7d27b6f6cf
p
2023-02-11 14:07:17 +02:00
3d1dea472d
move loc near seed sch
2023-02-11 13:11:54 +02:00
68e3e7c5cc
fixes
2023-02-11 12:54:40 +02:00
aa2f7de4dd
progress
2023-02-11 12:47:43 +02:00
7b883f38da
initial c
2023-02-11 12:40:17 +02:00
817fc515ec
tiny change, finished
2023-02-11 10:27:00 +02:00
6784cc3765
comment out gif related gradio func
...
will remove when PILgif is completely removed from the entire code base
2023-02-11 01:24:16 +02:00
667f01cfa6
fix non compact row
2023-02-11 01:18:14 +02:00
abff7a6432
add elem_id to top info accord
2023-02-11 01:13:37 +02:00
5a480b30ba
remove old commented line
2023-02-11 01:10:21 +02:00
44f73de0f9
update ui texts
2023-02-11 01:08:42 +02:00
0afa6bf45d
del old rife msg about gifs
2023-02-11 00:58:23 +02:00
8de0ecaf18
upscale W/H txt box to sliders
2023-02-11 00:46:13 +02:00
b6c76855d3
cleanups p1
2023-02-11 00:40:06 +02:00
131a58cd3d
rife frame2vid and upscale to tabs
2023-02-11 00:37:34 +02:00
50a70b922c
Update args.py
2023-02-11 00:23:49 +02:00
cf01f1c713
fix upload box height
2023-02-11 00:14:07 +02:00
76247e2b54
fix old wrong elem_id name
2023-02-10 23:23:18 +02:00
3deb56d6c4
edit accord name
2023-02-10 23:22:33 +02:00
8418b00786
fix typos + close upscale accord at default
2023-02-10 23:21:46 +02:00
365aac73b7
Update render.py
2023-02-10 22:37:06 +02:00
629a38d193
fix wrong name
2023-02-10 22:30:59 +02:00
2ec90a75ef
done?
2023-02-10 22:30:13 +02:00
437a30bc81
Update render.py
2023-02-10 22:13:52 +02:00
b16249a887
closer to done
2023-02-10 21:48:32 +02:00
3842b43be0
upgrades
2023-02-10 21:32:42 +02:00
32d00deb08
Update generate.py
2023-02-10 21:16:53 +02:00
1f630bedee
Update generate.py
2023-02-10 21:01:24 +02:00
701ce0ac7c
Update generate.py
2023-02-10 20:56:27 +02:00
33ee2c692e
Merge remote-tracking branch 'upstream/automatic1111-webui' into cli_upgrades
2023-02-10 20:17:38 +02:00
c25cd77820
Update render.py
2023-02-10 19:50:08 +02:00
38f27bd0ae
Update render.py
2023-02-10 19:20:30 +02:00
d2d3f88ea6
more p
2023-02-10 18:17:59 +02:00
1796393cd7
PROGRESS
2023-02-10 17:57:09 +02:00
7c6dac1304
Update render.py
2023-02-10 17:11:42 +02:00
14dbd8925f
progress
2023-02-10 16:55:14 +02:00
56c0cba1c9
d
2023-02-10 16:30:02 +02:00
33961de218
c
2023-02-10 15:45:26 +02:00
55c22cb03c
b
2023-02-10 15:38:55 +02:00
79bbeaa566
make def val of pix2piximgcfgscale = webui's one
2023-02-10 02:54:24 +02:00
93562052e1
add missing things to args
2023-02-10 02:37:56 +02:00
5dea4577fd
initial commit
2023-02-10 02:27:08 +02:00
ad6447e223
Merge branch 'automatic1111-webui' into upscale-video
2023-02-10 01:42:56 +03:00
c1c3f575ae
allow all upscalers
2023-02-10 01:04:04 +03:00
be424e8630
Merge pull request #315 from hithereai/ui-updates-v0.12
...
