Skip to content

Commit 9d6d728

Browse files
committed
Squashed commit of the following:
commit 1c649e4 Author: Lincoln Stein <[email protected]> Date: Mon Sep 12 13:29:16 2022 -0400 fix torchvision dependency version CompVis#511 commit 4d197f6 Merge: a3e07fb 190ba78 Author: Lincoln Stein <[email protected]> Date: Mon Sep 12 07:29:19 2022 -0400 Merge branch 'development' of github.com:lstein/stable-diffusion into development commit a3e07fb Author: Lincoln Stein <[email protected]> Date: Mon Sep 12 07:28:58 2022 -0400 fix grid crash commit 9fa1f31 Author: Lincoln Stein <[email protected]> Date: Mon Sep 12 07:07:05 2022 -0400 fix opencv and realesrgan dependencies in mac install commit 190ba78 Author: Lincoln Stein <[email protected]> Date: Mon Sep 12 01:50:58 2022 -0400 Update requirements-mac.txt Fixed dangling dash on last line. commit 25d9ccc Author: Any-Winter-4079 <[email protected]> Date: Mon Sep 12 03:17:29 2022 +0200 Update model.py commit 9cdf3ac Author: Any-Winter-4079 <[email protected]> Date: Mon Sep 12 02:52:36 2022 +0200 Update attention.py Performance improvements to generate larger images in M1 CompVis#431 Update attention.py Added dtype=r1.dtype to softmax commit 49a96b9 Author: Mihai <[email protected]> Date: Sat Sep 10 16:58:07 2022 +0300 ~7% speedup (1.57 to 1.69it/s) from switch to += in ldm.modules.attention. (CompVis#482) Tested on 8GB eGPU nvidia setup so YMMV. 512x512 output, max VRAM stays same. commit aba94b8 Author: Niek van der Maas <[email protected]> Date: Fri Sep 9 15:01:37 2022 +0200 Fix macOS `pyenv` instructions, add code block highlight (CompVis#441) Fix: `anaconda3-latest` does not work, specify the correct virtualenv, add missing init. commit aac5102 Author: Henry van Megen <[email protected]> Date: Thu Sep 8 05:16:35 2022 +0200 Disabled debug output (CompVis#436) Co-authored-by: Henry van Megen <[email protected]> commit 0ab5a36 Author: Lincoln Stein <[email protected]> Date: Sun Sep 11 17:19:46 2022 -0400 fix missing lines in outputs commit 5e43372 Author: Lincoln Stein <[email protected]> Date: Sun Sep 11 16:20:14 2022 -0400 upped max_steps in v1-finetune.yaml and fixed TI docs to address CompVis#493 commit 7708f4f Author: Lincoln Stein <[email protected]> Date: Sun Sep 11 16:03:37 2022 -0400 slight efficiency gain by using += in attention.py commit b86a1de Author: blessedcoolant <[email protected]> Date: Mon Sep 12 07:47:12 2022 +1200 Remove print statement styling (CompVis#504) Co-authored-by: Lincoln Stein <[email protected]> commit 4951e66 Author: chromaticist <[email protected]> Date: Sun Sep 11 12:44:26 2022 -0700 Adding support for .bin files from huggingface concepts (CompVis#498) * Adding support for .bin files from huggingface concepts * Updating documentation to include huggingface .bin info commit 79b445b Merge: a323070 f7662c1 Author: Lincoln Stein <[email protected]> Date: Sun Sep 11 15:39:38 2022 -0400 Merge branch 'development' of github.com:lstein/stable-diffusion into development commit a323070 Author: Lincoln Stein <[email protected]> Date: Sun Sep 11 15:28:57 2022 -0400 update requirements for new location of gfpgan commit f7662c1 Author: Lincoln Stein <[email protected]> Date: Sun Sep 11 15:00:24 2022 -0400 update requirements for changed location of gfpgan commit 93c242c Author: Lincoln Stein <[email protected]> Date: Sun Sep 11 14:47:58 2022 -0400 make gfpgan_model_exists flag available to web interface commit c7c6cd7 Author: Lincoln Stein <[email protected]> Date: Sun Sep 11 14:43:07 2022 -0400 Update UPSCALE.md New instructions needed to