97 Commits

Author SHA1 Message Date
Ean Garvey
2004d16945 Revert "[SDXL] Add SDXL pipeline to SHARK (#1731)" (#1882)
This reverts commit 9f0a421764.
2023-10-09 18:01:44 -07:00
Abhishek Varma
9f0a421764 [SDXL] Add SDXL pipeline to SHARK (#1731)
-- This commit adds SDXL pipeline to SHARK.

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
2023-10-09 13:01:37 -05:00
gpetters94
79bd0b84a1 Fix an issue with diffusers>0.19.3 (#1775) 2023-08-18 14:06:06 -04:00
Daniel Garvey
a57eccc997 fix lint (#1720) 2023-08-04 14:54:33 -05:00
Daniel Garvey
a686d7d89f temporarily disable langchain stuff in webui (#1719)
its breaking the exe
2023-08-04 12:48:06 -07:00
Stefan Kapusniak
a2a436eb0c SD - Add repeatable (batch) seeds option (#1654)
* Generates the seeds for all batch_count batches being run up front
rather than generating the seed for a batch just before it is run.
* Adds a --repeatable_seeds argument defaulting to False
* When repeatable_seeds=True, the first seed for a set of batches will
also be used as the rng seed for the subsequent batch seeds in the run.
The rng seed is then reset.
* When repeatable_seeds=False, batch seeding works as currently.
* Update scripts under apps/scripts that support the batch_count
argument to also support the repeatable_seeds argument.
* UI/Web: Adds a checkbox element on each SD tab after batch count/size
for toggling repeatable seeds, and update _inf functions to take
this into account.
* UI/Web: Moves the Stop buttons out of the Advanced sections and next
to Generate to make things not fit quite so badly with the extra UI
elements.
* UI/Web: Fixes logging to the upscaler output text box not working
correctly when running multiple batches.
2023-07-15 16:22:41 -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
gpetters94
6274a813c9 Add unet512 support for the other StableDiffusion pipelines (#1602) 2023-06-27 12:28:57 -07:00
Ean Garvey
ccf944c1bd Enable tuner for upscaler unet. (#1563) 2023-06-20 13:40:13 -05:00
gpetters94
b204113563 Add UNet512 (#1504)
Co-authored-by: Ean Garvey <87458719+monorimet@users.noreply.github.com>
2023-06-17 03:46:25 -04:00
Ean Garvey
5f5823ccd9 Fix inference object imports for SD apps. (#1334) 2023-04-21 13:40:48 -05:00
Gaurav Shukla
0b01bbe479 [SD] Add txt2img/upscaler/inpaint/outpaint Rest API (#1325)
Signed-off-by: Gaurav Shukla <gaurav@nod-labs.com>
2023-04-21 09:06:06 -07:00
yzhang93
25c5fc44ae Modify tuner.py to take vulkan target triple flag (#1328) 2023-04-20 14:31:32 -07:00
jinchen62
bda92a54ab Fix custom vae path (#1317) 2023-04-18 20:50:43 -07:00
jinchen62
747ed383b1 Add custom vae dropdown in webui (#1314) 2023-04-18 17:24:02 -07:00
jinchen62
b70919b38d Fix memory leak with ondemand (#1312)
support ondemand for outpainting and multi batch_count
2023-04-18 13:03:16 -05:00
m68k-fr
4e513d647f Update list of scheduler available for inferences (#1298) 2023-04-17 22:37:00 -05:00
jinchen62
94cd2a0fed Fix outpainting config (#1310) 2023-04-17 10:48:52 -07:00
Kyle Herndon
606029c01c Fix LoRA device format bug and allow LoRA to resume from a previous training 2023-04-17 13:19:46 +05:30
yzhang93
467f900759 Add auto-tuner to SD apps (#1291) 2023-04-12 09:21:17 -07:00
jinchen62
428cfe8dae Fix low vram mode issues (#1295)
- add ondemand back to img2img
- workaround memory leak for batch count
2023-04-11 17:59:09 -07:00
Gaurav Shukla
1b49b5149a [SD] Add Img2Img rest API
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
2023-04-11 23:06:58 +05:30
jinchen62
3002793301 Unload clip on demand and workaround memory leak (#1283) 2023-04-10 16:59:03 -07:00
jinchen62
a0af3bb0cb xload and unload models (#1242) 2023-04-03 14:42:18 -07:00
Gaurav Shukla
f49d41a807 [SD] Add Stable diffusion text2image rest API (#1265)
Signed-off-by: Gaurav Shukla <gaurav@nod-labs.com>
2023-04-03 12:02:24 -07:00
Abhishek Varma
0ef6a0e234 [SD] Fix Stencil scribble crash by updating image resize (#1255)
-- This commit updates Stencil resize feature to cap the size of
   images within [128,768] as supported by the SD pipeline.
-- This solves the issue of scribble crashing on larger image.

