jaydrennan
|
80ff006604
|
fix: updates weights_url's for controlnet
|
10 months ago |
jaydrennan
|
e91a041a78
|
refactor: removes unused model configs
|
10 months ago |
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
|
10 months ago |
Bryce
|
6cd519cdb2
|
refactor: move code to avoid conflicts with "http" namespace
|
12 months ago |
Bryce
|
558d3388e5
|
style: speed up linting and autoformatting. fix lints
|
1 year ago |
Bryce
|
8243ed616d
|
fix: pydantic models for http server working now. Fixes #380
|
1 year ago |
Bryce
|
7c2004bfcc
|
feature/fix: migrate to pydantic 2.3
- test: add schema tests/fuzzer and fixes
- fix default prompt. add tests
- fix outpaint and controlnet defaults
- fix init image strength defaults
|
1 year ago |
Bryce
|
8e956f5360
|
feature: add some helper functions
|
1 year ago |
Bryce
|
f243006236
|
fix: allow tile_mode to be set to True or False for backward compatibility
|
1 year ago |
Bryce
|
477d161c91
|
build: better communicate lack of support for Python 3.11
|
1 year ago |
Bryce
|
82d74c6b49
|
feature: switch to pydantic models
- allow prompt re-use by deferring random seed
|
1 year ago |
Bryce
|
3fb0dcd891
|
fix: hide log warning
|
1 year ago |
Bryce
|
c5c90df337
|
feature: fix debug level logging
|
1 year ago |
Bryce
|
8ffb0fac0e
|
fix: add routes to match stablestudio routes
|
1 year ago |
Bryce
|
edafcc5529
|
feature: show full stack trace on server error
|
1 year ago |
Bryce
|
671aa86ad7
|
version: 13.0.0
|
1 year ago |
Bryce
|
7b032c8e9a
|
feature: StableStudio web interface
run `aimg server` and visit http://127.0.0.1:8000/
|
1 year ago |
Bryce
|
8e28a2ed02
|
feature: API support for StableStudio
|
1 year ago |
Bryce
|
e53459a50a
|
build: check for torch version at runtime (fixes #329)
|
1 year ago |
Bryce
|
2a26495653
|
fix: package will not try to install xformers on `aarch64` machines.
While this will allow the dockerfile to build on MacOS M1, [torch will not be able to use the M1 when generating images.](https://github.com/pytorch/pytorch/issues/81224#issuecomment-1499741152)
|
1 year ago |
Bryce
|
14739bc90b
|
feature: api server (alpha)
`aimg run-api-server`
Proof of concept for now
|
1 year ago |
Bryce
|
38ac0b7f54
|
tests: fix tests
|
1 year ago |
Bryce
|
39dffa9166
|
style: lintfix
|
1 year ago |
Bryce
|
dc8f8d5a3d
|
feature: add colorization controlnet. improve `aimg colorize` command
|
1 year ago |
Bryce
|
df25936d6f
|
feature: automatic use of inpainting
feature disabled since controlnet inpainting doesn't work great. Was disabled by setting `inpaint_method="finetune",`
|
1 year ago |
Bryce
|
d32e1060cd
|
feature: multi-controlnet support at the command line
add controlnet option for edit demo
|
1 year ago |
Bryce
|
bcaa000d35
|
fix: model logging
|
1 year ago |
Bryce
|
926692ad03
|
tests: "prime" the controlnets
Trying to get things working on m1. doesn't fix everything
|
1 year ago |
Bryce
|
fb19e34acc
|
fix: allow use of upscaler on mps device
|
1 year ago |
Bryce
|
3b066f8e29
|
fix: don't hide error messages during upscale
|
1 year ago |
Bryce
|
eca97a25a0
|
tests: adjust tests to pass
|
1 year ago |
Bryce
|
4c77fd376b
|
feature: improvements to memory management
not thoroughly tested on low-memory devices
|
1 year ago |
Bryce
|
d5a276584b
|
fix: move normal map code inline
Fixes conda package. Fixes #317
|
1 year ago |
Bryce
|
3258af7e02
|
fix: use correct device for depth images on mps
|
1 year ago |
Bryce
|
17f3541d57
|
version: 12.0.0
|
1 year ago |
Bryce
|
c9fccc1757
|
feature: add openjourney-v4
|
1 year ago |
Bryce
|
db8d3b74ea
|
feature: add "detail" control mode.
Add details to an image. Great for upscaling an image.
|
1 year ago |
Bryce
|
b5356b143f
|
feature: partial add of inpainting controlnet
todo: figure out how to input "mask" for this mode
|
1 year ago |
Bryce
|
9526a85a71
|
feature: add "edit" control mode
Edit images using text instructions with any SD 1.5 based model. Similar to instructPix2Pix.
|
1 year ago |
Bryce
|
476a81a967
|
feature: add "shuffle" control mode
Image is generated from elements of control image. similar to style transfer
|
1 year ago |
Bryce
|
750d4f7ea8
|
docs: cleanup
|
1 year ago |
Bryce
|
832adf27bc
|
feature: update controlnets to 1.1
- smaller filesizes for the controlnet weights
- fix: works with other 1.5 based models
- enables more control modes getting added
|
1 year ago |
Bryce
|
9a82dc5e4c
|
fix: raw control images are now properly loaded. fixes #296
|
1 year ago |
Bryce
|
765e607c2c
|
fix: file numbers start after latest image, even if some previous images were deleted
|
1 year ago |
Luke Pearson
|
94728d978e
|
fix: changed sample to True to generate caption using blip model
|
1 year ago |
Bryce
|
95d3d08d27
|
fix: better input image path handling
throw exception for non-existent images
|
1 year ago |
Bryce
|
37d6642c83
|
fix: fix model downloads that were broken
by [library change in transformers 4.27.0](8f3b4a1d5b )
|
2 years ago |
Bryce
|
eb26d5a7c5
|
feature: add art-scene, desktop-background, interior-style, painting-style phraselists
fix: file globbing works in the interactive shell
feature: make compilation animations simple slide shows
|
2 years ago |
Bryce
|
52044c1073
|
fix: use model appropriate composition size
|
2 years ago |
Bryce
|
3b777b98d8
|
fix: improved large images using composition
|
2 years ago |