accommodate fact that the ESRGAN and GFPGAN packages are now installed by environment.yaml. commit 77ca83e Author: Lincoln Stein <[email protected]> Date: Sun Sep 11 14:31:56 2022 -0400 Update CLI.md Final documentation tweak. commit 0ea145d Author: Lincoln Stein <[email protected]> Date: Sun Sep 11 14:29:26 2022 -0400 Update CLI.md More doc fixes. commit 162285a Author: Lincoln Stein <[email protected]> Date: Sun Sep 11 14:28:45 2022 -0400 Update CLI.md Minor documentation fix commit 37c921d Author: Lincoln Stein <[email protected]> Date: Sun Sep 11 14:26:41 2022 -0400 documentation enhancements commit 4f72cb4 Author: Lincoln Stein <[email protected]> Date: Sun Sep 11 13:05:38 2022 -0400 moved the notebook files into their own directory commit 878ef2e Author: Lincoln Stein <[email protected]> Date: Sun Sep 11 12:58:06 2022 -0400 documentation tweaks commit 4923118 Merge: 16f6a67 defafc0 Author: Lincoln Stein <[email protected]> Date: Sun Sep 11 12:51:25 2022 -0400 Merge branch 'development' of github.com:lstein/stable-diffusion into development commit defafc0 Author: Dominic Letz <[email protected]> Date: Sun Sep 11 18:51:01 2022 +0200 Enable upscaling on m1 (CompVis#474) commit 16f6a67 Author: Lincoln Stein <[email protected]> Date: Sun Sep 11 12:47:26 2022 -0400 install GFPGAN inside SD repository in order to fix 'dark cast' issue CompVis#169 commit 0881d42 Author: blessedcoolant <[email protected]> Date: Mon Sep 12 03:52:43 2022 +1200 Docs Update (CompVis#466) Authored-by: @blessedcoolant Co-authored-by: Lincoln Stein <[email protected]> commit 9a29d44 Author: Gérald LONLAS <[email protected]> Date: Sun Sep 11 23:23:18 2022 +0800 Revert "Add 3x Upscale option on the Web UI (CompVis#442)" (CompVis#488) This reverts commit f8a5408. commit d301836 Author: Lincoln Stein <[email protected]> Date: Sun Sep 11 10:52:19 2022 -0400 can select prior output for init_img using -1, -2, etc commit 70aa674 Author: Lincoln Stein <[email protected]> Date: Sun Sep 11 10:34:06 2022 -0400 merge PR CompVis#495 - keep using float16 in ldm.modules.attention commit 8748370 Author: Lincoln Stein <[email protected]> Date: Sun Sep 11 10:22:32 2022 -0400 negative -S indexing recovers correct previous seed; closes issue CompVis#476 commit 839e30e Author: Lincoln Stein <[email protected]> Date: Sun Sep 11 10:02:44 2022 -0400 improve CUDA VRAM monitoring extra check that device==cuda before getting VRAM stats commit bfb2781 Author: tildebyte <[email protected]> Date: Sat Sep 10 10:15:56 2022 -0400 fix(readme): add note about updating env via conda (CompVis#475) commit 5c43988 Author: Lincoln Stein <[email protected]> Date: Sat Sep 10 10:02:43 2022 -0400 reduce VRAM memory usage by half during model loading * This moves the call to half() before model.to(device) to avoid GPU copy of full model. Improves speed and reduces memory usage dramatically * This fix contributed by @mh-dm (Mihai) commit 9912270 Merge: 817c4a2 ecc6b75 Author: Lincoln Stein <[email protected]> Date: Sat Sep 10 09:54:34 2022 -0400 Merge branch 'development' of github.com:lstein/stable-diffusion into development commit 817c4a2 Author: Lincoln Stein <[email protected]> Date: Sat Sep 10 09:53:27 2022 -0400 remove -F option from normalized prompt; closes CompVis#483 commit ecc6b75 Author: Lincoln Stein <[email protected]> Date: Sat Sep 10 09:53:27 2022 -0400 remove -F option from normalized prompt commit 723d074 Author: Lincoln Stein <[email protected]> Date: Fri Sep 9 18:49:51 2022 -0400 Allow ctrl c when using --from_file (CompVis#472) * added ansi escapes to highlight