UI updates v0.12
2023-02-10 00:49:43 +03:00
b26c607cc9
extra ui cleaning + new hints
2023-02-09 23:37:16 +02:00
3555898c0a
fix videogen sorting
...
closes #305 . at least, I didn't get the bug running it after the fix
2023-02-10 00:33:48 +03:00
badd911186
fix videogen sorting
...
closes #305 . at least, I didn't get the bug running it after the fix
2023-02-10 00:33:24 +03:00
ebf2d2145b
fixup
2023-02-10 00:28:01 +03:00
10d84d7f43
remove ugly columns
2023-02-09 21:32:24 +02:00
b2e97e1358
add html elem_ids to some elements
2023-02-09 21:19:07 +02:00
169cde95df
run from file & resume into 1 accord, and now as tabs
2023-02-09 20:52:06 +02:00
e4075ddf60
more cleaning
2023-02-09 19:57:22 +02:00
950b86f1b8
cleaning up
2023-02-09 19:37:24 +02:00
1c2431c906
rename arg and update info comment
...
doesn't ruin anything (!)
2023-02-09 18:29:45 +02:00
af3f08b43f
fix "sorry, no audio" bug-msg when rifing external vid with no audio
2023-02-09 18:26:08 +02:00
1b8b34acde
fixup args
2023-02-09 16:04:08 +03:00
227d80b953
lower the default upscale value
...
so it won't take an eternity to test
2023-02-09 15:45:44 +03:00
a59be97d9c
fixup
2023-02-09 15:42:18 +03:00
2ac11aa1bd
video upscaling logic
2023-02-09 15:24:40 +03:00
e511ad8d96
depth_w and fov to tabs under accordion
2023-02-09 12:29:14 +02:00
b0bfba7dd8
hide mask_contrast_adjust + mask_brightness_adjust from ui
2023-02-09 12:19:21 +02:00
8ab755d00b
cleanup, still not ready for prime time (!)
2023-02-09 01:11:51 +02:00
f6635cdade
better margins before text
2023-02-09 00:59:07 +02:00
40d83be379
better Composable Mask scheduling text, now formatted properly
2023-02-09 00:56:38 +02:00
d16caa2055
better prompt info text
2023-02-09 00:52:27 +02:00
80df6019a8
progress
2023-02-09 00:51:05 +02:00
8e75d236b9
GETTING BETTER
2023-02-08 23:21:00 +02:00
4c58ff06a5
bugfixes and improvs
2023-02-08 23:14:53 +02:00
1a6e4b409f
TABS
2023-02-08 22:31:35 +02:00
66d2b93619
switch coherence and noise place in ui+ close checkpoint accord at default
2023-02-08 19:20:31 +02:00
d09f709a88
hide perlin h and w for now, slicker perlin ui
2023-02-08 19:13:17 +02:00
3c3a19bc3b
prettify init tab
2023-02-08 18:45:39 +02:00
7f10dc6b53
updated hints, css and ui (args py)
2023-02-08 18:41:01 +02:00
ad5aded65b
Merge branch 'automatic1111-webui' into upscale-video
2023-02-08 19:04:33 +03:00
c1f38ef84e
update neg/pos ui text
2023-02-08 17:50:53 +02:00
b05564f812
a few changes def in desc
...
- move prompts info to accordion
- change prompts_negative text so it doesn't say ''don't use --neg here', and instead replacing --neg in the backend (should be a rare case, and a hint will be added in a diff commit)
2023-02-08 17:49:18 +02:00
881aeda3d0
args labels in ui no longer contain underscores for better a experience
2023-02-08 17:33:05 +02:00
ce3d97a263
a
2023-02-08 14:42:09 +02:00
21160cee07
warning style controlled by css now, and code order
2023-02-08 02:13:02 +02:00
5a13ea1a97
auto enable-disable hybrid tab with crystal clear msg c1
2023-02-08 01:55:45 +02:00
c303687790
revert line count change
2023-02-07 22:17:07 +02:00
0c36d0b688
anim prompt height from 8 to 6 lines
2023-02-07 22:16:23 +02:00
3eb351debd
better default values
2023-02-07 20:03:10 +02:00
5538386a64
better code order
2023-02-07 19:38:23 +02:00
ce1cc754ab
Update args.py
2023-02-07 19:03:10 +02:00
16410e8f2a
move stuff outside of args.py
2023-02-07 19:02:03 +02:00
3ba89a2cb0
keep gradio visibility UI related funcs in dedicated file
2023-02-07 18:59:28 +02:00
0069285799
Raise clear error when ada can't load properly with URL fox a fix
2023-02-07 18:40:35 +02:00
44653d11d5
updated cli-print def script info
...
