51c65457c4
workaround for a weird bug in DDIM's make_schedule
3 years ago
53e7616b51
DDIM support returned for img2img
3 years ago
e38ad2ee95
added detailed installation instructions
...
fixed bug with missing same dir for a new install
added ctrl+c hander to immediately stop the program instead of waiting
3 years ago
5ce4f66855
default value for txt2img samplers
3 years ago
7434b3ebcc
updated interface to use Blocks
...
added mode toggle for img2img
added inpainting to readme
3 years ago
bb2faa5fb8
applied fill to all but one inpainting modes, fixed issue with mask resizing
3 years ago
ff98e09d72
UI options for mask blur and inpainting fill
3 years ago
54f74d4472
added first version of inpainting
...
fixed flag option
3 years ago
587db9c420
fixed some bugs in grid
...
changed some default values to more reasonable
added PNG info tab
3 years ago
3402461055
gfpgan is not kept in memory
...
font selection setting
3 years ago
808590654e
pushed the lost --precision switch fr anon to test i
3 years ago
036a0dde70
forgot to remove debug messages
3 years ago
9c9f048b5e
support for generating images on video cards with 4GB
3 years ago
7a7a3a6b19
Option to not save grid for single images for #22
3 years ago
6bec9c3a4f
Merge pull request #21 from orionaskatu/patch-1
...
Typo StableDiffuion
3 years ago
20c33f4423
Queue concurrency 1 to prevent CUDA OOM
...
Mandatory for me as I have a RTX 2070 (8Gb) and I get CUDA OOM if two users launch jobs at the same time.
I can also use multiple tabs and jobs will be queued.
You may not want it to be the default though.
3 years ago
e5480e3688
Typo StableDiffuion
...
Small typo StableDiffuionModelHijack() => StableDiffusionModelHijack()
3 years ago
93e7dbaa71
support for running custom code (primarily to generate various labeled grids)
...
export for 4chan option
3 years ago
d5266c07f9
split draw_prompt_matrix into two: generalized grid annotation and actual prompt matrix
...
disabled saving samples for SD upscale
3 years ago
4ed435dd85
add upscaler modes for #19
3 years ago
c30aee2f4b
fixed all lines PyCharm was nagging me about
...
fixed input verification not working properly with long textual inversion tokens in some cases (plus it will prevent incorrect outputs for forks that use the :::: prompt weighing method)
changed process_images to object class with same fields as args it was previously accepting
changed options system to make it possible to explicitly specify gradio objects with args
3 years ago
4e0fdca2f4
Implementation for SD upscale.
3 years ago
9597b265ec
implementation for attention using [] and ()
3 years ago
92138df5cc
fix gfpgan oom on 6GB
...
force a gc if out of memory
3 years ago
21bcbb945e
fix a bug with wrong row count in prompt matrix
3 years ago
21765c17e6
added samples to img2img
...
fixed a bug with sampler selection (oops)
3 years ago
155dd2fc0c
Renamed GFPGAN to extras
...
Added Real-ESRGAN to extras tab
3 years ago
055dd10aae
Add Denoising Strength to output parameters in the output text
3 years ago
5e83e7081a
option to add prompt matrix variable text parts to start of the prompt rather than the end
3 years ago
c9579b51a6
extra samplers from K-diffusion
3 years ago
91dc8710ec
textual inversion embeddings support
...
settings tab
3 years ago
6a8e76e37f
Check for the embedding manager
3 years ago
781f054a20
Merge branch 'master' of https://github.com/AUTOMATIC1111/stable-diffusion-webui
3 years ago
4b0188dcbf
Textual inversion support
3 years ago
199123e98d
add execution timings to output
...
change the text output element to HTML
3 years ago
29f7e7ab89
save image generation params into text chunks for png images
3 years ago
da96bbf485
commandline options to control saved file type/quality/names
3 years ago
15a700bbe5
Merge branch 'master' into master
3 years ago
32dd552883
loopback mode for img2img
...
commandline options for grid filetypes and max batch count
3 years ago
abb83239e5
torch_gc/empty cache after generation
...
added torch_gc() which calls both cuda.empty_cache() and cuda.ipc_collect()
called before and after generation
3 years ago
29d0d65504
jpg grid, named grid
...
Grid file named with seed and prompt, output as jpg
3 years ago
852baf422a
gfpgan dir for the guide's directory names
...
fix a bug in image resizing
3 years ago
1463d44faf
added resizing modes
...
added more info into readme
3 years ago
2a0f8afb29
remove remote image as sample for img2img (it will now use a local image if you have one, none otherwise)
3 years ago
6efddcb279
hide gradio progressbar for about 10% speed increase on my GPU; a commandline option to prevent hiding
3 years ago
165da39fb1
fixed a possible issue with older versions of PIL
3 years ago
81087207bc
--no-half commandline option to disable .half()
3 years ago
7fd0f31661
added prompt verification: if it's too long, a warning is returned in the text field along with the part of prompt that has been truncated
3 years ago
aa67540eba
Added prompt matrix to img2img
...
refactoring: separated duplicate code from img2img and txt2img into a single function
3 years ago
cb118c4036
Prompt matrix now draws text like in demo.
3 years ago
61bfa6c16b
additional picture for prompt matrix
...
proper seeds for img2img
a bit of refactoring
3 years ago
60e95f1d8c
silence the warning from transformers
...
add feature demonstrations to readme
3 years ago
3395c29127
added prompt matrix feature
...
all images in batches now have proper seeds, not just the first one
added code to remove bad characters from filenames
added code to flag output which writes it to csv and saves images
renamed some fields in UI for clarity
3 years ago
b63d0726cd
fixed bug with images not resizing for img2img
...
added GFPGAN as an option for img2img
added GFPGAN as a tab
added autodetection for row counts for grids, enabled by default
removed Fixed Code sampling because no one can figure out what it does; maybe someone will be upset by removal and will tell me
3 years ago
3324f31e84
first
3 years ago
AUTOMATIC
orionaskatu
Craftyawesome
dogewanwan
hlky