Archives/imaginAIry
2
0
Fork 0
mirror of https://github.com/brycedrennan/imaginAIry synced 2024-10-31 03:20:40 +00:00
Code Issues Packages Projects Releases Wiki Activity
438 Commits 10 Branches 104 Tags 322 MiB
3f3e080d39
Commit Graph

438 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
jaydrennan
3f3e080d39 feature: adds ability to use qrcode 
feature: adds controlnet qrcode image generation.
feature: adds control net for qrcode image generation.
 2023-12-14 21:12:25 -08:00
Bryce
62de446a92 ci: add mypy github action 2023-12-12 20:54:39 -08:00
Bryce
012cc648d3 style: fix all the mypy typing issues 
...or ignore them.
 2023-12-12 20:54:39 -08:00
Bryce
5a636e45c5 feature: skip composition at sizes slightly larger than model is expecting 2023-12-12 20:54:39 -08:00
Bryce
203747b14f refactor: simplify model_weights/architecture 2023-12-12 20:54:39 -08:00
Bryce
37ecd1e5e0 fix: videogen. track gpu tests 2023-12-12 20:54:39 -08:00
Bryce
eae4f20ae2 ci: add type checker 
fix some typehint issues
 2023-12-12 20:54:39 -08:00
Bryce
e898e3a799 fix: several cli commands, edit demo, negative prompt 
- fix colorize cmd. add test
- fix describe cmd. add test
- fix model-list cmd. add test
- fix stable studio
- hide stack grace for ValueErrors in cli
- set controlnet scale
- fix negative prompt to allow emptystring instead of replacing it with default
- adjust edit-demo parameters
- arg scheduler that works at click level (but disable it). works but not ideal experience.
 2023-12-12 20:54:39 -08:00
Bryce
c299cfffd9 fix: cache the controlnet models 2023-12-12 20:54:39 -08:00
Bryce
9b95e8b0b6 perf: improve cli startup time 
- do not provide automatically imported api functions and objects in `imaginairy` root module
- horrible hack to overcome horrible design choices by easy_install/setuptools

The hack modifies the installed script to remove the __import__ pkg_resources line

If we don't do this then the scripts will be slow to start up because of
pkg_resources.require() which is called by setuptools to ensure the
"correct" version of the package is installed.

before modification example:
```
__requires__ = 'imaginAIry==14.0.0b5'
__import__('pkg_resources').require('imaginAIry==14.0.0b5')
__file__ = '/home/user/projects/imaginairy/imaginairy/bin/aimg'
with open(__file__) as f:
    exec(compile(f.read(), __file__, 'exec'))
```
 2023-12-12 20:54:39 -08:00
Bryce
2bd6cb264b feature: large refactor 
- add type hints
- size parameter
- ControlNetInput => ControlInput
- simplify imagineresult
 2023-12-12 20:54:39 -08:00
Bryce
db85f0898a feature: remove training feature 2023-12-06 22:04:06 -08:00
jaydrennan
ef0f44646e feature: adds --control-strength as parameter for cli 2023-12-05 22:14:19 -08:00
Bryce
24f4af3482 feature: better torch installation experience 2023-12-05 21:46:55 -08:00
Bryce
71d4992dca feature: added --size parameter to allow using named sizes 2023-12-05 21:46:55 -08:00
Bryce
14ecf93c6a feature: add sliced self-attention for future use with video generation 2023-12-05 21:46:55 -08:00
Bryce
1136fdb939 version: 14.0.0b5 2023-12-03 15:48:36 -08:00
Bryce
6fcf0da331 test: try local runner 2023-12-03 09:13:01 -08:00
Bryce
0fe3733933 fix: memory management issue 
the dtype being used as a cache key wasn't consistent. this caused the model to be loaded twice
 2023-12-03 09:13:01 -08:00
Bryce
82c30024c9 feature: DDIM now default sampler 
better output quality
 2023-12-03 09:13:01 -08:00
Bryce
ba57393022 feature: patch refiners ScaledDotProductAttention for sliced attention 2023-12-03 09:13:01 -08:00
Bryce
1b15d6dcd4 feature: sliced image encoding for SD1Autoencoder 2023-12-03 09:13:01 -08:00
Bryce
b61d06651c tests: fix tests 
- disable details mode. needs more work done to support
 2023-12-03 09:13:01 -08:00
jaydrennan
cff17ef6f4
feature: adds text to video generation flag (#404) 
Co-authored-by: jaydrennan
 2023-11-27 18:00:56 -08:00
Bryce
8fec56970e version: 14.0.0b4 2023-11-25 16:25:14 -08:00
Bryce
8267482aad fix: remove padding approach 
- padding didnt make animations better
- some changes to better support CPU generation (not yet working)
- better log output coloring
- better log messages when cuda not found
 2023-11-25 16:18:44 -08:00
Bryce
6e1c44dae7 fix: add missing data files 
fixes #402
 2023-11-25 15:44:44 -08:00
Bryce
b9e245eb7d fix: remove cuda memory tracking 2023-11-24 12:39:49 -08:00
Bryce
3b2265f82d feature: add video progress bar 2023-11-24 12:33:36 -08:00
Bryce
b5a0e65f35 fix: edit mode and some controlnet tests 2023-11-24 09:10:12 -08:00
Bryce
b7fad562d0 feature: improved logging 
- clean up some error messages
- add color
- indent tqdm bar
 2023-11-24 08:27:36 -08:00
Bryce
07b097e001 version: 14.0.0b3 2023-11-23 12:25:35 -08:00
Bryce
a126e1c1d7 feature: better error message when file not found 2023-11-23 12:24:48 -08:00
Bryce
aa91d0a9c9 feature: autoresize and crop videos. 
This means you can just stick any image into the video generator without worrying about the size.