key parts of CLI session * adjust exception handling so that ^C will abort when reading prompts from a file commit 75f633c Author: Lincoln Stein <[email protected]> Date: Fri Sep 9 12:03:45 2022 -0400 re-add new logo commit 10db192 Author: Lincoln Stein <[email protected]> Date: Fri Sep 9 09:26:10 2022 -0400 changes to dogettx optimizations to run on m1 * Author @Any-Winter-4079 * Author @dogettx Thanks to many individuals who contributed time and hardware to benchmarking and debugging these changes. commit c85ae00 Author: Lincoln Stein <[email protected]> Date: Thu Sep 8 23:57:45 2022 -0400 fix bug which caused seed to get "stuck" on previous image even when UI specified -1 commit 1b5aae3 Author: Lincoln Stein <[email protected]> Date: Thu Sep 8 22:36:47 2022 -0400 add icon to dream web server commit 6abf739 Author: Lincoln Stein <[email protected]> Date: Thu Sep 8 22:25:09 2022 -0400 add favicon to web server commit db825b8 Merge: 33874ba afee7f9 Author: Lincoln Stein <[email protected]> Date: Thu Sep 8 22:17:37 2022 -0400 Merge branch 'deNULL-development' into development commit 33874ba Author: Lincoln Stein <[email protected]> Date: Thu Sep 8 22:16:29 2022 -0400 Squashed commit of the following: commit afee7f9 Merge: 6531446 171f8db Author: Lincoln Stein <[email protected]> Date: Thu Sep 8 22:14:32 2022 -0400 Merge branch 'development' of github.com:deNULL/stable-diffusion into deNULL-development commit 171f8db Author: Denis Olshin <[email protected]> Date: Thu Sep 8 03:15:20 2022 +0300 saving full prompt to metadata when using web ui commit d7e67b6 Author: Denis Olshin <[email protected]> Date: Thu Sep 8 01:51:47 2022 +0300 better logic for clicking to make variations commit afee7f9 Merge: 6531446 171f8db Author: Lincoln Stein <[email protected]> Date: Thu Sep 8 22:14:32 2022 -0400 Merge branch 'development' of github.com:deNULL/stable-diffusion into deNULL-development commit 6531446 Author: Lincoln Stein <[email protected]> Date: Thu Sep 8 20:41:37 2022 -0400 work around unexplained crash when timesteps=1000 (CompVis#440) * work around unexplained crash when timesteps=1000 * this fix seems to work commit c33a84c Author: blessedcoolant <[email protected]> Date: Fri Sep 9 12:39:51 2022 +1200 Add New Logo (CompVis#454) * Add instructions on how to install alongside pyenv (CompVis#393) Like probably many others, I have a lot of different virtualenvs, one for each project. Most of them are handled by `pyenv`. After installing according to these instructions I had issues with ´pyenv`and `miniconda` fighting over the $PATH of my system. But then I stumbled upon this nice solution on SO: https://stackoverflow.com/a/73139031 , upon which I have based my suggested changes. It runs perfectly on my M1 setup, with the anaconda setup as a virtual environment handled by pyenv. Feel free to incorporate these instructions as you see fit. Thanks a million for all your hard work. * Disabled debug output (CompVis#436) Co-authored-by: Henry van Megen <[email protected]> * Add New Logo Co-authored-by: Håvard Gulldahl <[email protected]> Co-authored-by: Henry van Megen <[email protected]> Co-authored-by: Henry van Megen <[email protected]> Co-authored-by: Lincoln Stein <[email protected]> commit f8a5408 Author: Gérald LONLAS <[email protected]> Date: Fri Sep 9 01:45:54 2022 +0800 Add 3x Upscale option on the Web UI (CompVis#442) commit 244239e Author: James Reynolds <[email protected]> Date: Thu Sep 8 05:36:33 2022 -0600 macOS CI workflow, dream.py exits with an error, but the workflow com… (CompVis#396) * macOS CI workflow, dream.py