mirror of
https://github.com/invoke-ai/InvokeAI.git
synced 2026-04-23 03:00:31 -04:00
Squashed commit of the following:
commit1c649e4663Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Mon Sep 12 13:29:16 2022 -0400 fix torchvision dependency version #511 commit4d197f699eMerge:a3e07fb190ba78Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Mon Sep 12 07:29:19 2022 -0400 Merge branch 'development' of github.com:lstein/stable-diffusion into development commita3e07fb84aAuthor: Lincoln Stein <lincoln.stein@gmail.com> Date: Mon Sep 12 07:28:58 2022 -0400 fix grid crash commit9fa1f31bf2Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Mon Sep 12 07:07:05 2022 -0400 fix opencv and realesrgan dependencies in mac install commit190ba78960Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Mon Sep 12 01:50:58 2022 -0400 Update requirements-mac.txt Fixed dangling dash on last line. commit25d9ccc509Author: Any-Winter-4079 <50542132+Any-Winter-4079@users.noreply.github.com> Date: Mon Sep 12 03:17:29 2022 +0200 Update model.py commit9cdf3aca7dAuthor: Any-Winter-4079 <50542132+Any-Winter-4079@users.noreply.github.com> Date: Mon Sep 12 02:52:36 2022 +0200 Update attention.py Performance improvements to generate larger images in M1 #431 Update attention.py Added dtype=r1.dtype to softmax commit49a96b90d8Author: Mihai <299015+mh-dm@users.noreply.github.com> Date: Sat Sep 10 16:58:07 2022 +0300 ~7% speedup (1.57 to 1.69it/s) from switch to += in ldm.modules.attention. (#482) Tested on 8GB eGPU nvidia setup so YMMV. 512x512 output, max VRAM stays same. commitaba94b85e8Author: Niek van der Maas <mail@niekvandermaas.nl> Date: Fri Sep 9 15:01:37 2022 +0200 Fix macOS `pyenv` instructions, add code block highlight (#441) Fix: `anaconda3-latest` does not work, specify the correct virtualenv, add missing init. commitaac5102cf3Author: Henry van Megen <h.vanmegen@gmail.com> Date: Thu Sep 8 05:16:35 2022 +0200 Disabled debug output (#436) Co-authored-by: Henry van Megen <hvanmegen@gmail.com> commit0ab5a36464Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Sun Sep 11 17:19:46 2022 -0400 fix missing lines in outputs commit5e433728b5Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Sun Sep 11 16:20:14 2022 -0400 upped max_steps in v1-finetune.yaml and fixed TI docs to address #493 commit7708f4fb98Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Sun Sep 11 16:03:37 2022 -0400 slight efficiency gain by using += in attention.py commitb86a1deb00Author: blessedcoolant <54517381+blessedcoolant@users.noreply.github.com> Date: Mon Sep 12 07:47:12 2022 +1200 Remove print statement styling (#504) Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com> commit4951e66103Author: chromaticist <mhostick@gmail.com> Date: Sun Sep 11 12:44:26 2022 -0700 Adding support for .bin files from huggingface concepts (#498) * Adding support for .bin files from huggingface concepts * Updating documentation to include huggingface .bin info commit79b445b0caMerge: a323070f7662c1Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Sun Sep 11 15:39:38 2022 -0400 Merge branch 'development' of github.com:lstein/stable-diffusion into development commita323070a4dAuthor: Lincoln Stein <lincoln.stein@gmail.com> Date: Sun Sep 11 15:28:57 2022 -0400 update requirements for new location of gfpgan commitf7662c1808Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Sun Sep 11 15:00:24 2022 -0400 update requirements for changed location of gfpgan commit93c242c9fbAuthor: Lincoln Stein <lincoln.stein@gmail.com> Date: Sun Sep 11 14:47:58 2022 -0400 make gfpgan_model_exists flag available to web interface commitc7c6cd7735Author: Lincoln Stein <lincoln.stein@gmail.com> 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. commit77ca83e103Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Sun Sep 11 14:31:56 2022 -0400 Update CLI.md Final documentation tweak. commit0ea145d188Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Sun Sep 11 14:29:26 2022 -0400 Update CLI.md More doc fixes. commit162285ae86Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Sun Sep 11 14:28:45 2022 -0400 Update CLI.md Minor documentation fix commit37c921dfe2Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Sun Sep 11 14:26:41 2022 -0400 documentation enhancements commit4f72cb44adAuthor: Lincoln Stein <lincoln.stein@gmail.com> Date: Sun Sep 11 13:05:38 2022 -0400 moved the notebook files into their own directory commit878ef2e9e0Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Sun Sep 11 12:58:06 2022 -0400 documentation tweaks commit4923118610Merge:16f6a67defafc0Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Sun Sep 11 12:51:25 2022 -0400 Merge branch 'development' of github.com:lstein/stable-diffusion into development commitdefafc0e8eAuthor: Dominic Letz <dominic@diode.io> Date: Sun Sep 11 18:51:01 2022 +0200 Enable upscaling on m1 (#474) commit16f6a6731dAuthor: Lincoln Stein <lincoln.stein@gmail.com> Date: Sun Sep 11 12:47:26 2022 -0400 install GFPGAN inside SD repository in order to fix 'dark cast' issue #169 commit0881d429f2Author: blessedcoolant <54517381+blessedcoolant@users.noreply.github.com> Date: Mon Sep 12 03:52:43 2022 +1200 Docs Update (#466) Authored-by: @blessedcoolant Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com> commit9a29d442b4Author: Gérald LONLAS <gerald@lonlas.com> Date: Sun Sep 11 23:23:18 2022 +0800 Revert "Add 3x Upscale option on the Web UI (#442)" (#488) This reverts commitf8a540881c. commitd301836fbdAuthor: Lincoln Stein <lincoln.stein@gmail.com> Date: Sun Sep 11 10:52:19 2022 -0400 can select prior output for init_img using -1, -2, etc commit70aa674e9eAuthor: Lincoln Stein <lincoln.stein@gmail.com> Date: Sun Sep 11 10:34:06 2022 -0400 merge PR #495 - keep using float16 in ldm.modules.attention commit8748370f44Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Sun