ad7a9db824
fixup
2023-01-28 18:54:01 +03:00
409c2b8d9e
do not antiblur not masked areas
2023-01-28 18:47:47 +03:00
7e3213d40a
add notes about json and links to validators
2023-01-28 18:22:23 +03:00
50f3443e8c
open RIFE since nothing is below atm
2023-01-28 18:14:35 +03:00
c9d4363173
name the version 2.0b
...
I absolutely think now that all this week PRs are merged, we have a full right to name the extension Deforum 2.0 (beta, at least)
2023-01-28 18:13:27 +03:00
2b477fc0c1
move composable mask to prompts
...
since they are basically clipseg prompts and that tab is nearly empty anyway
2023-01-28 18:10:37 +03:00
03b6624877
open mask, seed and checkpoint schedules
...
they are opened quite often
2023-01-28 18:08:37 +03:00
9e3d0a4054
move steps to sampler to reflect webui's tab
2023-01-28 18:06:00 +03:00
cf0c3cdc0f
hide seed extras under accordion
2023-01-28 18:02:41 +03:00
044d6c4f43
move parseq to init tab
2023-01-28 18:02:23 +03:00
a3764d7fd1
move seed_behavior to schedules
2023-01-28 17:58:46 +03:00
eecfb05a0f
put manual video settings under accordeon
2023-01-28 17:55:09 +03:00
1fc342f2db
add FizzleDorf's guide to links
2023-01-28 17:52:35 +03:00
62b12f24e9
note about enabling composable masks
2023-01-28 17:48:39 +03:00
bb5a67d591
close 3d depth and fov sections
2023-01-28 17:47:07 +03:00
3a2913f6ae
move guided images higher
2023-01-28 17:45:31 +03:00
ba4517088f
move noise schedule unver noise settings
2023-01-28 17:43:11 +03:00
74c2bce5b3
Merge branch 'automatic1111-webui' into pr/260
2023-01-28 17:34:26 +03:00
c1c061f8b6
Merge branch 'automatic1111-webui' into reduce-torch-cv2-conversions
2023-01-28 17:29:57 +03:00
d6b80ad965
save loop args
2023-01-28 17:29:32 +03:00
14bb7f2bd4
compacting run even more
2023-01-28 16:05:37 +02:00
6f69254a7e
more compact 'run' tab + removal of more hrfix params
2023-01-28 16:02:57 +02:00
c1ef1cc125
fixup word mask sample format
...
fixup
2023-01-28 16:33:56 +03:00
676ac2e514
blend noise, so it won't be whitened out
2023-01-28 16:29:49 +03:00
51b1e8d0c5
fixup
...
fixupx2
fixupx3
fixupx4
fixupx5
fixupx11
2023-01-28 16:06:14 +03:00
d65adb0aed
better composable mask text format
2023-01-28 14:44:01 +02:00
f5797eb738
Merge remote-tracking branch 'upstream/automatic1111-webui' into better_ui_and_cleanups
2023-01-28 14:34:24 +02:00
2d8fa220a2
Merge branch 'automatic1111-webui' into reduce-torch-cv2-conversions
2023-01-28 15:26:50 +03:00
b3dcba62df
Merge remote-tracking branch 'upstream/automatic1111-webui' into better_ui_and_cleanups
2023-01-28 14:13:41 +02:00
6184788725
rename frame interpolation text
2023-01-28 14:03:32 +02:00
8eb949cd86
fix header text
2023-01-28 13:55:45 +02:00
129f8d7773
remove redundant line from ui
2023-01-28 13:54:19 +02:00
3eb9b81f44
Merge branch 'automatic1111-webui' into masking-overhaul
2023-01-28 14:53:22 +03:00
3ae0103246
Merge branch 'automatic1111-webui' into masking-overhaul
2023-01-28 14:53:03 +03:00
7b0888de55
better args order
2023-01-28 14:48:55 +03:00
714fbb5efd
fix subseed text
2023-01-28 13:48:35 +02:00
2de462b919
hide save_samples and display_samples
...
doesn't do anything, not sure if to keep or not
2023-01-28 13:48:18 +02:00
1055082a36
remove override_these_with_webui
2023-01-28 13:44:50 +02:00
6346dae8a8
move steps up
2023-01-28 13:42:21 +02:00
dbdfaaf8ae
add deforum rng to set noise seed better
2023-01-28 14:41:39 +03:00
f3bdad2d58
rename enable extras text
2023-01-28 13:40:00 +02:00
70518c5633
remove never-worked grids
2023-01-28 13:39:14 +02:00
a1a4fbc976
move tiling down
2023-01-28 13:35:48 +02:00
0e0d4593b7
remove restore_faces
...
