2bd6cb264b
feature: large refactor
...
- add type hints
- size parameter
- ControlNetInput => ControlInput
- simplify imagineresult
10 months ago
24f4af3482
feature: better torch installation experience
10 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
10 months ago
cff17ef6f4
feature: adds text to video generation flag ( #404 )
...
Co-authored-by: jaydrennan
10 months ago
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
558d3388e5
style: speed up linting and autoformatting. fix lints
1 year ago
8e956f5360
feature: add some helper functions
1 year ago
82d74c6b49
feature: switch to pydantic models
...
- allow prompt re-use by deferring random seed
1 year ago
e53459a50a
build: check for torch version at runtime ( fixes #329 )
1 year ago
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
d32e1060cd
feature: multi-controlnet support at the command line
...
add controlnet option for edit demo
1 year ago
4c77fd376b
feature: improvements to memory management
...
not thoroughly tested on low-memory devices
1 year ago
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
765e607c2c
fix: file numbers start after latest image, even if some previous images were deleted
1 year ago
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
52044c1073
fix: use model appropriate composition size
2 years ago
3b777b98d8
fix: improved large images using composition
2 years ago
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
2 years ago
d5cff45bff
feature: allow input of raw control images
2 years ago
d7e494241c
fix: composition images were too blurry
2 years ago
b261c62d4e
docs: update docs
2 years ago
54c3ad51d6
feature: controlnet
2 years ago
929eff353e
fix: edit was broken by recent changes
2 years ago
882cc7e0f1
feature: generate large images with coherent composition
2 years ago
2aef6089e0
feature: generate large images
...
Added a composition stage so large images are more coherent
2 years ago
1c8893cecc
fix: fix image gen retry
2 years ago
ea1d4baafe
refactor: cleanup image generation code
2 years ago
6c1e3b2ae7
feature: allow specifying output format
...
closes #228
2 years ago
9eacf5e7ed
perf: improve startup time by doing some imports lazily ( #233 )
...
just running `aimg --help` or `aimg --version` was very slow due to all the imports being brought in eagerly
Before changes `aimg --help`
`2.24s user 4.05s system 184% cpu 3.416 total`
After changes:
`0.04s user 0.02s system 8% cpu 0.625 total`
Used `PYTHONPROFILEIMPORTTIME=1 aimg --help` to find time consuming imports.
Also switched to using `scripts` instead of `entrypoints` since the scripts are much faster.
Made duplicate SAMPLER_TYPE_OPTIONS that can be loaded without loading all the samplers themselves.
Likely a breaking change - not sure.
2 years ago
19444d8e22
fix: first frame should be the interesting one
2 years ago
9ee09ac842
feature: add compilation animations ( #224 )
...
- add generation/compare gifs
2 years ago
9e06013ade
feature: save gifs that show image generation process ( #218 )
2 years ago
7bdde559cc
performance: memory management improvements ( #210 )
...
- tile mode made more efficient. especially when not being used
- add script to iteratively make bigger images
2 years ago
c7ed86a36f
feature: auto-retry generation unsafe image is created
2 years ago
16cef16c3e
feature: facilitate references to previous image generation
2 years ago
7c05c3aae2
feature: image edit gifs and demo-reels
2 years ago
2a3e19f5a1
feature: 🎉 Edit Images with Instructions alone!
2 years ago
81f294216b
feature: 🎉 outpainting
2 years ago
fad7f17790
feature: run face enhancement on the GPU
...
Should run 10x faster
2 years ago
5cc73f6087
feature: finetuning
...
- feature: finetuning your own image models
- feature: image prep command. crops to face or other interesting parts of photo
- fix: back-compat for hf_hub_download
- feature: add prune-ckpt command
- feature: allow specification of model config file
2 years ago
239b235140
feature: depth-based image-to-image generations (and inpainting)
2 years ago
ad0b9e8ab8
feature: tile in a single dimension ("x" or "y")
2 years ago
2f8edc1530
feature: negative prompting
...
- feature: negative prompting. `--negative-prompt` or `ImaginePrompt(..., negative_prompt="ugly, deformed, extra arms, etc")`
- feature: a default negative prompt is added to all generations. Images in SD-2.0 don't look bad anymore. Images in 1.5 look improved as well.
2 years ago
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
2 years ago
893b041a8f
feature: progress image callback
2 years ago
7af1ab66ca
fix: add workaround for bug in k_diffusion on mps
...
As documented here: https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/4558#issuecomment-1310387114
- make image logs more consistent
- note which step the progress images belong to in the filename
2 years ago
7fba2972e8
feature: added `DPM++ 2S a` and `DPM++ 2M` samplers
...
-fix: fix bug with `--show-work`
2 years ago
021a0c540d
feature: inpainting model support; improved model manager
2 years ago
94c0aeab12
feature: switch between models without restarting python instance
2 years ago
4d802a043e
feature: stable diffusion 1.5
2 years ago
Bryce
jaydrennan