and removal of non working typo-ed compat element
2023-02-07 12:46:41 +02:00
a834349d7d
better updated info text
2023-02-07 12:34:20 +02:00
efb5b86650
Merge branch 'automatic1111-webui' into upscale-video
2023-02-07 12:53:45 +03:00
a69eb50395
fix video mask loading
...
closes #287
2023-02-07 12:43:03 +03:00
292a3d3a1f
fixme
2023-02-07 11:33:50 +03:00
002aec5f72
better stitch a video text
2023-02-07 09:36:32 +02:00
d5fd8b2c12
Video Output to Output renaming
...
it also saves depth maps now
2023-02-07 09:18:35 +02:00
0a82e890ad
add info that frame insertion works only with 2d/3d anim modes
2023-02-07 02:17:50 +02:00
f86bfa8215
hide anti-blur when not in 2d or 3d anim modes
2023-02-07 02:03:29 +02:00
ad9e8d41e4
naming changes
2023-02-07 01:59:29 +02:00
0b8beb1103
more progress on auto-hiding
2023-02-07 01:50:56 +02:00
997a173328
more auto-hiding
...
still not ready for prime time
2023-02-07 01:12:09 +02:00
52b0ae45ae
save_depth_maps moved to output tab
...
so we can auto-hide 3d depth warp accord whenever 3d isn't selected. as save_depth_maps work in all modes.
2023-02-07 00:46:08 +02:00
0baebb8f49
flip_2d_perspective -> enable_perspective_flip renaming
...
loading old setting file work properly:
WARNING: Setting 'flip_2d_perspective' has been renamed to 'enable_perspective_flip'. The saved settings file will reflect the change
2023-02-07 00:06:06 +02:00
1ce6f45e44
merged two motion accordions, auto-hide non-relevant params
2023-02-06 23:45:14 +02:00
190fc0cd3a
remove old commented line
2023-02-06 23:05:17 +02:00
2b5070a68c
fix frames-to-video
2023-02-06 22:33:56 +02:00
1495ad819e
revive "manual settings" as Stitch frames To video
2023-02-06 22:14:19 +02:00
56be2b8df0
set to_frame=999999 if to_frame received as -1
2023-02-06 22:13:32 +02:00
6d77ecdc62
align deforum 2.0b to center, stitch frames almost ready (still hidden)
2023-02-06 21:13:06 +02:00
3731ae957d
revert manual set visibility to hidden again
2023-02-06 19:05:52 +02:00
fc6c9b03d3
don't try to run stitch frame when no img is uploaded
2023-02-06 19:02:54 +02:00
4e39fbd008
add style.css, hide non-working buttons under video gallery
...
and initial (hidden for now) new version of manual settings --> stitch video from frames. Not active yet.
2023-02-06 18:15:56 +02:00
84d2777089
remove old commented linees
2023-02-06 13:48:19 +02:00
27e6b7168c
bring back restore_faces, but visible=False for now
...
Until it's fixed
2023-02-06 13:43:34 +02:00
db226a51dc
fix manual sett accord to visible=false again
2023-02-06 00:56:00 +02:00
6e45198b9b
wrap entire ui in gradio.Blocks() for css compatability
2023-02-06 00:48:32 +02:00
b2e8b9d38a
move fov accordion to inside of 3d d-warp accordion
2023-02-05 23:58:56 +02:00
295d043a06
move resume_from from init to to 'run' tab's bottom
2023-02-05 23:05:20 +02:00
b73373be27
manual_settings accord Visible=False for now
...
Until I fix it to work like it should have from the start (dedicated button inside the accord to actually stitch frames to video without generating a new animation while doing so)
2023-02-05 22:02:17 +02:00
9ef61abb7f
hide Manual Settings when skip_vid = True
...