exits with an error, but the workflow completes. * Files for testing Co-authored-by: James Reynolds <[email protected]> Co-authored-by: Lincoln Stein <[email protected]> commit 711d49e Author: James Reynolds <[email protected]> Date: Thu Sep 8 05:35:08 2022 -0600 Cache model workflow (CompVis#394) * Add workflow that caches the model, step 1 for CI * Change name of workflow job Co-authored-by: James Reynolds <[email protected]> Co-authored-by: Lincoln Stein <[email protected]> commit 7996a30 Author: Lincoln Stein <[email protected]> Date: Thu Sep 8 07:34:03 2022 -0400 add auto-creation of mask for inpainting (CompVis#438) * now use a single init image for both image and mask * turn on debugging for now to write out mask and image * add back -M option as a fallback commit a69ca31 Author: elliotsayes <[email protected]> Date: Thu Sep 8 15:30:06 2022 +1200 .gitignore WebUI temp files (CompVis#430) * Add instructions on how to install alongside pyenv (CompVis#393) Like probably many others, I have a lot of different virtualenvs, one for each project. Most of them are handled by `pyenv`. After installing according to these instructions I had issues with ´pyenv`and `miniconda` fighting over the $PATH of my system. But then I stumbled upon this nice solution on SO: https://stackoverflow.com/a/73139031 , upon which I have based my suggested changes. It runs perfectly on my M1 setup, with the anaconda setup as a virtual environment handled by pyenv. Feel free to incorporate these instructions as you see fit. Thanks a million for all your hard work. * .gitignore WebUI temp files Co-authored-by: Håvard Gulldahl <[email protected]> commit 5c6b612 Author: Lincoln Stein <[email protected]> Date: Wed Sep 7 22:50:55 2022 -0400 fix bug that caused same seed to be redisplayed repeatedly commit 56f155c Author: Johan Roxendal <[email protected]> Date: Thu Sep 8 04:50:06 2022 +0200 added support for parsing run log and displaying images in the frontend init state (CompVis#410) Co-authored-by: Johan Roxendal <[email protected]> Co-authored-by: Lincoln Stein <[email protected]> commit 4168774 Author: Lincoln Stein <[email protected]> Date: Wed Sep 7 20:24:35 2022 -0400 added missing initialization of latent_noise to None commit 171f8db Author: Denis Olshin <[email protected]> Date: Thu Sep 8 03:15:20 2022 +0300 saving full prompt to metadata when using web ui commit d7e67b6 Author: Denis Olshin <[email protected]> Date: Thu Sep 8 01:51:47 2022 +0300 better logic for clicking to make variations commit d1d044a Author: Lincoln Stein <[email protected]> Date: Wed Sep 7 17:56:59 2022 -0400 actual image seed now written into web log rather than -1 (CompVis#428) commit edada04 Author: Arturo Mendivil <[email protected]> Date: Wed Sep 7 10:42:26 2022 -0700 Improve notebook and add requirements file (CompVis#422) commit 29ab3c2 Author: Lincoln Stein <[email protected]> Date: Wed Sep 7 13:28:11 2022 -0400 disable neonpixel optimizations on M1 hardware (CompVis#414) * disable neonpixel optimizations on M1 hardware * fix typo that was causing random noise images on m1 commit 7670ecc Author: cody <[email protected]> Date: Wed Sep 7 12:24:41 2022 -0500 add more keyboard support on the web server (CompVis#391) add ability to submit prompts with the "enter" key add ability to cancel generations with the "escape" key commit dd2aeda Author: Lincoln Stein <[email protected]> Date: Wed Sep 7 13:23:53 2022 -0400 report VRAM usage stats during initial model loading (CompVis#419) commit f628477 Author: Lincoln Stein <[email protected]> Date: Tue Sep 6 17:12:39 2022 -0400 Squashed commit of the following: commit 7d1344282d942a33dcecda4d5144fc154ec82915 Merge: caf4ea3 ebeb556 Author: Lincoln Stein <[email protected]> Date: Mon Sep 5 10:07:27 2022 -0400 Merge branch 'development' of github.com:WebDev9000/stable-diffusion into WebDev9000-development commit ebeb556 Author: Web Dev 9000 <[email protected]> Date: Sun Sep 4 18:05:15 2022 -0700 Fixed unintentionally removed lines commit ff2c4b9 Author: Web Dev 9000 <[email protected]> Date: Sun Sep 4 17:50:13 2022 -0700 Add ability to recreate variations via image click commit c012929 Author: Web Dev 9000 <[email protected]> Date: Sun Sep 4 14:35:33 2022 -0700 Add files via upload commit 02a6018 Author: Web Dev 9000 <[email protected]> Date: Sun Sep 4 14:35:07 2022 -0700 Add files via upload commit eef7889 Author: Olivier Louvignes <[email protected]> Date: Tue Sep 6 12:41:08 2022 +0200 feat(txt2img): allow from_file to work with len(lines) < batch_size (CompVis#349) commit 720e5cd Author: Lincoln Stein <[email protected]> Date: Mon Sep 5 20:40:10 2022 -0400 Refactoring simplet2i (CompVis#387) * start refactoring -not yet functional * first phase of refactor done - not sure weighted prompts working * Second phase of refactoring. Everything mostly working. * The refactoring has moved all the hard-core inference work into ldm.dream.generator.*, where there are submodules for txt2img and img2img. inpaint will go in there as well. * Some additional refactoring will be done soon, but relatively minor work. * fix -save_orig flag to actually work * add @neonsecret attention.py memory optimization * remove unneeded imports * move token logging into conditioning.py * add placeholder version of inpaint; porting in progress * fix crash in img2img * inpainting working; not tested on variations * fix crashes in img2img * ported attention.py memory optimization CompVis#117 from basujindal branch * added @torch_no_grad() decorators to img2img, txt2img, inpaint closures * Final commit prior to PR against development * fixup crash when generating intermediate images in web UI * rename ldm.simplet2i to ldm.generate * add backward-compatibility simplet2i shell with deprecation warning * add back in mps exception, addresses @Vargol comment in CompVis#354 * replaced Conditioning class with exported functions * fix wrong type of with_variations attribute during intialization * changed "image_iterator()" to "get_make_image()" * raise NotImplementedError for calling get_make_image() in parent class * Update ldm/generate.py better error message Co-authored-by: Kevin Gibbons <[email protected]> * minor stylistic fixes and assertion checks from code review * moved get_noise() method into img2img class * break get_noise() into two methods, one for txt2img and the other for img2img * inpainting works on non-square images now * make get_noise() an abstract method in base class * much improved inpainting Co-authored-by: Kevin Gibbons <[email protected]> commit 1ad2a8e Author: thealanle <[email protected]> Date: Mon Sep 5 17:35:04 2022 -0700 Fix --outdir function for web (CompVis#373) * Fix --outdir function for web * Removed unnecessary hardcoded path commit 52d8bb2 Author: Lincoln Stein <[email protected]> Date: Mon Sep 5 10:31:59 2022 -0400 Squashed commit of the following: commit 0cd48e932f1326e000c46f4140f98697eb9bdc79 Author: Lincoln Stein <[email protected]> Date: Mon Sep 5 10:27:43 2022 -0400 resolve conflicts with development commit d7bc8c12e05535a363ac7c745a3f3abc2773bfcf Author: Scott McMillin <[email protected]> Date: Sun Sep 