- better generated video filenames
- output h264 video as well
 2023-11-23 10:16:12 -08:00
Bryce
f6c9927d0c version: 14.0.0b2 2023-11-22 20:44:30 -08:00
Bryce
c24ed1f33d feature: videogen improvements 
- better filenames
- allow urls as image inputs
- better memory efficiency
- add timing information
 2023-11-22 20:43:32 -08:00
Bryce
ab75c49b15 docs: smaller animations 2023-11-22 18:33:28 -08:00
Bryce
ed23c7e1ca version: 14.0.0b1 2023-11-22 18:26:50 -08:00
Bryce
1da7043081 docs: update documentation 2023-11-22 18:26:50 -08:00
Bryce
e8fe8d7d6c feature: stable diffusion video (SVD) 2023-11-22 17:20:08 -08:00
jaydrennan
80ff006604 fix: updates weights_url's for controlnet 2023-11-22 17:18:22 -08:00
jaydrennan
e91a041a78 refactor: removes unused model configs 2023-11-22 17:14:44 -08:00
jaydrennan
76df1210f4 refactor: removes outdated info and spelling error 2023-11-22 17:14:44 -08:00
jaydrennan
d6d2f4b9dd refactor: updates README for 14.0.0 
adds notes under currently broken features, removes deprecated features descriptions, and adds 14.0.0 changelog
 2023-11-22 17:14:44 -08:00
Bryce
f97f6a3b4b feature: use refiners library for generation 
BREAKING CHANGE

  - stable diffusion 1.5 + inpainting working
  - self-attention guidance working. improves image generation quality
  - tile-mode working
  - inpainting self-attention guidance working

disable/broken features:
  - sd 1.4, 2.0, 2.1
  - most of the samplers
  - pix2pix edit
  - most of the controlnets
  - memory management
  - python 3.8 support

wip
 2023-11-22 13:22:00 -08:00
Bryce
6cd519cdb2 refactor: move code to avoid conflicts with "http" namespace 2023-10-10 23:03:01 -07:00
Bryce
703fb6e331 ci: faster pip install in github actions 2023-09-29 23:01:50 -07:00
Bryce
2273c9144d ci: smarter model caching in github actions 2023-09-29 23:01:50 -07:00
Bryce
db4f040536 tests: split test suite for faster overall runtime 2023-09-29 23:01:50 -07:00
Bryce
558d3388e5 style: speed up linting and autoformatting. fix lints 2023-09-29 23:01:50 -07:00