I checked and it won't run even the manual settings when skip_vid is True.
2023-02-05 21:46:06 +02:00
42849dac8e
hide most vid out elements when skip_vid is True
2023-02-05 21:21:25 +02:00
da9973ce6d
Merge remote-tracking branch 'upstream/automatic1111-webui' into ui_updates
2023-02-05 20:30:00 +02:00
be167130e1
Merge pull request #298 from hithereai/t2
...
fix interpolation mode, remove histogram_matching, rename core arg from useLooper -> use_looper
2023-02-05 18:40:33 +03:00
24d9abba0e
no need to rename useLooper
...
It is a backend variable
2023-02-05 18:39:53 +03:00
9454afa488
handle deprecation on settings load
2023-02-05 17:54:09 +03:00
61e3b10754
add deprecation utils
2023-02-05 17:51:08 +03:00
0ddbc46d9a
Merge pull request #303 from MatissesProjects/add-pos-neg-to-save-load
...
add positive and negative prompts to save/load
2023-02-05 17:25:51 +03:00
b4f764e6d4
str_sch 0.6 -> 0.65, noise_sch 0.08 -> 0.065
2023-02-04 23:05:10 +02:00
bf09e8ba15
remove 'general settings' accord, contr_sch to coherence
2023-02-04 22:48:16 +02:00
e529e29e09
auto-hide cadence if anim_mode=interp or vid_input
2023-02-04 22:31:58 +02:00
dd312deddc
move cadence to top accordion
2023-02-04 22:22:35 +02:00
4c4fcba54c
ffmpeg preset from from veryslow to slow
2023-02-04 22:12:06 +02:00
a852776ad1
fps def val from 12 to 15
2023-02-04 22:08:43 +02:00
82f68b897a
init strength slider steps from 0.02 to 0.01 fix
2023-02-04 21:50:39 +02:00
b2145c205e
ffmpeg prints runtime, errors, audio handling and more
2023-02-04 21:45:46 +02:00
7e55910c17
set default royalty free working vid in vid_init_path
2023-02-04 21:26:16 +02:00
b77fd6900c
support redirection for fetching vid/aud files from the net
...
302 redirect would give an error until this change. now it reads it properly from the redirected link.
2023-02-04 20:08:13 +02:00
afaf9c2dbc
check animation prompt pos/neg exist in file
2023-02-04 07:18:23 -08:00
2f3904748e
set min width for hybrid top columns
2023-02-04 15:13:10 +02:00
69b11a8511
getting there
2023-02-04 13:29:34 +02:00
fbbef016f8
add positive and negative prompts to save/load
2023-02-03 19:04:38 -08:00
8bb093d3b9
shorter code same logic
2023-02-04 03:45:54 +02:00
f56d70c22b
option to auto-close/open all accordions
2023-02-04 03:15:05 +02:00
6905b778d0
better
2023-02-04 02:51:13 +02:00
88232fef1f
shorter functions - less code
2023-02-04 02:34:45 +02:00
a2b2c1fd21
...
2023-02-04 02:25:17 +02:00
8e18495cd4
more prog
2023-02-04 01:15:53 +02:00
83b0861a44
more progress
2023-02-04 01:05:45 +02:00
e800ac7fb0
progress
2023-02-04 00:44:50 +02:00
e04dec02b9
progress
2023-02-04 00:03:43 +02:00
734c972037
border -> gr.radio
2023-02-03 22:35:38 +02:00
58d0f56d55
auto-hide max_frames when anim_mode=vid_input
2023-02-03 22:28:37 +02:00
0c1e7b1028
initial
2023-02-03 22:02:38 +02:00
0a5ad1914a
color_force_grayscale now works in all animation modes
...
Thanks to @reallybigname's quick tip/fix!
2023-02-03 20:36:57 +02:00
554e4caf98
fix interp mode, remove histogram_matching +
...
arg from useLooper --> use_looper to make it less confusing
2023-02-03 13:41:45 +02:00
e88692638a
remove default 'hq' positive and 'blurry' negative prompts
2023-02-03 11:07:01 +02:00
c1d8539ea2
Revert "flip_2d_perspective -> enable_perspective_flip renaming ( #294 )"
...
