Archives/imaginAIry
2
0
Fork 0
mirror of https://github.com/brycedrennan/imaginAIry synced 2024-11-09 13:10:27 +00:00
Code Issues Packages Projects Releases Wiki Activity
182 Commits 10 Branches 104 Tags 322 MiB
e0af5d0089
Commit Graph

38 Commits

Author SHA1 Message Date
Bryce
015088507f feature/refactor/fix: better defaults. correct version in metadata 
- feature: use different default steps and image sizes depending on sampler and model selceted
- fix: #110 use proper version in image metadata
- refactor: samplers all have their own class that inherits from ImageSampler
 2022-11-26 16:18:08 -08:00
Maxime Mouchet
40ab571fc1 cli: show defaults and cleanup help text 2022-11-25 07:46:40 -08:00
Bryce
584e0d9df0 feature: change default sampler to k_dpmpp_2m, which is more than twice as fast 2022-11-12 20:56:38 -08:00
Bryce
94c0aeab12 feature: switch between models without restarting python instance 2022-10-23 22:55:28 -07:00
Bryce
4ba1965db8 feature: k-diff sampler img2img and masking 2022-10-14 03:23:16 -07:00
Bryce
299687645b refactor: remove unused parameter 2022-10-11 01:06:24 -05:00
Bryce
df3c752eb8 refactor: consolidate logging utils 2022-10-10 22:32:39 -05:00
Bryce Drennan
31c2160e21
feature: prompt expansion (#51) 
You can use `{}` to randomly pull values from lists.  A list of values separated by `|` and enclosed in `{ }` will be randomly drawn from in a non-repeating fashion. Values that are surrounded by `_ _` will pull from a phrase list of the same name.   Folders containing .txt phraselist files may be specified via
`--prompt_library_path`. The option may be specified multiple times.  Built-in categories:

      3d-term, adj-architecture, adj-beauty, adj-detailed, adj-emotion, adj-general, adj-horror, animal, art-movement,
      art-site, artist, artist-botanical, artist-surreal, aspect-ratio, bird, body-of-water, body-pose, camera-brand,
      camera-model, color, cosmic-galaxy, cosmic-nebula, cosmic-star, cosmic-term, dinosaur, eyecolor, f-stop,
      fantasy-creature, fantasy-setting, fish, flower, focal-length, food, fruit, games, gen-modifier, hair, hd,
      iso-stop, landscape-type, national-park, nationality, neg-weight, noun-beauty, noun-fantasy, noun-general,
      noun-horror, occupation, photo-term, pop-culture, pop-location, punk-style, quantity, rpg-item, scenario-desc,
      skin-color, spaceship, style, tree-species, trippy, world-heritage-site

   Examples:

   `imagine "a {red|black} dog" -r 2 --seed 0` will generate both "a red dog" and "a black dog"

   `imagine "a {_color_} dog" -r 4 --seed 0` will generate four, different colored dogs. The colors will eb pulled from an included
   phraselist of colors.

   `imagine "a {_spaceship_|_fruit_|hot air balloon}. low-poly" -r 4 --seed 0` will generate images of spaceships or fruits or a hot air balloon

   Credit to [noodle-soup-prompts](https://github.com/WASasquatch/noodle-soup-prompts/) where most, but not all, of the wordlists originate.
 2022-10-08 18:34:35 -07:00
Bryce
340a90bacd feature: allow loading custom model weights at command line 
Addresses #40
 2022-10-06 00:30:50 -05:00
Bryce
48117bbcb1 feature: face-fidelity is now configurable 
remove face-fixing from upscaled version
 2022-10-03 16:33:17 -07:00
Bryce
95a8fa31a9 fix: inpainting producing blurry images 
while the previous version did produce much better blending it also makes images that lack detail for some reason.

tests: Added more tests to help catch this sort of thing earlies

fix: found that median blur is really slow, so I made sure we only do it on downsampled masks.  Was taking like 3 minutes to run on the large pearl girl picture on M1

- docs: update examples
 2022-09-27 17:19:25 -07:00
Bryce
d563e0c7fb refactor: image version management 
- mask_modify_original is now a prompt attribute
 2022-09-25 22:50:16 -07:00
Bryce
2f959c7394 docs: complete sentence 2022-09-24 23:31:03 -07:00
Bryce
d832f15297 fix: masking now works properly at strengths 0 and 1 2022-09-24 23:31:03 -07:00
Bryce
b69072d382 fix: various bugfixes 2022-09-24 23:31:03 -07:00
Bryce
b69b4c770e feature: interactive prompt 
- add quiet flag
- add mask-modify-original flag
 2022-09-24 23:31:03 -07:00
Bryce
38c7f88950 feature: boolean logic masks 
Specify advanced text based masks using boolean logic and strength modifiers. Mask descriptions must be lowercase. Keywords uppercase.
Valid symbols: `AND`, `OR`, `NOT`, `()`, and mask strength modifier `{*1.5}` where `+` can be any of `+ - * /`. Single-character boolean
operators also work.  When writing strength modifies know that pixel values are between 0 and 1.