4 18:52:09 2022 -0500 Add title attribute back to img tag commit 5397c89184ebfb8260bc2d8c3f23e73e103d24e6 Author: Scott McMillin <[email protected]> Date: Sun Sep 4 13:49:46 2022 -0500 Remove temp code commit 1da080b50972696db2930681a09cb1c14e524758 Author: Scott McMillin <[email protected]> Date: Sun Sep 4 13:33:56 2022 -0500 Cleaned up HTML; small style changes; image click opens image; add seed to figcaption beneath image commit caf4ea3 Author: Adam Rice <[email protected]> Date: Mon Sep 5 10:05:39 2022 -0400 Add a 'Remove Image' button to clear the file upload field (CompVis#382) * added "remove image" button * styled a new "remove image" button * Update index.js commit 95c088b Author: Kevin Gibbons <[email protected]> Date: Sun Sep 4 19:04:14 2022 -0700 Revert "Add CORS headers to dream server to ease integration with third-party web interfaces" (CompVis#371) This reverts commit 91e826e. commit a20113d Author: Kevin Gibbons <[email protected]> Date: Sun Sep 4 18:59:12 2022 -0700 put no_grad decorator on make_image closures (CompVis#375) commit 0f93dad Author: Lincoln Stein <[email protected]> Date: Sun Sep 4 21:39:15 2022 -0400 fix several dangling references to --gfpgan option, which no longer exists commit f4004f6 Author: tildebyte <[email protected]> Date: Sun Sep 4 19:43:04 2022 -0400 TOIL(requirements): Split requirements to per-platform (CompVis#355) * toil(reqs): split requirements to per-platform Signed-off-by: Ben Alkov <[email protected]> * toil(reqs): fix for Win and Lin... ...allow pip to resolve latest torch, numpy Signed-off-by: Ben Alkov <[email protected]> * toil(install): update reqs in Win install notebook Signed-off-by: Ben Alkov <[email protected]> Signed-off-by: Ben Alkov <[email protected]> commit 4406fd1 Merge: 5116c81 fd7a72e Author: Lincoln Stein <[email protected]> Date: Sun Sep 4 08:23:53 2022 -0400 Merge branch 'SebastianAigner-main' into development Add support for full CORS headers for dream server. commit fd7a72e Author: Lincoln Stein <[email protected]> Date: Sun Sep 4 08:23:11 2022 -0400 remove debugging message commit 3a2be62 Merge: 91e826e 5116c81 Author: Lincoln Stein <[email protected]> Date: Sun Sep 4 08:15:51 2022 -0400 Merge branch 'development' into main commit 5116c81 Author: Justin Wong <[email protected]> Date: Sun Sep 4 07:17:58 2022 -0400 fix save_original flag saving to the same filename (CompVis#360) * Update README.md with new Anaconda install steps (CompVis#347) pip3 version did not work for me and this is the recommended way to install Anaconda now it seems * fix save_original flag saving to the same filename Before this, the `--save_orig` flag was not working. The upscaled/GFPGAN would overwrite the original output image. Co-authored-by: greentext2 <[email protected]> commit 91e826e Author: Sebastian Aigner <[email protected]> Date: Sun Sep 4 10:22:54 2022 +0200 Add CORS headers to dream server to ease integration with third-party web interfaces commit 6266d9e Author: Lincoln Stein <[email protected]> Date: Sat Sep 3 15:45:20 2022 -0400 remove stray debugging message commit 138956e Author: greentext2 <[email protected]> Date: Sat Sep 3 13:38:57 2022 -0500 Update README.md with new Anaconda install steps (CompVis#347) pip3 version did not work for me and this is the recommended way to install Anaconda now it seems commit 60be735 Author: Cora Johnson-Roberson <[email protected]> Date: Sat Sep 3 14:28:34 2022 -0400 Switch to regular pytorch channel and restore Python 3.10 for Macs. (CompVis#301) * Switch to regular pytorch channel and restore Python 3.10 