This reverts commit 3519de8a7d
2023-02-02 22:34:37 +03:00
3519de8a7d
flip_2d_perspective -> enable_perspective_flip renaming ( #294 )
...
+ updated hints and UI
2023-02-02 20:43:37 +02:00
a36a8e6917
Merge branch 'automatic1111-webui' into pr/289
2023-02-02 18:00:28 +03:00
2ac7957cef
even better process_video_interpolation
2023-02-02 14:35:50 +02:00
7b08396561
better shorter process_video_interpolation func
2023-02-02 14:22:47 +02:00
859d7f1000
better comment
2023-02-02 13:49:45 +02:00
368725984d
remove old comment
2023-02-02 13:48:44 +02:00
a5a4e66470
finish cleaning args.py
2023-02-02 13:46:12 +02:00
67b65508cd
move more from args.py + remove imports
2023-02-02 13:41:29 +02:00
026fb2062d
move code outside of args.py + better comments
2023-02-02 13:35:53 +02:00
39719eb58a
better comment
2023-02-02 13:07:02 +02:00
9ae1c7cdcb
remove old commented line
2023-02-02 13:01:38 +02:00
090e77afed
more shortening (same logic ofc)
2023-02-02 12:56:51 +02:00
d0817fa9f4
more code shortening
2023-02-02 12:53:59 +02:00
c47262450a
code shortening
2023-02-02 12:50:55 +02:00
c99c181192
tiny improv make more sense
2023-02-02 07:44:00 +02:00
5ce6c4516e
if out fps is int, show int and not float (30 instead of 30.0)
2023-02-02 07:01:02 +02:00
642fdc6c33
set UHD=True if input res is 2K or higher
2023-02-02 06:53:37 +02:00
dc050bfaa2
support 5 digits instead of 4 for filename ending number
...
and better info text
2023-02-02 06:31:37 +02:00
e17a6aab0d
more comments
2023-02-02 06:15:09 +02:00
6295bec47a
more fixups and upgrades
2023-02-02 05:59:21 +02:00
6f81045bff
rife hidden link in rife word in info txt
2023-02-02 04:58:45 +02:00
3c4e576f61
replace dots in out_foldername
2023-02-02 04:50:08 +02:00
40067860c7
better code order
2023-02-02 04:04:33 +02:00
794abceaeb
cleanups
2023-02-02 03:49:00 +02:00
984b5566f7
Update args.py
2023-02-02 03:37:42 +02:00
dfd5203692
move set_interp_out_fps from args to frameinterp
2023-02-02 03:37:33 +02:00
7a2b74b622
move function from args.py to frame_interp file
2023-02-02 03:34:10 +02:00
8ea440b3c9
deduplicate function - import instead
2023-02-02 03:32:20 +02:00
f73be57fd9
better set_interp_out_fps func
2023-02-02 03:30:02 +02:00
40178382c7
set inputs, outputs for better readability
...
+ print to cli instead of return to no one
2023-02-02 03:25:58 +02:00
75d04b48ed
better function name
2023-02-02 02:59:46 +02:00
7427f0002c
revert hybrid_motion name
2023-02-02 02:51:52 +02:00
a165b07095
fixed hybrid accordion UI
2023-02-02 02:45:40 +02:00
6851d25da2
Merge branch 'deforum-art:automatic1111-webui' into rife_standalone_buttons
2023-02-02 00:54:03 +02:00
08138a6d11
fixes
2023-02-02 00:43:22 +02:00
ebd6f163cc
textbox shows out interp vid expected fps
2023-02-02 00:09:07 +02:00
db97c288ef
progress, don't add audio if slowmo is enabled!