never worked
2023-01-28 13:33:50 +02:00
dd59464f9b
remove highrezfix
2023-01-28 13:31:57 +02:00
15eca6b9e3
add pairwise implementation internally
...
not to upgrade the whole python to 3.10 just for one function
2023-01-28 13:35:55 +03:00
6e559058f2
fix text
2023-01-28 12:20:07 +02:00
dd21743655
keep sample as cv2 in add_noise
2023-01-28 13:16:51 +03:00
2709aa28cd
less bottom margin before video preview
2023-01-28 12:01:27 +02:00
af6bf6810d
more cleaning and fixing paths
2023-01-28 11:59:32 +02:00
3c56718bb8
fov to 70 and better seed_sch text
2023-01-28 11:19:13 +02:00
368e9bbf13
fix broken hybrid info tab
2023-01-28 11:10:58 +02:00
4a698c6dd6
more removing
2023-01-28 10:42:20 +02:00
e086917cad
remove html_trash done
2023-01-28 10:37:16 +02:00
f17b233570
Progresss
2023-01-28 10:24:43 +02:00
5611827ed0
added exceptions when incorrect looper settings
2023-01-28 00:22:20 -08:00
f90e6f1cbf
reordered args
2023-01-28 00:21:33 -08:00
2609dc8121
making description more readable
2023-01-27 23:49:20 -08:00
f479e28ff3
cleaning up imports
2023-01-27 21:42:17 -08:00
eb5ce51ea5
v1
2023-01-28 03:03:57 +02:00
4165fdedf4
no more redundant cv2 torch conversions in render
2023-01-28 02:09:44 +03:00
f76b1c1343
adding more details to variables
2023-01-27 15:01:59 -08:00
9c67bee3a6
remove return_sample
2023-01-28 01:58:39 +03:00
367c870183
making sure save works
2023-01-27 14:51:50 -08:00
ea0c4498b8
Merge branch 'deforum-art:automatic1111-webui' into frame-insertion
2023-01-27 14:39:02 -08:00
79c5307ba2
reverting readme putting into guided image
2023-01-27 14:38:27 -08:00
2afed339ae
remove unneeded sampler callback
2023-01-28 01:31:18 +03:00
e1f453122f
remove unneeded k_samplers
2023-01-28 01:25:57 +03:00
697c3230db
updating looper keys to use proper names
2023-01-27 14:13:21 -08:00
93f840a654
Merge remote-tracking branch 'upstream/automatic1111-webui' into frame-insertion
2023-01-27 14:00:52 -08:00
9cf4a99474
remove debug printing
2023-01-28 00:52:44 +03:00
4b4c465cc6
update html counter
2023-01-28 00:46:04 +03:00
34c9d5a787
Merge branch 'automatic1111-webui' into masking-overhaul
2023-01-28 00:42:27 +03:00
24e9bf627a
fixup video settings IO
2023-01-28 00:30:34 +03:00
35db8dbcfe
make it finally work!
...
fixup
2023-01-28 00:23:00 +03:00
2643076978
gradio stuff is passed as args, not kwargs
2023-01-27 23:59:47 +03:00
0337bb8613
syntax errors fixup
2023-01-27 23:23:09 +03:00
ff5f0eac75
fixup
2023-01-27 23:07:41 +03:00
af66378971
move run_deforum to kwargs too
2023-01-27 23:05:33 +03:00
2a5f5b5773
save/load settings as kwargs
2023-01-27 22:45:00 +03:00
c760166806
get components from list
2023-01-27 22:03:14 +03:00
638040ad1f
separate hybrid and html args
2023-01-27 22:02:44 +03:00
7285af2fab
store settings list only in one place in args.py
2023-01-27 21:44:55 +03:00
2b1f26e4da
removing prepare mask, its imported
2023-01-27 10:27:04 -08:00
5189a6aab3
adding back in loop vars
2023-01-27 10:26:47 -08:00
a00b727ada
removing extra image load def
2023-01-27 10:03:37 -08:00
b4d58becb0
Merge remote-tracking branch 'upstream/automatic1111-webui' into frame-insertion
2023-01-27 10:03:21 -08:00
11d48147b9
Merge pull request #250 from hithereai/fix_rife_fixed_fmpeg_path
...