for Macs. Although pytorch-nightly should in theory be faster, it is currently causing increased memory usage and slower iterations: invoke-ai/InvokeAI#283 (comment) This changes the environment-mac.yaml file back to the regular pytorch channel and moves the `transformers` dep into pip for now (since it cannot be satisfied until tokenizers>=0.11 is built for Python 3.10). * Specify versions for Pip packages as well. commit d0d95d3 Author: Lincoln Stein <[email protected]> Date: Sat Sep 3 14:10:31 2022 -0400 make initimg appear in web log commit b90a215 Merge: 1eee811 6270e31 Author: Lincoln Stein <[email protected]> Date: Sat Sep 3 13:47:15 2022 -0400 Merge branch 'prixt-seamless' into development commit 6270e31 Author: Lincoln Stein <[email protected]> Date: Sat Sep 3 13:46:29 2022 -0400 add credit to prixt for seamless circular tiling commit a01b7bd Merge: 1eee811 9d88abe Author: Lincoln Stein <[email protected]> Date: Sat Sep 3 13:43:04 2022 -0400 add web interface for seamless option commit 1eee811 Merge: 64eca42 fb857f0 Author: Lincoln Stein <[email protected]> Date: Sat Sep 3 12:33:39 2022 -0400 Merge branch 'development' of github.com:lstein/stable-diffusion into development commit 64eca42 Merge: 9130ad7 21a1f68 Author: Lincoln Stein <[email protected]> Date: Sat Sep 3 12:33:05 2022 -0400 Merge branch 'main' into development * brings in small documentation fixes that were added directly to main during release tweaking. commit fb857f0 Author: Lincoln Stein <[email protected]> Date: Sat Sep 3 12:07:07 2022 -0400 fix typo in docs commit 9d88abe Author: prixt <[email protected]> Date: Sat Sep 3 22:42:16 2022 +0900 fixed typo commit a61e49b Author: prixt <[email protected]> Date: Sat Sep 3 22:39:35 2022 +0900 * Removed unnecessary code * Added description about --seamless commit 02bee4f Author: prixt <[email protected]> Date: Sat Sep 3 16:08:03 2022 +0900 added --seamless tag logging to normalize_prompt commit d922b53 Author: prixt <[email protected]> Date: Sat Sep 3 15:13:31 2022 +0900 added seamless tiling mode and commands
1 parent 62863ac commit 9d6d728

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

64 files changed

+3834
-2736
lines changed

.github/workflows/cache-model.yml

Lines changed: 64 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,64 @@
1+
name: Cache Model
2+
on:
3+
workflow_dispatch
4+
jobs:
5+
build:
6+
strategy:
7+
matrix:
8+
os: [ macos-12 ]
9+
name: Create Caches using ${{ matrix.os }}
10+
runs-on: ${{ matrix.os }}
11+
steps:
12+
- name: Checkout sources
13+
uses: actions/checkout@v3
14+
- name: Cache model
15+
id: cache-sd-v1-4
16+
uses: actions/cache@v3
17+
env:
18+
cache-name: cache-sd-v1-4
19+
with:
20+
path: models/ldm/stable-diffusion-v1/model.ckpt
21+
key: ${{ env.cache-name }}
22+
restore-keys: |
23+
${{ env.cache-name }}
24+
- name: Download Stable Diffusion v1.4 model
25+
if: ${{ steps.cache-sd-v1-4.outputs.cache-hit != 'true' }}
26+
continue-on-error: true
27+
run: |
28+
if [ ! -e models/ldm/stable-diffusion-v1 ]; then
29+
mkdir -p models/ldm/stable-diffusion-v1
30+
fi
31+
if [ ! -e models/ldm/stable-diffusion-v1/model.ckpt ]; then
32+
curl -o models/ldm/stable-diffusion-v1/model.ckpt ${{ secrets.SD_V1_4_URL }}
33+
fi
34+
# Uncomment this when we no longer make changes to environment-mac.yaml
35+
# - name: Cache environment
36+
# id: cache-conda-env-ldm
37+
# uses: actions/cache@v3
38+
# env:
39+
# cache-name: cache-conda-env-ldm
40+
# with:
41+
# path: ~/.conda/envs/ldm
42+
# key: ${{ env.cache-name }}
43+
# restore-keys: |
44+
# ${{ env.cache-name }}
45+