Sep 11 10:22:32 2022 -0400 negative -S indexing recovers correct previous seed; closes issue #476 commit839e30e4b8Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Sun Sep 11 10:02:44 2022 -0400 improve CUDA VRAM monitoring extra check that device==cuda before getting VRAM stats commitbfb2781279Author: tildebyte <337875+tildebyte@users.noreply.github.com> Date: Sat Sep 10 10:15:56 2022 -0400 fix(readme): add note about updating env via conda (#475) commit5c43988862Author: Lincoln Stein <lincoln.stein@gmail.com> 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) commit99122708caMerge:817c4a2ecc6b75Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Sat Sep 10 09:54:34 2022 -0400 Merge branch 'development' of github.com:lstein/stable-diffusion into development commit817c4a26deAuthor: Lincoln Stein <lincoln.stein@gmail.com> Date: Sat Sep 10 09:53:27 2022 -0400 remove -F option from normalized prompt; closes #483 commitecc6b75a3eAuthor: Lincoln Stein <lincoln.stein@gmail.com> Date: Sat Sep 10 09:53:27 2022 -0400 remove -F option from normalized prompt commit723d074442Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Fri Sep 9 18:49:51 2022 -0400 Allow ctrl c when using --from_file (#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 commit75f633cda8Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Fri Sep 9 12:03:45 2022 -0400 re-add new logo commit10db192cc4Author: Lincoln Stein <lincoln.stein@gmail.com> 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. commitc85ae00b33Author: Lincoln Stein <lincoln.stein@gmail.com> 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 commit1b5aae3ef3Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Thu Sep 8 22:36:47 2022 -0400 add icon to dream web server commit6abf739315Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Thu Sep 8 22:25:09 2022 -0400 add favicon to web server commitdb825b8138Merge:33874baafee7f9Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Thu Sep 8 22:17:37 2022 -0400 Merge branch 'deNULL-development' into development commit33874bae8dAuthor: Lincoln Stein <lincoln.stein@gmail.com> Date: Thu Sep 8 22:16:29 2022 -0400 Squashed commit of the following: commitafee7f9ceaMerge:6531446171f8dbAuthor: Lincoln Stein <lincoln.stein@gmail.com> Date: Thu Sep 8 22:14:32 2022 -0400 Merge branch 'development' of github.com:deNULL/stable-diffusion into deNULL-development commit171f8db742Author: Denis Olshin <me@denull.ru> Date: Thu Sep 8 03:15:20 2022 +0300 saving full prompt to metadata when using web ui commitd7e67b62f0Author: Denis Olshin <me@denull.ru> Date: Thu Sep 8 01:51:47 2022 +0300 better logic for clicking to make variations commitafee7f9ceaMerge:6531446171f8dbAuthor: Lincoln Stein <lincoln.stein@gmail.com> Date: Thu Sep 8 22:14:32 2022 -0400 Merge branch 'development' of github.com:deNULL/stable-diffusion into deNULL-development commit653144694fAuthor: Lincoln Stein <lincoln.stein@gmail.com> Date: Thu Sep 8 20:41:37 2022 -0400 work around unexplained crash when timesteps=1000 (#440) * work around unexplained crash when timesteps=1000 * this fix seems to work commitc33a84cdfdAuthor: blessedcoolant <54517381+blessedcoolant@users.noreply.github.com> Date: Fri Sep 9 12:39:51 2022 +1200 Add New Logo (#454) * Add instructions on how to install alongside pyenv (#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 (#436) Co-authored-by: Henry van Megen <hvanmegen@gmail.com> * Add New Logo Co-authored-by: Håvard Gulldahl <havard@lurtgjort.no> Co-authored-by: Henry van Megen <h.vanmegen@gmail.com> Co-authored-by: Henry van Megen <hvanmegen@gmail.com> Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com> commitf8a540881cAuthor: Gérald LONLAS <gerald@lonlas.com> Date: Fri Sep 9 01:45:54 2022 +0800 Add 3x Upscale option on the Web UI (#442) commit244239e5f6Author: James Reynolds <magnusviri@users.noreply.github.com> Date: Thu Sep 8 05:36:33 2022 -0600 macOS CI workflow, dream.py exits with an error, but the workflow com… (#396) * macOS CI workflow, dream.py exits with an error, but the workflow completes. * Files for testing Co-authored-by: James Reynolds <magnsuviri@me.com> Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com> commit711d49ed30Author: James Reynolds <magnusviri@users.noreply.github.com> Date: Thu Sep 8 05:35:08 2022 -0600 Cache model workflow (#394) * Add workflow that caches the model, step 1 for CI * Change name of workflow job Co-authored-by: James Reynolds <magnsuviri@me.com> Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com> commit7996a30e3aAuthor: Lincoln Stein <lincoln.stein@gmail.com> Date: Thu Sep 8 07:34:03 2022 -0400 add auto-creation of mask for inpainting (#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 commita69ca31f34Author: elliotsayes <elliotsayes@gmail.com> Date: Thu Sep 8 15:30:06 2022 +1200 .gitignore WebUI temp files (#430) * Add instructions on how to install alongside pyenv (#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 <havard@lurtgjort.no> commit5c6b612a72Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Wed Sep 7 22:50:55 2022 -0400 fix bug that caused same seed to be redisplayed repeatedly commit56f155c590Author: Johan Roxendal <johan@roxendal.com> Date: Thu Sep 8 04:50:06 2022 +0200 added support for parsing run log and displaying images in the frontend init state (#410) Co-authored-by: Johan Roxendal <johan.roxendal@litteraturbanken.se> Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com> commit41687746beAuthor: Lincoln Stein <lincoln.stein@gmail.com> Date: Wed Sep 7 20:24:35 2022 -0400 added missing initialization of latent_noise to None commit171f8db742Author: Denis Olshin <me@denull.ru> Date: Thu Sep 8 03:15:20 2022 +0300 saving full prompt to metadata when using web ui commitd7e67b62f0Author: Denis Olshin <me@denull.ru> Date: Thu Sep 8 01:51:47 2022 +0300 better