KDPM2AncestralDiscrete, & HeunDiscrete.
- did not add `DPMSolverMultistepInverse` or `DDIMInverse` as they only output latent noise, there are a few I did not try adding yet.
- accidentally set `upscaler_ui.py` to EulerDiscrete by default last commit while reverting DEIS changes.
- add `xzuyn/PhotoMerge-inpainting` as an in or out painting model.

* black line length 79

* add help section stuff and some other changes
- list the rest of the schedulers in argument help section.
- replace mutable default arguments.
- increased default window height to 91% to remove any scrolling for the main txt2img page (tested on a 1920x1080 monitor). width is the same as its just enough to have the image output on the side instead of the bottom.
- cleanup
2023-07-04 18:51:23 -07:00
Eliasj42
4015793f84 changed method of compiling vicuna to remove first and second vicuna (#1611)
Co-authored-by: Elias Joseph <elias@nod-labs.com>
Co-authored-by: powderluv <powderluv@users.noreply.github.com>
2023-07-03 12:12:43 -07:00
Ean Garvey
d63ce76dd8 Use sortable image filenames for SD outputs. (#1528) 2023-07-03 10:30:47 -07:00
Ean Garvey
6d286c0609 Enable tuning for rectangle sizes on rdna2. (#1608) 2023-06-30 22:28:24 -07:00
Stefan Kapusniak
7392b22731 UI/Web Reduce animation of default --progress_bars (#1613) 2023-06-30 21:12:10 -07:00
jinchen62
534de05791 Update precision check for vicuna (#1610) 2023-06-29 16:16:33 -05:00
Daniel Garvey
5779e8c039 int4/int8 vicuna download support (#1609)
* set task_topology_max_group to cpu_count

by default. Can be overriden with a flag of the same str

* add download for int4/int8 mlir
2023-06-29 13:35:51 -07:00
gpetters94
6274a813c9 Add unet512 support for the other StableDiffusion pipelines (#1602) 2023-06-27 12:28:57 -07:00
Gaurav Shukla
1d6a1f9f8a [vicuna] Add tokens streaming(step=3) (#1600)
Signed-off-by: Gaurav Shukla <gaurav@nod-labs.com>
2023-06-27 08:59:27 -07:00
Stefan Kapusniak
eaa49cce17 UI/App - Allow text selection (#1593)
* When run in app mode on windows, allows selection of text from
non-input controls, which is the same behaviour as web mode.
2023-06-26 02:16:53 -07:00
powderluv
10657d6fb1 Disable upx 2023-06-25 07:28:52 -07:00
Stefan Kapusniak
e3ab844cd1 Fix output gallery for csv format inc. VAE & LoRA (#1591) 2023-06-24 06:20:53 -07:00
powderluv
5ce6001b41 Update stablelm_ui.py to default to fp16 2023-06-23 22:55:47 -07:00
powderluv
501d0ca52e Add sentencepiece to webui for pyinstaller 2023-06-23 22:52:06 -07:00
AyaanShah2204
8cdb38496e Final REST API Fixes (#1590)
* fixed outpaint api and added tests

* fixed text2img api

* more elegant generator to subscriptable conversion

* final fixes
2023-06-23 16:46:47 -07:00
powderluv
726d73d6ba Revert "[vicuna] Add streaming of tokens (#1587)" (#1588)
This reverts commit 4d55e51d46.
2023-06-23 10:29:00 -07:00
Gaurav Shukla
4d55e51d46 [vicuna] Add streaming of tokens (#1587)
Signed-off-by: Gaurav Shukla <gaurav@nod-labs.com>
2023-06-23 08:20:46 -07:00
jinchen62
4002da7161 Add int4/int8 options to chatbot webui (#1586) 2023-06-23 07:18:34 -07:00
powderluv
ecb5e8e5d8 Update txt2img_ui.py 2023-06-23 06:42:12 -07:00
AyaanShah2204
97f7e79391 [Blender Integration] Fixed Inpainting REST API (#1577)
* fixed inpaint api

* added inpainting test

* fixed linter errors

---------

Co-authored-by: powderluv <powderluv@users.noreply.github.com>
2023-06-22 16:08:26 -07:00
Nelson Sharpe
44a8f2f8db Include VAE & LoRA data into PNG metadata (#1573)
* include custom lora and vae data in png metadata