- name: Install dependencies
46+
# if: ${{ steps.cache-conda-env-ldm.outputs.cache-hit != 'true' }}
47+
run: |
48+
conda env create -f environment-mac.yaml
49+
- name: Cache hugginface and torch models
50+
id: cache-hugginface-torch
51+
uses: actions/cache@v3
52+
env:
53+
cache-name: cache-hugginface-torch
54+
with:
55+
path: ~/.cache
56+
key: ${{ env.cache-name }}
57+
restore-keys: |
58+
${{ env.cache-name }}
59+
- name: Download Huggingface and Torch models
60+
if: ${{ steps.cache-hugginface-torch.outputs.cache-hit != 'true' }}
61+
continue-on-error: true
62+
run: |
63+
export PYTHON_BIN=/usr/local/miniconda/envs/ldm/bin/python
64+
$PYTHON_BIN scripts/preload_models.py
Lines changed: 80 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,80 @@
1+
name: Build
2+
on:
3+
push:
4+
branches: [ main ]
5+
pull_request:
6+
branches: [ main ]
7+
jobs:
8+
build:
9+
strategy:
10+
matrix:
11+
os: [ macos-12 ]
12+
name: Build on ${{ matrix.os }} miniconda
13+
runs-on: ${{ matrix.os }}
14+
steps:
15+
- name: Checkout sources
16+
uses: actions/checkout@v3
17+
- name: Cache model
18+
id: cache-sd-v1-4
19+
uses: actions/cache@v3
20+
env:
21+
cache-name: cache-sd-v1-4
22+
with:
23+
path: models/ldm/stable-diffusion-v1/model.ckpt
24+
key: ${{ env.cache-name }}
25+
restore-keys: |
26+
${{ env.cache-name }}
27+
- name: Download Stable Diffusion v1.4 model
28+
if: ${{ steps.cache-sd-v1-4.outputs.cache-hit != 'true' }}
29+
continue-on-error: true
30+
run: |
31+
if [ ! -e models/ldm/stable-diffusion-v1 ]; then
32+
mkdir -p models/ldm/stable-diffusion-v1
33+
fi
34+
if [ ! -e models/ldm/stable-diffusion-v1/model.ckpt ]; then
35+
curl -o models/ldm/stable-diffusion-v1/model.ckpt ${{ secrets.SD_V1_4_URL }}
36+
fi
37+
# Uncomment this when we no longer make changes to environment-mac.yaml
38+
# - name: Cache environment
39+
# id: cache-conda-env-ldm
40+
# uses: actions/cache@v3
41+
# env:
42+
# cache-name: cache-conda-env-ldm
43+
# with:
44+
# path: ~/.conda/envs/ldm
45+
# key: ${{ env.cache-name }}
46+
# restore-keys: |
47+
# ${{ env.cache-name }}
48+
- name: Install dependencies
49+
# if: ${{ steps.cache-conda-env-ldm.outputs.cache-hit != 'true' }}
50+
run: |
51+
conda env create -f environment-mac.yaml
52+
- name: Cache hugginface and torch models
53+
id: cache-hugginface-torch
54+
uses: actions/cache@v3
55+
env:
56+
cache-name: cache-hugginface-torch
57+
with:
58+
path: ~/.cache
59+
key: ${{ env.cache-name }}
60+
restore-keys: |
61+
${{ env.cache-name }}
62+
- name: Download Huggingface and Torch models
63+
if: ${{ steps.cache-hugginface-torch.outputs.cache-hit != 'true' }}
64+
continue-on-error: true
65+
run: |
66+
export PYTHON_BIN=/usr/local/miniconda/envs/ldm/bin/python
67+
$PYTHON_BIN scripts/preload_models.py
68+
- name: Run the tests
69+
run: |
70+
# Note, can't "activate" via automation, and activation is just env vars and path
71+
export PYTHON_BIN=/usr/local/miniconda/envs/ldm/bin/python
72+
export PYTORCH_ENABLE_MPS_FALLBACK=1
73+
$PYTHON_BIN scripts/preload_models.py
74+
mkdir -p outputs/img-samples
75+
time $PYTHON_BIN scripts/dream.py --from_file tests/prompts.txt </dev/null 2> outputs/img-samples/err.log > outputs/img-samples/out.log
76+
- name: Archive results
77+
uses: actions/upload-artifact@v3
78+
with:
79+
name: results
80+
path: outputs/img-samples

.gitignore

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -77,6 +77,9 @@ db.sqlite3-journal
7777
instance/
7878
.webassets-cache
7979

80+
# WebUI temp files:
81+
img2img-tmp.png
82+
8083
# Scrapy stuff:
8184
.scrapy
8285

0 commit comments

Comments
 (0)