2023-02-01 23:00:46 +02:00
0cfaee87a1
drop windows style endings too
2023-02-01 23:18:08 +03:00
466b24c53f
pass args as 1=1 instead of 1,2,3
2023-02-01 22:16:24 +02:00
73f211371b
Merge branch 'automatic1111-webui' into pr/275
2023-02-01 22:49:59 +03:00
343fd11a3c
Merge pull request #274 from MatissesProjects/positive-negative-prompt
...
add positive and negative prompts to all prompts
2023-02-01 22:45:32 +03:00
2a678e9813
Update inference_video.py
2023-02-01 21:40:44 +02:00
559a7d783d
better printing
2023-02-01 21:34:25 +02:00
3d81c39f6e
Update inference_video.py
2023-02-01 21:26:07 +02:00
bb117c399c
use ffmpegstitch func from import
2023-02-01 21:24:20 +02:00
ddec99a295
remove old comments
2023-02-01 21:01:43 +02:00
7660309bf5
better ffmpeg not found msgs
2023-02-01 21:01:10 +02:00
ef8dc8bd94
Update video_audio_utilities.py
2023-02-01 20:09:10 +02:00
b5e8892fe5
move ffmpeg to function
2023-02-01 20:07:15 +02:00
cad3cee973
order better
2023-02-01 19:12:35 +02:00
58fd6c69e9
clean some more
2023-02-01 19:09:51 +02:00
12435f08c9
more cleaning
2023-02-01 19:00:04 +02:00
e6cd348600
removing not-needed stuff
2023-02-01 18:36:03 +02:00
ab904025e1
Update hybrid_video.py
2023-02-01 03:32:00 +02:00
aee500f1ce
hybrid_vid tiny improvs
2023-02-01 03:30:38 +02:00
93ec4f02d6
vid2frames now gets args with 1=1 format
2023-02-01 03:13:27 +02:00
9129149fe7
p
2023-02-01 03:06:12 +02:00
18bda5fa16
updates
2023-02-01 02:48:03 +02:00
935f112eee
Update inference_video.py
2023-02-01 02:04:22 +02:00
8329e2e1ed
remove printing
2023-02-01 01:59:39 +02:00
3b1affb393
remove/clean png param
2023-02-01 01:58:17 +02:00
b68f6b1b61
no more converting of pngs in case of input VID
2023-02-01 01:54:14 +02:00
ee452672b0
slowmo for input vid fix
2023-02-01 01:42:27 +02:00
aa81308591
Update args.py
2023-02-01 01:29:02 +02:00
38652c8cd1
fix nested folders
2023-02-01 01:28:49 +02:00
94b270ce7d
Merge remote-tracking branch 'upstream/automatic1111-webui' into rife_standalone_buttons
2023-02-01 01:20:16 +02:00
ec2ebf0dc3
Update args.py
2023-02-01 01:20:10 +02:00
17e1d1aaa0
clipskip schedule
...
closes #188
2023-02-01 01:59:52 +03:00
249afdc745
Update args.py
2023-02-01 00:45:19 +02:00
a3607ffbe7
remove code duplication
...
remove weird code duplication again
2023-02-01 01:32:50 +03:00
0f3f6a0305
fix bugs
2023-01-31 22:23:31 +02:00
18380c9a9a
updates
2023-01-31 19:43:38 +02:00
9a6367e0f2
comment on new kaba's if
2023-01-31 19:24:35 +02:00
cd9198611a
Merge remote-tracking branch 'upstream/automatic1111-webui' into rife_standalone_buttons
2023-01-31 18:58:35 +02:00
f008cb0785
add perspective flip to 3d mode too
...
the more interesting effects we can have, the better
2023-01-31 15:51:55 +03:00
c12912e020
second depth check for previous files in folder
2023-01-31 15:25:37 +03:00
3fdb7b4959
update to cadence logic for new motion against prev_img
...