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
Co-authored-by: Abhishek Varma <abhishek@nod-labs.com>
2023-03-28 10:13:11 -07:00
Daniel Garvey
5bb7846227 single entry point exe for all cli apps (#1158)
usage:
add --app="img2img" (or "inpaint" "outpaint" "txt2img")
2023-03-28 11:15:21 -05:00
Phaneesh Barwaria
431132b8ee Fix img2img mode switch (#1247)
* add updated scheduler value in global config

* clear scheduler global variable with others
2023-03-27 07:01:22 -07:00
Kyle Herndon
0b0526699a Fix incorrect device argument initialization for LoRA training by extracting the device type and number and formatting it for pytorch (#1237)
Co-authored-by: Kyle Herndon <kyle@nod-labs.com>
2023-03-24 01:10:50 -07:00
Abhishek Varma
593428bda4 [SD] Fix for transformers/__init__.py issue in PyInstaller (#1233)
-- This commit fixes the transformers/__init__.py issue in PyInstaller.

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
Co-authored-by: Abhishek Varma <abhishek@nod-labs.com>
2023-03-22 08:43:53 -07:00
Abhishek Varma
cede9b4fec [SD] Fix custom_vae as a required parameter in inpaint (#1232) 2023-03-22 04:30:17 -07:00
Prashant Kumar
c2360303f0 Add the int8 quantized model. 2023-03-22 16:28:13 +05:30
jinchen62
420366c1b8 Move schedulers to global obj (#1225) 2023-03-21 22:40:43 -07:00
Kyle Herndon
c23fcf3748 Fix incorrect device argument initialization for LoRA training (#1231)
Co-authored-by: Kyle Herndon <kyle@nod-labs.com>
Co-authored-by: powderluv <powderluv@users.noreply.github.com>
2023-03-21 19:07:18 -07:00
Abhishek Varma
8b8cc7fd33 [SD] Update LoRA inference to handle various checkpoints (#1215) 2023-03-21 06:52:20 -07:00
m68k-fr
4a622532e5 [Web] Stop images (#1212) 2023-03-19 14:37:30 -07:00
Kyle Herndon
ba48ff8d25 Implement LoRA training and UI for training and UI for inference in img2img, inpaint, outpaint (#1200)
txt2img inference UI is already committed.

Co-authored-by: Kyle Herndon <kyle@nod-labs.com>
Co-authored-by: powderluv <powderluv@users.noreply.github.com>
2023-03-17 12:54:56 -07:00
Gaurav Shukla
638840925c [SD] Add support for larger size upscaling (#1204)
Signed-off-by: Gaurav Shukla <gaurav@nod-labs.com>
2023-03-17 10:20:48 -07:00
m68k-fr
b661656c03 [Web] Fix custom model path for upscaler (#1199) 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) 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>
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
m68k-fr
2dd1491ec1 [Web] Add clear queue button (#1192) 2023-03-15 10:12:59 -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
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
1b08242aaa [Web] Improve dropdowns ux (#1175) 2023-03-12 12:41:51 -07:00