logic for clicking to make variations commitd1d044aa87Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Wed Sep 7 17:56:59 2022 -0400 actual image seed now written into web log rather than -1 (#428) commitedada042b3Author: Arturo Mendivil <60411196+artmen1516@users.noreply.github.com> Date: Wed Sep 7 10:42:26 2022 -0700 Improve notebook and add requirements file (#422) commit29ab3c2028Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Wed Sep 7 13:28:11 2022 -0400 disable neonpixel optimizations on M1 hardware (#414) * disable neonpixel optimizations on M1 hardware * fix typo that was causing random noise images on m1 commit7670ecc63fAuthor: cody <cnmizell@gmail.com> Date: Wed Sep 7 12:24:41 2022 -0500 add more keyboard support on the web server (#391) add ability to submit prompts with the "enter" key add ability to cancel generations with the "escape" key commitdd2aedacafAuthor: Lincoln Stein <lincoln.stein@gmail.com> Date: Wed Sep 7 13:23:53 2022 -0400 report VRAM usage stats during initial model loading (#419) commitf6284777e6Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Tue Sep 6 17:12:39 2022 -0400 Squashed commit of the following: commit 7d1344282d942a33dcecda4d5144fc154ec82915 Merge:caf4ea3ebeb556Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Mon Sep 5 10:07:27 2022 -0400 Merge branch 'development' of github.com:WebDev9000/stable-diffusion into WebDev9000-development commitebeb556af9Author: Web Dev 9000 <rirath@gmail.com> Date: Sun Sep 4 18:05:15 2022 -0700 Fixed unintentionally removed lines commitff2c4b9a1bAuthor: Web Dev 9000 <rirath@gmail.com> Date: Sun Sep 4 17:50:13 2022 -0700 Add ability to recreate variations via image click commitc012929cdaAuthor: Web Dev 9000 <rirath@gmail.com> Date: Sun Sep 4 14:35:33 2022 -0700 Add files via upload commit02a6018992Author: Web Dev 9000 <rirath@gmail.com> Date: Sun Sep 4 14:35:07 2022 -0700 Add files via upload commiteef788981cAuthor: Olivier Louvignes <olivier@mg-crea.com> Date: Tue Sep 6 12:41:08 2022 +0200 feat(txt2img): allow from_file to work with len(lines) < batch_size (#349) commit720e5cd651Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Mon Sep 5 20:40:10 2022 -0400 Refactoring simplet2i (#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 #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 #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 <bakkot@gmail.com> * 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 <bakkot@gmail.com> commit1ad2a8e567Author: thealanle <35761977+thealanle@users.noreply.github.com> Date: Mon Sep 5 17:35:04 2022 -0700 Fix --outdir function for web (#373) * Fix --outdir function for web * Removed unnecessary hardcoded path commit52d8bb2836Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Mon Sep 5 10:31:59 2022 -0400 Squashed commit of the following: commit 0cd48e932f1326e000c46f4140f98697eb9bdc79 Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Mon Sep 5 10:27:43 2022 -0400 resolve conflicts with development commitd7bc8c12e0Author: Scott McMillin <scott@scottmcmillin.com> Date: Sun Sep 4 18:52:09 2022 -0500 Add title attribute back to img tag commit5397c89184Author: Scott McMillin <scott@scottmcmillin.com> Date: Sun Sep 4 13:49:46 2022 -0500 Remove temp code commit1da080b509Author: Scott McMillin <scott@scottmcmillin.com> 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 commitcaf4ea3d89Author: Adam Rice <adam@askadam.io> Date: Mon Sep 5 10:05:39 2022 -0400 Add a 'Remove Image' button to clear the file upload field (#382) * added "remove image" button * styled a new "remove image" button * Update index.js commit95c088b303Author: Kevin Gibbons <bakkot@gmail.com> Date: Sun Sep 4 19:04:14 2022 -0700 Revert "Add CORS headers to dream server to ease integration with third-party web interfaces" (#371) This reverts commit91e826e5f4. commita20113d5a3Author: Kevin Gibbons <bakkot@gmail.com> Date: Sun Sep 4 18:59:12 2022 -0700 put no_grad decorator on make_image closures (#375) commit0f93dadd6aAuthor: Lincoln Stein <lincoln.stein@gmail.com> Date: Sun Sep 4 21:39:15 2022 -0400 fix several dangling references to --gfpgan option, which no longer exists commitf4004f660eAuthor: tildebyte <337875+tildebyte@users.noreply.github.com> Date: Sun Sep 4 19:43:04 2022 -0400 TOIL(requirements): Split requirements to per-platform (#355) * toil(reqs): split requirements to per-platform Signed-off-by: Ben Alkov <ben.alkov@gmail.com> * toil(reqs): fix for Win and Lin... ...allow pip to resolve latest torch, numpy Signed-off-by: Ben Alkov <ben.alkov@gmail.com> * toil(install): update reqs in Win install notebook Signed-off-by: Ben Alkov <ben.alkov@gmail.com> Signed-off-by: Ben Alkov <ben.alkov@gmail.com> commit4406fd138dMerge:5116c81fd7a72eAuthor: Lincoln Stein <lincoln.stein@gmail.com> Date: Sun Sep 4 08:23:53 2022 -0400 Merge branch 'SebastianAigner-main' into development Add support for full CORS headers for dream server. commitfd7a72e147Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Sun Sep 4 08:23:11 2022 -0400 remove debugging message commit3a2be621f3Merge:91e826e5116c81Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Sun Sep 4 08:15:51 2022 -0400 Merge branch 'development' into main commit5116c8178cAuthor: Justin Wong <1584142+wongjustin99@users.noreply.github.com> Date: Sun Sep 4 07:17:58 2022 -0400 fix save_original flag saving to the same filename (#360) * Update README.md with new Anaconda install steps (#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 <112735219+greentext2@users.noreply.github.com> commit91e826e5f4Author: Sebastian Aigner <SebastianAigner@users.noreply.github.com> Date: Sun Sep 4 10:22:54 2022 +0200 Add CORS headers to dream server to ease integration with third-party web interfaces commit6266d9e8d6Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Sat Sep 3 15:45:20 2022 -0400 remove stray debugging message commit138956e516Author: greentext2 <112735219+greentext2@users.noreply.github.com> Date: Sat Sep 3 13:38:57 2022 -0500 Update README.md with new Anaconda install steps (#347) pip3 version did not work for me and this is the recommended way to install Anaconda now it seems commit60be735e80Author: Cora Johnson-Roberson <cora.johnson.roberson@gmail.com> Date: Sat Sep 3 14:28:34 2022 -0400 Switch to regular pytorch channel and restore Python 3.10 for Macs. (#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: https://github.com/lstein/stable-diffusion/pull/283#issuecomment-1234784885 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. commitd0d95d3a2aAuthor: Lincoln Stein <lincoln.stein@gmail.com> Date: Sat Sep 3 14:10:31 2022 -0400 make initimg appear in web log commitb90a215000Merge:1eee8116270e31Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Sat Sep 3 13:47:15 2022 -0400 Merge branch 'prixt-seamless' into development commit6270e313b8Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Sat Sep 3 13:46:29 2022 -0400 add credit to prixt for seamless circular tiling commita01b7bdc40Merge:1eee8119d88abeAuthor: Lincoln Stein <lincoln.stein@gmail.com> Date: Sat Sep 3 13:43:04 2022 -0400 add web interface for seamless option commit1eee8111b9Merge:64eca42fb857f0Author: Lincoln Stein <lincoln.stein@gmail.com> Date: Sat Sep 3 12:33:39 2022 -0400 Merge branch 'development' of github.com:lstein/stable-diffusion into development commit64eca42610Merge:9130ad721a1f68Author: Lincoln Stein <lincoln.stein@gmail.com> 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. commitfb857f05baAuthor: Lincoln Stein <lincoln.stein@gmail.com> Date: Sat Sep 3 12:07:07 2022 -0400 fix typo in docs commit9d88abe2eaAuthor: prixt <paraxite@naver.com> Date: Sat Sep 3 22:42:16 2022 +0900 fixed typo commita61e49bc97Author: prixt <paraxite@naver.com> Date: Sat Sep 3 22:39:35 2022 +0900 * Removed unnecessary code * Added description about --seamless commit02bee4fdb1Author: prixt <paraxite@naver.com> Date: Sat Sep 3 16:08:03 2022 +0900 added --seamless tag logging to normalize_prompt commitd922b53c26Author: prixt <paraxite@naver.com> Date: Sat Sep 3 15:13:31 2022 +0900 added seamless tiling mode and commands
This commit is contained in:
Lincoln Stein
265
notebooks/Stable-Diffusion-local-Windows.ipynb
Normal file
265
notebooks/Stable-Diffusion-local-Windows.ipynb
Normal file
@@ -0,0 +1,265 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Easy-peasy Windows install"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Note that you will need NVIDIA drivers, Python 3.10, and Git installed\n",
|
||||
"beforehand - simplified\n",
|
||||
"[step-by-step instructions](https://github.com/lstein/stable-diffusion/wiki/Easy-peasy-Windows-install)\n",
|
||||
"are available in the wiki (you'll only need steps 1, 2, & 3 )"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Run each cell in turn. In VSCode, either hit SHIFT-ENTER, or click on the little ▶️ to the left of the cell. In Jupyter/JupyterLab, you **must** hit SHIFT-ENTER"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%pip install pew"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%cmd\n",
|
||||
"git clone https://github.com/lstein/stable-diffusion.git"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%cd stable-diffusion"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%writefile requirements.txt\n",
|
||||
"albumentations==0.4.3\n",
|
||||
"einops==0.3.0\n",
|
||||
"huggingface-hub==0.8.1\n",
|
||||
"imageio-ffmpeg==0.4.2\n",
|
||||
"imageio==2.9.0\n",
|
||||
"kornia==0.6.0\n",
|
||||
"# pip will resolve the version which matches torch\n",
|
||||
"numpy\n",
|
||||
"omegaconf==2.1.1\n",
|
||||
"opencv-python==4.6.0.66\n",
|
||||
"pillow==9.2.0\n",
|
||||
"pip>=22\n",
|
||||
"pudb==2019.2\n",
|
||||
"pytorch-lightning==1.4.2\n",
|
||||
"streamlit==1.12.0\n",
|
||||
"# \"CompVis/taming-transformers\" doesn't work\n",
|
||||
"# ldm\\models\\autoencoder.py\", line 6, in <module>\n",
|
||||
"# from taming.modules.vqvae.quantize import VectorQuantizer2 as VectorQuantizer\n",
|
||||
"# ModuleNotFoundError\n",
|
||||
"taming-transformers-rom1504==0.0.6\n",
|
||||
"test-tube>=0.7.5\n",
|
||||
"torch-fidelity==0.3.0\n",
|
||||
"torchmetrics==0.6.0\n",
|
||||
"transformers==4.19.2\n",
|
||||
"git+https://github.com/openai/CLIP.git@main#egg=clip\n",
|
||||
"git+https://github.com/lstein/k-diffusion.git@master#egg=k-diffusion\n",
|
||||
"# No CUDA in PyPi builds\n",
|
||||
"--extra-index-url https://download.pytorch.org/whl/cu113 --trusted-host https://download.pytorch.org\n",
|
||||
"torch==1.11.0\n",
|
||||
"# Same as numpy - let pip do its thing\n",
|
||||
"torchvision\n",
|
||||
"-e .\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%cmd\n",
|
||||
"pew new --python 3.10 -r requirements.txt --dont-activate ldm"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Switch the notebook kernel to the new 'ldm' environment!\n",
|
||||
"\n",
|
||||
"## VSCode: restart VSCode and come back to this cell\n",
|
||||
"\n",
|
||||
"1. Ctrl+Shift+P\n",
|
||||
"1. Type \"Select Interpreter\" and select \"Jupyter: Select Interpreter to Start Jupyter Server\"\n",
|
||||
"1. VSCode will say that it needs to install packages. Click the \"Install\" button.\n",
|
||||
"1. Once the install is finished, do 1 & 2 again\n",
|
||||
"1. Pick 'ldm'\n",
|
||||
"1. Run the following cell"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%cd stable-diffusion"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"\n",
|
||||
"## Jupyter/JupyterLab\n",
|
||||
"\n",
|
||||
"1. Run the cell below\n",
|
||||
"1. Click on the toolbar where it says \"(ipyknel)\" ↗️. You should get a pop-up asking you to \"Select Kernel\". Pick 'ldm' from the drop-down.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### DO NOT RUN THE FOLLOWING CELL IF YOU ARE USING VSCODE!!"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# DO NOT RUN THIS CELL IF YOU ARE USING VSCODE!!\n",