just a slight reorganization of how hybrid_motion_use_prev_img works during cadence
2023-01-30 22:16:37 -08:00
4db9c32998
remove old commented line
2023-01-31 02:07:04 +02:00
af0db9d022
cleanups v0.0001
2023-01-31 02:03:00 +02:00
69e3dabac0
mucho comments and todo
2023-01-31 01:58:26 +02:00
8665a3d725
move functions outside of gr. blocks
2023-01-31 01:51:59 +02:00
08b5753ab9
c
2023-01-31 01:46:47 +02:00
076b7444ac
pro-gress
2023-01-31 00:34:43 +02:00
ac963c0a78
more progress
2023-01-31 00:14:08 +02:00
d794da0579
more progress
2023-01-30 21:21:47 +02:00
a2303f9bd1
typo
2023-01-30 20:01:58 +02:00
3ff0e229f7
buttons show input fps a f_count in UI
2023-01-30 20:01:42 +02:00
a31ae68133
fixes
2023-01-30 19:09:26 +02:00
8f2ead7a4b
fix typo in function and better printing
2023-01-30 18:40:49 +02:00
652beab852
better vid aud utils
2023-01-30 18:36:18 +02:00
88c77b7401
progress
2023-01-30 18:18:11 +02:00
945db4780a
extract vid using ffmpeg part 1 done
2023-01-30 17:14:35 +02:00
1f66d7becb
make it easy to test (revert when ready)
2023-01-30 17:14:24 +02:00
d0d7a483a1
replace old vid2frames import in args.py
2023-01-30 16:28:49 +02:00
c2d3ea3ca8
rename vid2frames.py to video_audio_utilities.py
...
more functions coming soon
2023-01-30 16:27:27 +02:00
2e04f7debf
Merge remote-tracking branch 'upstream/automatic1111-webui' into rife_standalone_buttons
2023-01-30 16:22:02 +02:00
54deb94030
fix rife failing when save_depthmaps = true
2023-01-30 16:18:25 +02:00
1a15fc7d55
add initial ffmpeg vid2frames
2023-01-30 15:56:08 +02:00
4b332cacc0
progress
2023-01-30 15:07:14 +02:00
6888574ac4
upgrade vid2frames part 1
2023-01-30 15:07:07 +02:00
20918f247b
todo comment
2023-01-30 14:40:04 +02:00
194ceaecc1
get access to root params
2023-01-30 14:38:21 +02:00
632fc37056
get input vid to interp fps
2023-01-30 12:27:55 +02:00
c6168cf4a7
Hybrid Video Update 2
...
This update fixes remap's border behavior when applying optical flow.
- I extended the function so it extends borders and recrops.
- obeys wrap/replicate setting, except that wrap is replaced with reflect101
Removed optical flow options that don't work unless you run contrib version of opencv (SF and DenseRLOF)
- functions remain for possible future use if I can figure out how to run both opencv's.
Added 'DIS Medium' optical flow, which a dense flow, similar to the two types that we can't run.
Added checkbox control for hybrid_motion_use_prev_img
- makes all motion, whether ransac or flow, compare against previous rendered frame rather than previous video frame
Added color_coherence_force_grayscale
- forces grayscale before and after generation, so that color coherence mode can still be used (like color matching against video), but the image will be forced to grayscale. (NOTE: actual image file is still RGB)
2023-01-29 17:15:15 -08:00
1e7c9cdcef
add positive and negative prompts to all prompts
2023-01-29 15:59:07 -08:00
c744149706
Update args.py
2023-01-30 01:17:29 +02:00
c5599bc939
proper vid upload box!
2023-01-30 01:15:16 +02:00
29011e747e
add initial 'upload mp4' button
2023-01-29 21:47:58 +02:00
14b92b4a7e
add "interpolate existing imgs/vids sub-accord
...
with a sample button
2023-01-29 21:36:41 +02:00
70357d1412
revert hybrid accord to old style
...
so it looks like the rest of the tabs. Will push a fix for the tab order in the near future too
2023-01-29 20:14:16 +02:00
1e54ca4b04
combine save_in_ram and skip_video to one line
2023-01-29 20:03:19 +02:00
a1debfea6b
shorter guided imgs tab + remove old commented linese
2023-01-29 19:58:04 +02:00
5fd7b1eba1
*much* smaller rife accord
2023-01-29 11:47:56 +02:00
b96bdaa2b0
remove comment
2023-01-29 02:06:39 +02:00
9ef21cca19
shorter rife accordion
2023-01-29 02:05:49 +02:00
ecd3920b24
remove unnecessary rife text from ui
...
it will fallback to save+keep the frames automatically if ffmpeg couldn't run properly.
a clear message explaining what's going on is showed to the user as well.
