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
|
7e62297f73
|
feature: add simple script to print structure of weight files
useful for debugging
|
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
|
6db296aa37
|
tests: faster tests
|
1 year ago |
Adam Menges
|
6f9e9f64a9
|
docs: fix incorrect command in readme (#327)
|
1 year ago |
|
Bryce
|
c082ea523f
|
tests: update tests
- controlnet version changes + graphics card change
|
1 year ago |
|
Bryce
|
a8aa9f703a
|
build: exclude broken versions of timm as dependencies
|
1 year ago |
|
Bryce
|
2a77b9b048
|
docs: add python prompt expansion example
|
1 year ago |
|
Bryce
|
629c1c9ba9
|
docs: add cache clear instructions
|
1 year ago |
|
Bryce
|
bffe1ffde0
|
docs: add python upscaling example
|
1 year ago |
|
Bryce
|
e5d6880bc3
|
version: 12.0.2
|
1 year ago |
|
Bryce
|
d5a276584b
|
fix: move normal map code inline
Fixes conda package. Fixes #317
|
1 year ago |
|
Bryce Drennan
|
726ffe48c9
|
docs: make controlnet sections linkable
|
1 year ago |
|
Bryce
|
23d4810670
|
version: 12.0.1
|
1 year ago |
|
Bryce
|
9ccf55e7c7
|
docs: better "add details" example
|
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 |
|
Bryce
|
4cbd278972
|
version: 11.1.1
|
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
|
3012d28357
|
version: 11.1.0
|
1 year ago |
|
Bryce
|
37d6642c83
|
fix: fix model downloads that were broken
by [library change in transformers 4.27.0](8f3b4a1d5b)
|
1 year 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
|
1 year ago |
|
Bryce
|
de2a72f718
|
version: 11.0.0
|
1 year ago |
|
Bryce
|
52044c1073
|
fix: use model appropriate composition size
|
1 year ago |
|
Bryce
|
3b777b98d8
|
fix: improved large images using composition
|
1 year ago |
|
Bryce
|
a449fbd5e2
|
feature: remove tiling message for upscaler
|
1 year ago |
|
Bryce
|
40da2b0357
|
tests: fix tests
|
1 year ago |
|
Bryce
|
dbc6a249a6
|
fix: k-diff samplers made more stable by skipping second to last step
https://github.com/crowsonkb/k-diffusion/issues/43#issuecomment-1305195666
See discussion here as well: https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/3483
|
1 year ago |
|
Bryce
|
70c58467c0
|
fix: img2img was broken for all samplers except ddim,plms
img2img was broken for all samplers except plms and ddim when init image strength was >~0.25. Been this way for a while. whoops
|
1 year ago |