|
||||
"%%cmd\n",
|
||||
"pew workon ldm\n",
|
||||
"pip3 install ipykernel\n",
|
||||
"python -m ipykernel install --name=ldm"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### When running the next cell, Jupyter/JupyterLab users might get a warning saying \"IProgress not found\". This can be ignored."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%run \"scripts/preload_models.py\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%cmd\n",
|
||||
"mkdir \"models/ldm/stable-diffusion-v1\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Now copy the SD model you downloaded from Hugging Face into the above new directory, and (if necessary) rename it to 'model.ckpt'"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Now go create some magic!\n",
|
||||
"\n",
|
||||
"VSCode\n",
|
||||
"\n",
|
||||
"- The actual input box for the 'dream' prompt will appear at the very top of the VSCode window. Type in your commands and hit 'ENTER'.\n",
|
||||
"- To quit, hit the 'Interrupt' button in the toolbar up there ⬆️ a couple of times, then hit ENTER (you'll probably see a terrifying traceback from Python - just ignore it).\n",
|
||||
"\n",
|
||||
"Jupyter/JupyterLab\n",
|
||||
"\n",
|
||||
"- The input box for the 'dream' prompt will appear below. Type in your commands and hit 'ENTER'.\n",
|
||||
"- To quit, hit the interrupt button (⏹️) in the toolbar up there ⬆️ a couple of times, then hit ENTER (you'll probably see a terrifying traceback from Python - just ignore it)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%run \"scripts/dream.py\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Once this seems to be working well, you can try opening a terminal\n",
|
||||
"\n",
|
||||
"- VSCode: type ('CTRL+`')\n",
|
||||
"- Jupyter/JupyterLab: File|New Terminal\n",
|
||||
"- Or jump out of the notebook entirely, and open Powershell/Command Prompt\n",
|
||||
"\n",
|
||||
"Now:\n",
|
||||
"\n",
|
||||
"1. `cd` to wherever the 'stable-diffusion' directory is\n",
|
||||
"1. Run `pew workon ldm`\n",
|
||||
"1. Run `winpty python scripts\\dream.py`"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.10.6 ('ldm')",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.6"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "a05e4574567b7bc2c98f7f9aa579f9ea5b8739b54844ab610ac85881c4be2659"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
281
notebooks/Stable_Diffusion_AI_Notebook.ipynb
Normal file
281
notebooks/Stable_Diffusion_AI_Notebook.ipynb
Normal file
@@ -0,0 +1,281 @@
|
||||
{
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 0,
|
||||
"metadata": {
|
||||
"colab": {
|
||||
"provenance": [],
|
||||
"collapsed_sections": [],
|
||||
"private_outputs": true
|
||||
},
|
||||
"kernelspec": {
|
||||
"name": "python3",
|
||||
"display_name": "Python 3"
|
||||
},
|
||||
"language_info": {
|
||||
"name": "python"
|
||||
},
|
||||
"accelerator": "GPU",
|
||||
"gpuClass": "standard"
|
||||
},
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"# Stable Diffusion AI Notebook (Release 1.13)\n",
|
||||
"\n",
|
||||
"<img src=\"https://user-images.githubusercontent.com/60411196/186547976-d9de378a-9de8-4201-9c25-c057a9c59bad.jpeg\" alt=\"stable-diffusion-ai\" width=\"170px\"/> <br>\n",
|
||||
"#### Instructions:\n",
|
||||
"1. Execute each cell in order to mount a Dream bot and create images from text. <br>\n",
|
||||
"2. Once cells 1-8 were run correctly you'll be executing a terminal in cell #9, you'll need to enter `python scripts/dream.py` command to run Dream bot.<br> \n",
|
||||
"3. After launching dream bot, you'll see: <br> `Dream > ` in terminal. <br> Insert a command, eg. `Dream > Astronaut floating in a distant galaxy`, or type `-h` for help.\n",
|
||||
"3. After completion you'll see your generated images in path `stable-diffusion/outputs/img-samples/`, you can also show last generated images in cell #10.\n",
|
||||
"4. To quit Dream bot use `q` command. <br> \n",
|
||||
"---\n",
|
||||
"<font color=\"red\">Note:</font> It takes some time to load, but after installing all dependencies you can use the bot all time you want while colab instance is up. <br>\n",
|
||||
"<font color=\"red\">Requirements:</font> For this notebook to work you need to have [Stable-Diffusion-v-1-4](https://huggingface.co/CompVis/stable-diffusion-v-1-4-original) stored in your Google Drive, it will be needed in cell #7\n",
|
||||
"##### For more details visit Github repository: [lstein/stable-diffusion](https://github.com/lstein/stable-diffusion)\n",
|
||||
"---\n"
|
||||
],
|
||||
"metadata": {
|
||||
"id": "ycYWcsEKc6w7"
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"## ◢ Installation"
|
||||
],
|
||||
"metadata": {
|
||||
"id": "dr32VLxlnouf"
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"source": [
|
||||
"#@title 1. Check current GPU assigned\n",
|
||||
"!nvidia-smi -L\n",
|
||||
"!nvidia-smi"
|
||||
],
|
||||
"metadata": {
|
||||
"cellView": "form",
|
||||
"id": "a2Z5Qu_o8VtQ"
|
||||
},
|
||||
"execution_count": null,
|
||||
"outputs": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"cellView": "form",
|
||||
"id": "vbI9ZsQHzjqF"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#@title 2. Download stable-diffusion Repository\n",
|
||||
"from os.path import exists\n",
|
||||
"\n",
|
||||
"if exists(\"/content/stable-diffusion/\")==True:\n",
|
||||
" %cd /content/stable-diffusion/\n",
|
||||
" print(\"Already downloaded repo\")\n",
|
||||
"else:\n",
|
||||
" !git clone --quiet https://github.com/lstein/stable-diffusion.git # Original repo\n",
|
||||
" %cd /content/stable-diffusion/\n",
|
||||
