d834e8b5b3
test: run non-gpu tests on github
5 months ago
df00109074
refactor: space formatting
5 months ago
d39486af54
fix: updates test marking to use nodeid instead of name
5 months ago
0c01cd690f
fix: sets correct default value for composition strength. ( #422 )
...
also corrects positional argument error by requiring _imagine_cmd to take key word arguments.
5 months ago
0c03612d44
feature: large images now stay well-composed thanks to tile controlnet
6 months ago
2372a71e6c
fix: adds tile/detail controlnet back in.
6 months ago
f88b5c1b2b
fix: word images still work without specified size ( #421 )
6 months ago
7880ee1389
feature: update midas (depth maps)
6 months ago
bf14ee6ee6
feature: add christmas-scene phrase list
...
Also add script that uses chatgpt to generate phrase-lists
6 months ago
c6ac5f553a
refactor: separate controlnet image preprocessing
6 months ago
9a0e0cd1a7
feature: better depth maps
6 months ago
2eee741b20
Merge pull request #418 from brycedrennan/fix_test_set_spu_full
...
fix: configures test_set_gpu_full to run on a m1 mac.
6 months ago
c99a169986
fix: configures test_set_gpu_full to run on a m1 mac.
6 months ago
2144f26fa7
feature: add ability to dynamically make word images ( #417 )
6 months ago
3bd3dfdeaf
feature: adds --composition-strength parameter to cli ( #416 )
6 months ago
41a9d7007b
test: adds tests for stablestudio ( #415 )
6 months ago
e1e6f8037c
refactor: removes unused code and configurations ( #405 )
...
Co-authored-by: jaydrennan
6 months ago
6d39d791b1
refactor: move safety to utils
6 months ago
168a843f29
refactor: move colorize to api
6 months ago
96f4268d44
refactor: move video_sample to api
6 months ago
e72e8992ab
refactor: create api module
6 months ago
ad561e8833
refactor: move model_manager to utils
6 months ago
d478771cc0
refactor: move a bunch of stuff to utils
6 months ago
987af23abe
refactor: move train.py
6 months ago
0c456cd52a
refactor: remove lr_scheduler.py
6 months ago
01e32ff3f6
refactor: move bin files
6 months ago
316114e660
docs: add docstrings
...
Wrote an openai script and custom prompt to generate them.
6 months ago
e7b6fc40fa
fix: adds default line ending for csv writing.
...
the csv library defaults to using CRLF line endings if not specified.
6 months ago
3f3e080d39
feature: adds ability to use qrcode
...
feature: adds controlnet qrcode image generation.
feature: adds control net for qrcode image generation.
6 months ago
62de446a92
ci: add mypy github action
6 months ago
012cc648d3
style: fix all the mypy typing issues
...
...or ignore them.
6 months ago
5a636e45c5
feature: skip composition at sizes slightly larger than model is expecting
6 months ago
203747b14f
refactor: simplify model_weights/architecture
6 months ago
37ecd1e5e0
fix: videogen. track gpu tests
6 months ago
eae4f20ae2
ci: add type checker
...
fix some typehint issues
6 months ago
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.
6 months ago
c299cfffd9
fix: cache the controlnet models
6 months ago
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'))
```
6 months ago
2bd6cb264b
feature: large refactor
...
- add type hints
- size parameter
- ControlNetInput => ControlInput
- simplify imagineresult
6 months ago
db85f0898a
feature: remove training feature
6 months ago
ef0f44646e
feature: adds --control-strength as parameter for cli
6 months ago
24f4af3482
feature: better torch installation experience
6 months ago
71d4992dca
feature: added `--size` parameter to allow using named sizes
6 months ago
14ecf93c6a
feature: add sliced self-attention for future use with video generation
6 months ago
1136fdb939
version: 14.0.0b5
6 months ago
6fcf0da331
test: try local runner
6 months ago
0fe3733933
fix: memory management issue
...
the dtype being used as a cache key wasn't consistent. this caused the model to be loaded twice
6 months ago
82c30024c9
feature: DDIM now default sampler
...
better output quality
6 months ago
ba57393022
feature: patch refiners ScaledDotProductAttention for sliced attention
6 months ago
1b15d6dcd4
feature: sliced image encoding for SD1Autoencoder
6 months ago
Bryce
jaydrennan
jaydrennan