make rife ffmpeg_path use ffmpeg_location
2023-01-27 18:27:18 +03:00
1a5c0d050d
Merge pull request #253 from hithereai/fix_interp_mode_not_running
...
fix interpolation mode not running
2023-01-27 18:27:03 +03:00
65e614d814
Merge pull request #251 from hithereai/ffmpeg_as_default_changes
...
ffmpeg as default + no more need to install or add to PATH
2023-01-27 18:26:41 +03:00
57cba7b6fd
save interp frames if ffmpeg can't be found as default
...
and return a more elegant message about what is happening if ffmpeg wasn't found instead of returning a general FILE NOT FOUND
2023-01-27 14:06:27 +02:00
68e35c4def
fix save settings
...
add missing checkpoint args and re-ordering
2023-01-27 12:57:23 +02:00
e4d9c9f666
fix interp mode not running
...
also add model_schedule suppport to interpolation mode
2023-01-27 11:36:39 +02:00
5c10d59c61
use looper init when use looper true
2023-01-26 22:31:17 -08:00
92f2f7a813
set default args
2023-01-26 22:06:39 -08:00
887e327c94
reordering ui elements
2023-01-26 20:32:47 -08:00
3354e1c5df
Update args.py
2023-01-27 02:45:22 +02:00
1f0240e41e
ffmpeg_location no longer hidden in the UI
...
also return 'ffmpeg' if couldn't find the right binaries in our env/venv
2023-01-27 02:24:39 +02:00
8e0bc99a09
reset ffmpeg_location to None
2023-01-27 02:06:39 +02:00
f1a093e0ec
add dynamic ffmpeg_location to frame_interpolation.py
2023-01-27 02:00:14 +02:00
04f27c9439
no more need to install ffmpeg + set ffmpeg to default
2023-01-27 01:35:09 +02:00
6179c06884
how to use and cleanups
2023-01-25 18:24:22 -08:00
37be9cafe0
removing extra prints
2023-01-25 17:48:51 -08:00
86e6be9edf
reordering params
2023-01-25 17:43:11 -08:00
384368155d
adding variable breakout and cleanup
2023-01-25 17:31:57 -08:00
e7bbb1bbca
Merge branch 'deforum-art:automatic1111-webui' into frame-insertion
2023-01-25 15:47:15 -08:00
1b2ebf5916
Update inference_video.py
2023-01-26 00:10:21 +02:00
f940610716
sync the main branch and masking-overhaul
2023-01-25 22:26:02 +03:00
c9d09ecc57
Merge branch 'deforum-art:automatic1111-webui' into frame-insertion
2023-01-24 15:53:27 -08:00
993ff0726d
add back requests
2023-01-24 15:46:47 -08:00
6d8f94878d
remove unnecessary sk-video import
2023-01-25 01:43:48 +02:00
96a6329466
Merge remote-tracking branch 'upstream/automatic1111-webui' into frame-insertion
2023-01-24 15:09:59 -08:00
8bb2cef635
Merge branch 'automatic1111-webui' into frame_interpolation
2023-01-24 22:28:55 +02:00
1334fc31a9
remove debug info printing
2023-01-24 23:19:15 +03:00
cda6f368ad
composable mask index fixup
2023-01-24 22:39:09 +03:00
9c1b6ade16
fix temp variable indices
2023-01-24 21:21:41 +03:00
35218c2f04
no half clipseg
...
halving clipseg doesn't work for some reason, so use fp32 here
2023-01-24 21:15:58 +03:00
7758adbca5
don't need to declare nonlocal twice
2023-01-24 20:14:31 +03:00
7bdf40734b
prevent overwriting of mask presets
...