" !git checkout --quiet tags/release-1.13"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"source": [
|
||||
"#@title 3. Install dependencies\n",
|
||||
"import gc\n",
|
||||
"\n",
|
||||
"if exists(\"/content/stable-diffusion/requirements-colab.txt\")==True:\n",
|
||||
" %cd /content/stable-diffusion/\n",
|
||||
" print(\"Already downloaded requirements file\")\n",
|
||||
"else:\n",
|
||||
" !wget https://raw.githubusercontent.com/lstein/stable-diffusion/development/requirements-colab.txt\n",
|
||||
"!pip install colab-xterm\n",
|
||||
"!pip install -r requirements-colab.txt\n",
|
||||
"gc.collect()"
|
||||
],
|
||||
"metadata": {
|
||||
"cellView": "form",
|
||||
"id": "QbXcGXYEFSNB"
|
||||
},
|
||||
"execution_count": null,
|
||||
"outputs": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"source": [
|
||||
"#@title 4. Load small ML models required\n",
|
||||
"%cd /content/stable-diffusion/\n",
|
||||
"!python scripts/preload_models.py\n",
|
||||
"gc.collect()"
|
||||
],
|
||||
"metadata": {
|
||||
"cellView": "form",
|
||||
"id": "ChIDWxLVHGGJ"
|
||||
},
|
||||
"execution_count": null,
|
||||
"outputs": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"source": [
|
||||
"#@title 5. Restart Runtime\n",
|
||||
"exit()"
|
||||
],
|
||||
"metadata": {
|
||||
"cellView": "form",
|
||||
"id": "8rSMhgnAttQa"
|
||||
},
|
||||
"execution_count": null,
|
||||
"outputs": []
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"## ◢ Configuration"
|
||||
],
|
||||
"metadata": {
|
||||
"id": "795x1tMoo8b1"
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"source": [
|
||||
"#@title 6. Mount google Drive\n",
|
||||
"from google.colab import drive\n",
|
||||
"drive.mount('/content/drive')"
|
||||
],
|
||||
"metadata": {
|
||||
"cellView": "form",
|
||||
"id": "YEWPV-sF1RDM"
|
||||
},
|
||||
"execution_count": null,
|
||||
"outputs": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"source": [
|
||||
"#@title 7. Drive Path to model\n",
|
||||
"#@markdown Path should start with /content/drive/path-to-your-file <br>\n",
|
||||
"#@markdown <font color=\"red\">Note:</font> Model should be downloaded from https://huggingface.co <br>\n",
|
||||
"#@markdown Lastest release: [Stable-Diffusion-v-1-4](https://huggingface.co/CompVis/stable-diffusion-v-1-4-original)\n",
|
||||
"from os.path import exists\n",
|
||||
"\n",
|
||||
"model_path = \"\" #@param {type:\"string\"}\n",
|
||||
"if exists(model_path)==True:\n",
|
||||
" print(\"✅ Valid directory\")\n",
|
||||
"else: \n",
|
||||
" print(\"❌ File doesn't exist\")"
|
||||
],
|
||||
"metadata": {
|
||||
"cellView": "form",
|
||||
"id": "zRTJeZ461WGu"
|
||||
},
|
||||
"execution_count": null,
|
||||
"outputs": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"source": [
|
||||
"#@title 8. Symlink to model\n",
|
||||
"\n",
|
||||
"from os.path import exists\n",
|
||||
"import os \n",
|
||||
"\n",
|
||||
"# Folder creation if it doesn't exist\n",
|
||||
"if exists(\"/content/stable-diffusion/models/ldm/stable-diffusion-v1\")==True:\n",
|
||||
" print(\"❗ Dir stable-diffusion-v1 already exists\")\n",
|
||||
"else:\n",
|
||||
" %mkdir /content/stable-diffusion/models/ldm/stable-diffusion-v1\n",
|
||||
" print(\"✅ Dir stable-diffusion-v1 created\")\n",
|
||||
"\n",
|
||||
"# Symbolic link if it doesn't exist\n",
|
||||
"if exists(\"/content/stable-diffusion/models/ldm/stable-diffusion-v1/model.ckpt\")==True:\n",
|
||||
" print(\"❗ Symlink already created\")\n",
|
||||
"else: \n",
|
||||
" src = model_path\n",
|
||||
" dst = '/content/stable-diffusion/models/ldm/stable-diffusion-v1/model.ckpt'\n",
|
||||
" os.symlink(src, dst) \n",
|
||||
" print(\"✅ Symbolic link created successfully\")"
|
||||
],
|
||||
"metadata": {
|
||||
"id": "UY-NNz4I8_aG",
|
||||
"cellView": "form"
|
||||
},
|
||||
"execution_count": null,
|
||||
"outputs": []
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"## ◢ Execution"
|
||||
],
|
||||
"metadata": {
|
||||
"id": "Mc28N0_NrCQH"
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"source": [
|
||||
"#@title 9. Run Terminal and Execute Dream bot\n",
|
||||
"#@markdown <font color=\"blue\">Steps:</font> <br>\n",
|
||||
"#@markdown 1. Execute command `python scripts/dream.py` to run dream bot.<br>\n",
|
||||
"#@markdown 2. After initialized you'll see `Dream>` line.<br>\n",
|
||||
"#@markdown 3. Example text: `Astronaut floating in a distant galaxy` <br>\n",
|
||||
"#@markdown 4. To quit Dream bot use: `q` command.<br>\n",
|
||||
"\n",
|
||||
"import gc\n",
|
||||
"%cd /content/stable-diffusion/\n",
|
||||
"%load_ext colabxterm\n",
|
||||
"%xterm\n",
|
||||
"gc.collect()"
|
||||
],
|
||||
"metadata": {
|
||||
"id": "ir4hCrMIuUpl",
|
||||
"cellView": "form"
|
||||
},
|
||||
"execution_count": null,
|
||||
"outputs": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"source": [
|
||||
"#@title 10. Show the last 15 generated images\n",
|
||||
"import gc\n",
|
||||
"import glob\n",
|
||||
"import matplotlib.pyplot as plt\n",
|
||||
"import matplotlib.image as mpimg\n",
|
||||
"%matplotlib inline\n",
|
||||
"\n",
|
||||
"images = []\n",
|
||||
"for img_path in sorted(glob.glob('/content/stable-diffusion/outputs/img-samples/*.png'), reverse=True):\n",
|
||||
" images.append(mpimg.imread(img_path))\n",
|
||||
"\n",
|
||||
"images = images[:15] \n",
|
||||
"\n",
|
||||
"plt.figure(figsize=(20,10))\n",
|
||||
"\n",
|
||||
"columns = 5\n",
|
||||
"for i, image in enumerate(images):\n",
|
||||
" ax = plt.subplot(len(images) / columns + 1, columns, i + 1)\n",
|
||||
" ax.axes.xaxis.set_visible(False)\n",
|
||||
" ax.axes.yaxis.set_visible(False)\n",
|
||||
" ax.axis('off')\n",
|
||||
" plt.imshow(image)\n",
|
||||
" gc.collect()\n",
|
||||
"\n"
|
||||
],
|
||||
"metadata": {
|
||||
"cellView": "form",
|
||||
"id": "qnLohSHmKoGk"
|
||||
},
|
||||
"execution_count": null,
|
||||
"outputs": []
|
||||
}
|
||||
]