 - feature: apply mask edits to original files
 - feature: auto-rotate images if exif data specifies to do so
 - fix: accept mask images in command line
 2022-09-24 00:02:31 -07:00
Bryce
09bc1c70e6 fix: try to address #13 BFloat16 issue 
Seems to be caused by incompatible types in group_norm when we use autocast.

Patch group_norm to cast the weights to the same type as the inputs

From what I can understand all the other repos just switch to full precision instead
of addressing this.  I think this would make things slower but I'm not sure. So maybe
the patching solution I'm doing is better?

https://github.com/pytorch/pytorch/pull/81852
 2022-09-21 22:03:12 -07:00
Bryce
ff7fc0dab7 feature: tile mode can now be specified per-prompt 2022-09-20 22:57:03 -07:00
Bryce
a46424c673 feature: img2img now supported with PLMS (instead of just DDIM) 
Kinda hacky copy/pasting from ddim.  Need to cleanup
 2022-09-20 08:42:00 -07:00
Bryce
4705d182d5 feature: generate captions for images 
- add wip functionality for negative masks
- ci: add code linter that removes unused imports
- add instructions to install rust on osx
 2022-09-19 21:19:22 -07:00
Bryce
f040e3bffe feature: allow multiple additive targets for text masking targets 2022-09-18 15:24:31 -07:00
Bryce
930295d840 feature: txt2mask - automated text replacement 
from https://github.com/timojl/clipseg
 2022-09-18 06:07:47 -07:00
Bryce
19d0b563ac style: lint fixes. remove unused code 2022-09-16 09:24:24 -07:00
Bryce
c7a822d701 feature: urls as init images 
- --init-image accepts urls
- cleanup command line code
 2022-09-15 23:06:59 -07:00
Bryce
23f0e2be12 fix: select ddim for img2img 2022-09-15 07:55:09 -07:00
Bryce
bb665b9eb6 fix: make k-diffusion samplers deterministic 
- add test for hashes on mps.  images look same on CUDA but are slightly different.
 2022-09-14 09:37:45 -07:00
Bryce
b4a3b8c2b3 feature: k-diffusion samplers 
- improved image logging functionality. can just stick log_latent wherever you want
- improved some variable naming
- moved all the samplers together
- vendored k-diffusion library
 2022-09-14 00:40:25 -07:00
Bryce
541ecb9701 feature: face enhancement and upscaling!! 2022-09-13 00:27:53 -07:00
Bryce
6ac3d40009 docs: update readme. add docs to package 
Clean up logging some more
 2022-09-11 21:36:14 -07:00
Bryce
84a73cb5a2 feature: (wip) better image to image 
I tried it with the DDIM sampler and it didn't work.

Probably need to use the k-diffusion sampler with it
from a846393251/find_noise.py

needs https://github.com/crowsonkb/k-diffusion
 2022-09-11 18:00:40 -07:00
Bryce
438c2868ad refactor: run import sorter 2022-09-11 13:58:14 -07:00
Bryce
3bdf2dc3ec feature: tile mode 
from https://github.com/replicate/cog-stable-diffusion/compare/main...TomMoore515:material_stable_diffusion:main
 2022-09-11 13:56:41 -07:00
Bryce
f1b1e1c1c8 feature: add nsfw image filter 2022-09-11 00:35:57 -07:00
Bryce
7a33ee2480 feature: cleaned up logging 
- cleans up all the logging. hide most of it
 - create better readme. show example images
 - save metadata into image
 2022-09-10 23:27:22 -07:00
Bryce
6d1d0622eb feature: Mac M1 Support out of box 
- auto-downloads checkpoints
- fixes bug in torch
- autoset environment variable
 2022-09-10 00:32:52 -07:00
Bryce
66c640ce7b feature: add ImageResult. step output option 
remove verbose args
 2022-09-09 22:14:04 -07:00
Bryce
47c6bcee59 refactor: move commands to entrypoints 2022-09-08 22:22:55 -07:00