instead of reloading them every frame
2023-01-24 20:11:19 +03:00
46d23a7bbc
remove commented-out code
2023-01-24 19:48:58 +03:00
f75d534f32
pass nonlocal inner_idx to mask loaders
2023-01-24 19:48:16 +03:00
3ca7d853f0
strip the curvy brackets from the output
2023-01-24 19:32:48 +03:00
5974a15d1e
reset mask vals every frame
2023-01-24 19:28:24 +03:00
b103e4d1b9
fix parser's output
2023-01-24 19:26:41 +03:00
c46c23ee7b
fix nested parentheses parsing
2023-01-24 18:52:28 +03:00
567bc87b3e
handle nested brackets with closure counter
2023-01-24 16:49:00 +03:00
c8c24f1033
fix regex and output strings
2023-01-24 16:48:38 +03:00
c10c98c894
add use_noise_mask to the args
2023-01-24 16:42:15 +03:00
ae37a48ca3
better text v2
2023-01-24 12:16:06 +02:00
b68f9d6d4f
better text
2023-01-24 12:09:36 +02:00
8ae5cc0c3f
Final fixes + option to keep interp frames
2023-01-24 12:04:13 +02:00
93ab7f3db3
add missing params to settings.py
2023-01-24 11:18:20 +02:00
f381897174
remove old comments
2023-01-24 11:06:23 +02:00
bfe90b8562
Merge branch 'frame_interpolation' of https://github.com/hithereai/deforum-for-automatic1111-webui into frame_interpolation
2023-01-24 10:50:59 +02:00
c65df56220
final touches
2023-01-24 10:50:55 +02:00
e6c54e4a5d
Delete ffmpeg_replacer.py
2023-01-24 02:59:02 +02:00
245cf87188
global controls for ffmpeg crf and preset + cleanup p1
2023-01-24 02:57:51 +02:00
6c36adc9b8
almost ready, add cli-ffmpeg calls that work
2023-01-24 01:04:37 +02:00
0ac8bd32fa
tabs -> spaces fixup
2023-01-23 22:15:54 +03:00
32d3b6fa38
add the actual schedule to the args
2023-01-23 22:15:15 +03:00
f417cc33ff
consistent use of quotes
2023-01-23 09:37:03 -08:00
c52751f5c0
add checkpoint schedule
2023-01-23 09:24:05 -08:00
0f99d791c9
add 'everywhere' to usable vars
2023-01-23 19:48:24 +03:00
aa72ee7bb4
var -> match_object
2023-01-22 20:10:09 +03:00
e874b451bd
fixup imports
2023-01-22 15:18:05 +03:00
e2d13eb04b
Update ffmpeg_replacer.py
2023-01-22 13:33:05 +02:00
7b9abc66cd
PyAV ffmpeg usage to save interp vids
2023-01-22 04:27:57 +02:00
3c111cafb0
Update inference_video.py
2023-01-21 15:57:06 +02:00
8ed69c2430
change logic!
...
change logic to save pngs instead of using cv2 to directly save the video cuz it cannot do proper h2654 with opencv-python.
First step out of a few prolly.
2023-01-21 15:56:47 +02:00
7d617f3faf
dynamic model loading fixes
2023-01-20 21:26:14 +02:00
0a6960ff2b
better UI-text and add hints
2023-01-20 20:48:06 +02:00
78b5639227
better folder name
2023-01-20 20:34:02 +02:00
96635be7a5
Delete inference_img.py
2023-01-20 20:29:02 +02:00
8ff265f7db
remove print statement
2023-01-20 20:27:52 +02:00
ed20c17342
move license to correct file
2023-01-20 20:26:55 +02:00
7fe85a81ca
less files more happy, add rife 4.0, revert args
2023-01-20 20:23:55 +02:00
94aa4052c7
tiny fixes
2023-01-20 18:04:39 +02:00
46e02c063f
Delete README.md
2023-01-20 17:31:38 +02:00
4a53e275aa
Working properly v1
2023-01-20 17:29:38 +02:00
60363b555c
still not 100% there, getting closer
2023-01-19 10:25:59 +02:00
6517100c4d
Merge branch 'frame_interpolation' of https://github.com/hithereai/deforum-for-automatic1111-webui into frame_interpolation
2023-01-18 02:00:42 +02:00
2c30e1ae93
Getting there, not ready yet, add rife 4.3
2023-01-18 02:00:36 +02:00
4b5c44e4a6
Merge branch 'deforum-art:automatic1111-webui' into frame_interpolation
2023-01-17 18:17:23 +02:00
0a91f4db11
Initial GUI Accordion
2023-01-17 18:16:41 +02:00
39c2c6f1f6
make it actually work on autos env
2023-01-17 16:55:27 +02:00
c73a80b62d
Add Practical-RIFE files to src
2023-01-17 13:48:52 +02:00
a51c22c553
remove references to p.sd_model
...