|
||||
}
|
||||
271
notebooks/notebook_helpers.py
Normal file
271
notebooks/notebook_helpers.py
Normal file
@@ -0,0 +1,271 @@
|
||||
from torchvision.datasets.utils import download_url
|
||||
from ldm.util import instantiate_from_config
|
||||
import torch
|
||||
import os
|
||||
# todo ?
|
||||
from google.colab import files
|
||||
from IPython.display import Image as ipyimg
|
||||
import ipywidgets as widgets
|
||||
from PIL import Image
|
||||
from numpy import asarray
|
||||
from einops import rearrange, repeat
|
||||
import torch, torchvision
|
||||
from ldm.models.diffusion.ddim import DDIMSampler
|
||||
from ldm.util import ismap
|
||||
import time
|
||||
from omegaconf import OmegaConf
|
||||
from ldm.dream.devices import choose_torch_device
|
||||
|
||||
def download_models(mode):
|
||||
|
||||
if mode == "superresolution":
|
||||
# this is the small bsr light model
|
||||
url_conf = 'https://heibox.uni-heidelberg.de/f/31a76b13ea27482981b4/?dl=1'
|
||||
url_ckpt = 'https://heibox.uni-heidelberg.de/f/578df07c8fc04ffbadf3/?dl=1'
|
||||
|
||||
path_conf = 'logs/diffusion/superresolution_bsr/configs/project.yaml'
|
||||
path_ckpt = 'logs/diffusion/superresolution_bsr/checkpoints/last.ckpt'
|
||||
|
||||
download_url(url_conf, path_conf)
|
||||
download_url(url_ckpt, path_ckpt)
|
||||
|
||||
path_conf = path_conf + '/?dl=1' # fix it
|
||||
path_ckpt = path_ckpt + '/?dl=1' # fix it
|
||||
return path_conf, path_ckpt
|
||||
|
||||
else:
|
||||
raise NotImplementedError
|
||||
|
||||
|
||||
def load_model_from_config(config, ckpt):
|
||||
print(f"Loading model from {ckpt}")
|
||||
pl_sd = torch.load(ckpt, map_location="cpu")
|
||||
global_step = pl_sd["global_step"]
|
||||
sd = pl_sd["state_dict"]
|
||||
model = instantiate_from_config(config.model)
|
||||
m, u = model.load_state_dict(sd, strict=False)
|
||||
model.cuda()
|
||||
model.eval()
|
||||
return {"model": model}, global_step
|
||||
|
||||
|
||||
def get_model(mode):
|
||||
path_conf, path_ckpt = download_models(mode)
|
||||
config = OmegaConf.load(path_conf)
|
||||
model, step = load_model_from_config(config, path_ckpt)
|
||||
return model
|
||||
|
||||
|
||||
def get_custom_cond(mode):
|
||||
dest = "data/example_conditioning"
|
||||
|
||||
if mode == "superresolution":
|
||||
uploaded_img = files.upload()
|
||||
filename = next(iter(uploaded_img))
|
||||
name, filetype = filename.split(".") # todo assumes just one dot in name !
|
||||
os.rename(f"{filename}", f"{dest}/{mode}/custom_{name}.{filetype}")
|
||||
|
||||
elif mode == "text_conditional":
|
||||
w = widgets.Text(value='A cake with cream!', disabled=True)
|
||||
display(w)
|
||||
|
||||
with open(f"{dest}/{mode}/custom_{w.value[:20]}.txt", 'w') as f:
|
||||
f.write(w.value)
|
||||
|
||||
elif mode == "class_conditional":
|
||||
w = widgets.IntSlider(min=0, max=1000)
|
||||
display(w)
|
||||
with open(f"{dest}/{mode}/custom.txt", 'w') as f:
|
||||
f.write(w.value)
|
||||
|
||||
else:
|
||||
raise NotImplementedError(f"cond not implemented for mode{mode}")
|
||||
|
||||
|
||||
def get_cond_options(mode):
|
||||
path = "data/example_conditioning"
|
||||
path = os.path.join(path, mode)
|
||||
onlyfiles = [f for f in sorted(os.listdir(path))]
|
||||
return path, onlyfiles
|
||||
|
||||
|
||||
def select_cond_path(mode):
|
||||
path = "data/example_conditioning" # todo
|
||||
path = os.path.join(path, mode)
|
||||
onlyfiles = [f for f in sorted(os.listdir(path))]
|
||||
|
||||
selected = widgets.RadioButtons(
|
||||
options=onlyfiles,
|
||||
description='Select conditioning:',
|
||||
disabled=False
|
||||
)
|
||||
display(selected)
|
||||
selected_path = os.path.join(path, selected.value)
|
||||
return selected_path
|
||||
|
||||
|
||||
def get_cond(mode, selected_path):
|
||||
example = dict()
|
||||
if mode == "superresolution":
|
||||
up_f = 4
|
||||
visualize_cond_img(selected_path)
|
||||
|
||||
c = Image.open(selected_path)
|
||||
c = torch.unsqueeze(torchvision.transforms.ToTensor()(c), 0)
|
||||
c_up = torchvision.transforms.functional.resize(c, size=[up_f * c.shape[2], up_f * c.shape[3]], antialias=True)
|
||||
c_up = rearrange(c_up, '1 c h w -> 1 h w c')
|
||||
c = rearrange(c, '1 c h w -> 1 h w c')
|
||||
c = 2. * c - 1.
|
||||
|
||||
device = choose_torch_device()
|
||||
c = c.to(device)
|
||||
example["LR_image"] = c
|
||||
example["image"] = c_up
|
||||
|
||||
return example
|
||||
|
||||
|
||||
def visualize_cond_img(path):
|
||||
display(ipyimg(filename=path))
|
||||
|
||||
|
||||
def run(model, selected_path, task, custom_steps, resize_enabled=False, classifier_ckpt=None, global_step=None):
|
||||
|
||||
example = get_cond(task, selected_path)
|
||||
|
||||
save_intermediate_vid = False
|
||||
n_runs = 1
|
||||
masked = False
|
||||
guider = None
|
||||
ckwargs = None
|
||||
mode = 'ddim'
|
||||
ddim_use_x0_pred = False
|
||||
temperature = 1.
|
||||
eta = 1.