* include pycharm settings

* lint with black
2023-06-22 16:05:54 -07:00
Eliasj42
8822b9acd7 added ability to use config file to shard vicuna (#1565)
Co-authored-by: Elias Joseph <elias@nod-labs.com>
2023-06-22 17:40:35 -05:00
Daniel Garvey
0ca3b9fce3 fix some mmap and vicuna bugs (#1576) 2023-06-22 17:39:55 -05:00
powderluv
1b0f39107c Move torch_mlir import to the top (#1574) 2023-06-21 22:31:35 -07:00
Ranvir Singh Virk
18c8e9e51e Metal typo fix (#1572)
* fixing typos for metal changes

* black formating
2023-06-21 21:56:11 -07:00
Daniel Garvey
a202bb466a fp16 fixes for webui (#1571) 2023-06-21 20:24:02 -07:00
Ranvir Singh Virk
07c1e1d712 Adding metal_utils for iree_utils (#1561)
* Adding metal_utils for iree_utils

* Add patch for making compile API work for both MEGABYTE and MiniGPT4 (#1559)

-- It also modifies the mega_test.py script

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

* [SD] Update unet in_channels API and add PIL metadata to spec. (#1560)

* Fix deprecation warning for unet config.

* Include PIL metadata instead of hidden imports in SD spec.

* Fixing iree-metal-target-platform

* adding metal to txt2img pipeline

* Fixing Copyright date

* removing debug prints

* black lint formating

* fixing device dump

---------

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
Co-authored-by: Abhishek Varma <avarma094@gmail.com>
Co-authored-by: Ean Garvey <87458719+monorimet@users.noreply.github.com>
Co-authored-by: powderluv <powderluv@users.noreply.github.com>
2023-06-21 19:09:03 -07:00
Ean Garvey
1a8e2024d6 Exclude non-square sizes from use_tuned on rdna2 (#1568) 2023-06-21 11:36:55 -05:00
AyaanShah2204
d61b6641fb Rest API: Resolved Generator Object not Subscripatable error (#1556) 2023-06-20 19:27:41 -07:00
Phaneesh Barwaria
88cc2423cc Enable Vicuna fp16 cpu (#1562)
* fix second vic mlir gen

* fp16 mlir/vmfb download from shark_tank
2023-06-20 13:43:21 -05:00
Ean Garvey
ccf944c1bd Enable tuner for upscaler unet. (#1563) 2023-06-20 13:40:13 -05:00
Ean Garvey
0def74f520 [SD] Update unet in_channels API and add PIL metadata to spec. (#1560)
* Fix deprecation warning for unet config.

* Include PIL metadata instead of hidden imports in SD spec.
2023-06-20 10:26:36 -07:00
Abhishek Varma
3fb72e192e Add patch for making compile API work for both MEGABYTE and MiniGPT4 (#1559)
-- It also modifies the mega_test.py script

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
2023-06-20 10:04:17 -07:00
Vivek Khandelwal
855435ee24 Fix for the user input for Falcon pipeline 2023-06-20 18:09:32 +05:30
Elias Joseph
6f9f868fc0 fixed a bug where designating device for vicuna didn't work 2023-06-20 17:09:32 +05:30
rprasad2
3e5c50f07b changes for tuning (#1542)
* Add tuning sizes for rdna3
2023-06-19 15:29:08 -05:00
Vivek Khandelwal
fafd713141 Minor change to falcon pipeline 2023-06-19 22:36:32 +05:30
Vivek Khandelwal
015d0132c3 Modify falcon pipeline to add fp16 support (#1551) 2023-06-19 09:57:13 -07:00
powderluv
ee33cfd2d1 Add PIL in main index.py (#1549)
* Add PIL in main index.py

This is to ensure pyinstaller picks it up

* Update index.py
2023-06-18 11:51:44 -07:00
Stefan Kapusniak
a3cba21d5b Fix load of unet512 vmfb fail on get of iree opts (#1546)
* Change retrieval of Iree options used when loading an existing
unet512 vmfb to look up the "unet" options rather than attempt to
find a non-existent set of options for "unet512"

Co-authored-by: powderluv <powderluv@users.noreply.github.com>
2023-06-18 06:42:20 -07:00
Stefan Kapusniak
a7b6ec4095 Fix unet512 always being used when --max_length=77 (#1547)
* Switches a few places in the SD pipeline where an assumption of
max_length=64 was being made, to using the actual max_length
as passed into the pipeline. This prevents unet512 always being
used and producing different images than previously when
--max_length=77
2023-06-18 06:41:25 -07:00