it was removed as a param in e0e8005009Closes #228
2023-01-17 01:48:30 +03:00
6777e0d927
fix set difference
2023-01-16 20:14:23 +03:00
ebe657f630
Merge branch 'automatic1111-webui' into masking-overhaul
2023-01-16 19:43:31 +03:00
9ba8462efd
add defaults so the var keys are always found
2023-01-16 19:31:52 +03:00
446e3430a6
Fixes, -1 as default for unlimited frames and more checks
2023-01-16 18:12:14 +02:00
afa80cd231
more mask format conversion checks
2023-01-16 18:52:39 +03:00
19d106fc9c
convert all input masks to binary
2023-01-16 18:31:24 +03:00
4b311bf874
none to blank to simplity compose logic
2023-01-16 18:28:00 +03:00
32df52f511
Merge branch 'automatic1111-webui' into masking-overhaul
2023-01-16 18:25:01 +03:00
585b2e2051
mask schedule logic
2023-01-16 18:24:46 +03:00
9e0ae9ef26
add extract_from_frame and extract_to_frame to input vid options
...
The current code will always extract all of the input video frames.
This PR adds two new input parameters for extracting an input video:
extract from frame, and extract to frame.
Now we can only test frames 0 to 50, 50 to 100, etc.
2023-01-16 00:56:16 +02:00
c9f41faf3e
use clipseg inference to get word masks
2023-01-16 00:24:43 +03:00
898a261f32
Minor improvements +
...
better handling of wrong file/folder names, added function to delete all imgs from a folder (shorter code); now users can generate only the masks again even without having the 'generate_hybrid_frames' button selected
2023-01-15 22:39:47 +02:00
8d09bc7ddf
upload clipseg directly to src
...
as the current webui's transformers version (4.19) doesn't include it
2023-01-15 18:18:59 +03:00
31df9ed541
add parser for multiple masks boolean combinations
2023-01-15 17:40:14 +03:00
a1d5ed7752
Merge pull request #216 from hithereai/HumanMasking
...
Masking Humans automatically using RVM
2023-01-15 17:36:20 +03:00
1336e84e10
revert pathlib removal
2023-01-15 03:24:53 +02:00
fcafc74c1d
enable offline usage for 3D animation mode
...
It will fetch the model from cache if it's there, so only need to run 3D mode online once for it to work offline afterwards.
* Currently it will work only for windows users.
2023-01-15 03:13:15 +02:00
ecd35261b5
remove pathlib import
2023-01-15 02:53:16 +02:00
891b682c49
enable offline usage after initial run
...
This PR enables to use the new human_mask feature while offline. It only needs to be run once when online, then it will use its cache as first priority.
2023-01-15 02:51:36 +02:00
269d8011e6
fixed setting load/save and comments
2023-01-14 23:35:53 +02:00
e09eecfeb3
Update human_masking.py
2023-01-14 23:13:57 +02:00
fc1faadaae
not needed, being loaded to cache with torch.load
2023-01-14 23:12:26 +02:00
5abe55d1d4
Sync fps according to extract_nth_frame and more
2023-01-14 23:10:08 +02:00
18c89806c2
revert model to mobilenetv3
2023-01-14 17:19:11 +02:00
c9fe53b75f
use extracted input imgs instead of input vid
2023-01-14 16:55:01 +02:00
690deb04a9
Add RobustVideoMatting repo for human masking
2023-01-14 16:08:05 +02:00
5d5287d6cf
V01 of human masking
2023-01-14 15:49:52 +02:00
9636a7510b
Make parseq adapter directly search the JSON data for a likely match if an unrecognised series is requested. This ensures that, when new schedules are added to Deforum, only the Parseq UI needs to be updated to support them (and this can be improved in the future with support for custom fields).
2023-01-12 21:27:54 +11:00
7fc51359a8
add 'Init Video' soundtrack option
2023-01-09 22:43:48 +03:00
b4c764a90a
added missing imports for interpolation mode in prompt.py
...
added imports for 'pandas' and 'numpy'
2023-01-07 23:49:26 +02:00
aa9bffded9
lower default antiblur amount a bit
2023-01-07 13:54:03 +03:00
0b9ac68ce4
rounds steps to int to fix error
2023-01-06 18:26:26 +03:00
23657be814
removed untested code
2023-01-05 21:12:46 -06:00
kabachuha
hithereai
Matisse
Ryan Scarbery
rewbs
Kitchen