|
||||
make_progrow = True
|
||||
custom_shape = None
|
||||
|
||||
height, width = example["image"].shape[1:3]
|
||||
split_input = height >= 128 and width >= 128
|
||||
|
||||
if split_input:
|
||||
ks = 128
|
||||
stride = 64
|
||||
vqf = 4 #
|
||||
model.split_input_params = {"ks": (ks, ks), "stride": (stride, stride),
|
||||
"vqf": vqf,
|
||||
"patch_distributed_vq": True,
|
||||
"tie_braker": False,
|
||||
"clip_max_weight": 0.5,
|
||||
"clip_min_weight": 0.01,
|
||||
"clip_max_tie_weight": 0.5,
|
||||
"clip_min_tie_weight": 0.01}
|
||||
else:
|
||||
if hasattr(model, "split_input_params"):
|
||||
delattr(model, "split_input_params")
|
||||
|
||||
invert_mask = False
|
||||
|
||||
x_T = None
|
||||
for n in range(n_runs):
|
||||
if custom_shape is not None:
|
||||
x_T = torch.randn(1, custom_shape[1], custom_shape[2], custom_shape[3]).to(model.device)
|
||||
x_T = repeat(x_T, '1 c h w -> b c h w', b=custom_shape[0])
|
||||
|
||||
logs = make_convolutional_sample(example, model,
|
||||
mode=mode, custom_steps=custom_steps,
|
||||
eta=eta, swap_mode=False , masked=masked,
|
||||
invert_mask=invert_mask, quantize_x0=False,
|
||||
custom_schedule=None, decode_interval=10,
|
||||
resize_enabled=resize_enabled, custom_shape=custom_shape,
|
||||
temperature=temperature, noise_dropout=0.,
|
||||
corrector=guider, corrector_kwargs=ckwargs, x_T=x_T, save_intermediate_vid=save_intermediate_vid,
|
||||
make_progrow=make_progrow,ddim_use_x0_pred=ddim_use_x0_pred
|
||||
)
|
||||
return logs
|
||||
|
||||
|
||||
@torch.no_grad()
|
||||
def convsample_ddim(model, cond, steps, shape, eta=1.0, callback=None, normals_sequence=None,
|
||||
mask=None, x0=None, quantize_x0=False, img_callback=None,
|
||||
temperature=1., noise_dropout=0., score_corrector=None,
|
||||
corrector_kwargs=None, x_T=None, log_every_t=None
|
||||
):
|
||||
|
||||
ddim = DDIMSampler(model)
|
||||
bs = shape[0] # dont know where this comes from but wayne
|
||||
shape = shape[1:] # cut batch dim
|
||||
print(f"Sampling with eta = {eta}; steps: {steps}")
|
||||
samples, intermediates = ddim.sample(steps, batch_size=bs, shape=shape, conditioning=cond, callback=callback,
|
||||
normals_sequence=normals_sequence, quantize_x0=quantize_x0, eta=eta,
|
||||
mask=mask, x0=x0, temperature=temperature, verbose=False,
|
||||
score_corrector=score_corrector,
|
||||
corrector_kwargs=corrector_kwargs, x_T=x_T)
|
||||
|
||||
return samples, intermediates
|
||||
|
||||
|
||||
@torch.no_grad()
|
||||
def make_convolutional_sample(batch, model, mode="vanilla", custom_steps=None, eta=1.0, swap_mode=False, masked=False,
|
||||
invert_mask=True, quantize_x0=False, custom_schedule=None, decode_interval=1000,
|
||||
resize_enabled=False, custom_shape=None, temperature=1., noise_dropout=0., corrector=None,
|
||||
corrector_kwargs=None, x_T=None, save_intermediate_vid=False, make_progrow=True,ddim_use_x0_pred=False):
|
||||
log = dict()
|
||||
|
||||
z, c, x, xrec, xc = model.get_input(batch, model.first_stage_key,
|
||||
return_first_stage_outputs=True,
|
||||
force_c_encode=not (hasattr(model, 'split_input_params')
|
||||
and model.cond_stage_key == 'coordinates_bbox'),
|
||||
return_original_cond=True)
|
||||
|
||||
log_every_t = 1 if save_intermediate_vid else None
|
||||
|
||||
if custom_shape is not None:
|
||||
z = torch.randn(custom_shape)
|
||||
print(f"Generating {custom_shape[0]} samples of shape {custom_shape[1:]}")
|
||||
|
||||
z0 = None
|
||||
|
||||
log["input"] = x
|
||||
log["reconstruction"] = xrec
|
||||
|
||||
if ismap(xc):
|
||||
log["original_conditioning"] = model.to_rgb(xc)
|
||||
if hasattr(model, 'cond_stage_key'):
|
||||
log[model.cond_stage_key] = model.to_rgb(xc)
|
||||
|
||||
else:
|
||||
log["original_conditioning"] = xc if xc is not None else torch.zeros_like(x)
|
||||
if model.cond_stage_model:
|
||||
log[model.cond_stage_key] = xc if xc is not None else torch.zeros_like(x)
|
||||
if model.cond_stage_key =='class_label':
|
||||
log[model.cond_stage_key] = xc[model.cond_stage_key]
|
||||
|
||||
with model.ema_scope("Plotting"):
|
||||
t0 = time.time()
|
||||
img_cb = None
|
||||
|
||||
sample, intermediates = convsample_ddim(model, c, steps=custom_steps, shape=z.shape,
|
||||
eta=eta,
|
||||
quantize_x0=quantize_x0, img_callback=img_cb, mask=None, x0=z0,
|
||||
temperature=temperature, noise_dropout=noise_dropout,
|
||||
score_corrector=corrector, corrector_kwargs=corrector_kwargs,
|
||||
x_T=x_T, log_every_t=log_every_t)
|
||||
t1 = time.time()
|
||||
|
||||
if ddim_use_x0_pred:
|
||||
sample = intermediates['pred_x0'][-1]
|
||||
|
||||
x_sample = model.decode_first_stage(sample)
|
||||
|
||||
try:
|
||||
x_sample_noquant = model.decode_first_stage(sample, force_not_quantize=True)
|
||||
log["sample_noquant"] = x_sample_noquant
|
||||
log["sample_diff"] = torch.abs(x_sample_noquant - x_sample)
|
||||
except:
|
||||
pass
|
||||
|
||||
log["sample"] = x_sample
|
||||
log["time"] = t1 - t0
|
||||
|
||||
return log
|
||||
Reference in New Issue
Block a user