(the logic for all of the above is already implemented and in place)
2023-01-29 01:59:12 +02:00
689aaabeda
typo fix for rife error msg
2023-01-29 01:55:17 +02:00
710b8cb72b
Merge pull request #265 from deforum-art/seed_sch_change_default_val
...
match default seed_sch to frame_insertion's example
2023-01-29 02:19:54 +03:00
eb9e6554cf
fix duplicate perlin text
2023-01-29 01:08:18 +02:00
a3bf9d1e12
match default seed_sch to frame_insertion example
2023-01-29 01:05:08 +02:00
bfd9ec842a
swap noise dimensions
...
should adress #264
2023-01-29 01:58:37 +03:00
5def7ac996
Merge pull request #260 from hithereai/better_ui_and_cleanups
...
Better UI and cleanups v01
2023-01-29 00:28:18 +03:00
64f79d3b71
don't try to fetch masks with use_mask=False
2023-01-28 22:58:40 +02:00
1809be216a
add_noise is not tensor
2023-01-28 23:36:58 +03:00
cfa2f211e7
proper error when no internet and trying to download masks
2023-01-28 22:27:43 +02:00
6675451e13
same init img, shorter url
2023-01-28 21:23:34 +02:00
a1bb2baae8
same mask, shorter url
2023-01-28 21:07:04 +02:00
d1ae1775fc
royalti-free legal music in soundtrack_path
2023-01-28 20:46:12 +02:00
b51bcfdcea
better-looking video output tab
2023-01-28 20:43:10 +02:00
8dc7401db8
even better rife error msgs
2023-01-28 20:01:08 +02:00
e65893a12d
print rife vid path upon completion +
...
better error handling
2023-01-28 19:57:45 +02:00
73643347f1
Merge branch 'better_ui_and_cleanups' of https://github.com/hithereai/deforum-for-automatic1111-webui into better_ui_and_cleanups
2023-01-28 19:48:26 +02:00
89fbd2f48a
move reroll down the accordion
2023-01-28 19:48:12 +02:00
1276820ed8
Merge branch 'better_ui_and_cleanups' of https://github.com/hithereai/deforum-for-automatic1111-webui into pr/260
2023-01-28 20:44:19 +03:00
f1addd97b2
Merge branch 'automatic1111-webui' into pr/260
2023-01-28 20:44:04 +03:00
35e8e4866d
if unsharp amount is 0, simply return the image
2023-01-28 20:36:48 +03:00
b3c407a3ec
fix types
2023-01-28 20:36:18 +03:00
f4fa70a623
change sampler to euler_a
...
KLMS is a very bad sampler for deforum, esp with low step count, and 20-25 is a low step count
2023-01-28 19:35:45 +02:00
1873f11840
change steps 21 -> 25
2023-01-28 19:35:11 +02:00
f3ba5fcdcc
move 'Run from Settings file' accord down
2023-01-28 19:33:45 +02:00
e89db9e3c1
move 'Run from Settings file' down
2023-01-28 19:33:16 +02:00
d990941238
move anti-blur up
2023-01-28 19:32:01 +02:00
714fc11bcb
remove batch_settings accordion
...
+ move batch_name to main accordion
+ hide filename_format as it's doing nothing as of 28-1-23
2023-01-28 19:28:19 +02:00
81b75f7eb8
better sub-accordion name
2023-01-28 19:20:39 +02:00
6a9c099cbe
move ddimeta and tiling to "More options"
...
also revert compact as it looks better like this with the minimum amount of elements we have
2023-01-28 19:19:11 +02:00
bf58365440
move seed_extras to the bottom of accordion
2023-01-28 19:15:40 +02:00
9f432e6e88
better insert_frame text, order and errors
2023-01-28 19:13:29 +02:00
bab42b541f
halved-length URLs for insert_img example
2023-01-28 19:05:33 +02:00
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
hithereai
kabachuha
Matisse
reallybigname
Ryan Scarbery
rewbs