94d21c95b7
fixed colors drifting during redo and optical flow redo
...
I just forgot that color would drift during repeated generations. Fixed. Now it's really consistent... and redo is incredible.
2023-03-17 09:34:46 -07:00
0c1440b80b
Added Diffusion Redo feature
...
Added slider for diffusion redo.
- llterally does a diffusion multiple extra times, feeding it back into itself. It is suggested to turn steps down if you turn redo up.
- while redoing, seed is randomized and restored
- fixed Optical Flow Redo so that it also randomizes and restores the seed, making it less muddy.
2023-03-17 08:48:55 -07:00
649472d200
Fixed mistake
...
accidentally removed this crucial division! all better
2023-03-16 23:56:20 -07:00
e1ddff8747
Hybrid Video Update
...
- Adds DIS Fine mode, and sets it as the new default
- Optical flow cadence and optical flow redo generation will now use DIS Fine, for pixel accuracy
- Adds flow guidance to hybrid flow. No setting needed, it just happens automatically, assisting the flow calculation by feeding in the last flow.
- Adds flow_factor_schedule for hybrid flow
- reduced some code for bordermode by setting a variable for the cv2 border mode translated from the user setting
2023-03-16 23:32:15 -07:00
3d008badbd
Fixed PIL version conflict
...
- replaced Image,Resampling.LANCZOS with PIL.Image.LANCZOS
- had to add import PIL
- had heard of people on colab encountering this issue. Should fix both hybrid video and image/video color matching.
- tested, works fine locally, so I see no reason not to change
2023-03-16 04:45:39 -07:00
55aebfd032
prevent color match on strength 0 if using Video or Image color coherence
...
Follow up to strength 0 color match reset... prevents color match sample being replaced when strength goes to 0 if using color coherence Video or color coherence Image.
2023-03-16 02:40:07 -07:00
e0a4337d8b
Added Optical flow redo generation
...
Option works in 2D/3D mode
Does a disposable generation before the actual generation to get the flow between previous image and the generation. Then, it discards that generation and warps the init_sample based on the captured flow before the actual generation happens.
- Takes twice as long (obviously)
- It can introduce smoothing, especially over time, but also adds a type of artistic consistency between frames.
- can be mixed and matched with any other modes, optical flow cadence, video, etc...
2023-03-16 01:39:41 -07:00
df3071c3b4
Added color_coherence 'Image'
...
You can now color match against an image!
- the one caveat is that normal color matching is done with the prev_img. There is no prev_img for the 1st frame, so I had to force the color match on the output rather than the input. It makes the first frame look sharpened at times, since the histogram is forced on it.
I also fixed video color coherence
- I realized that it was never color matching on the first frame for video. You usually just wouldn't notice, since you're using the video.
- I also realized it was one frame off, fixed.
2023-03-14 14:39:44 -07:00
2366bfdb47
use strength schedule in video input
...
closes #455
2023-03-14 15:24:16 +03:00
07760403e1
fixup
2023-03-14 00:16:04 +03:00
89b46124d4
auto-set the needed args for the GI mode
2023-03-13 22:51:11 +03:00
d4a48b1e0a
re-add matisse's changes
2023-03-13 22:22:22 +03:00
4e827e7c81
Merge remote-tracking branch 'upstream/automatic1111-webui' into pr/452
2023-03-13 17:01:27 +02:00
60fcc288e5
fix for color match sample incorrect colors
...
Once I tried some different images I realized that the color balance was RGB/BGR swapped on the color matches. Ooops! This fixes it. Perfect color matching after strength 0.
2023-03-13 06:54:04 -07:00
bb3b7bbd72
Fix for optical flow cadence on strength 0
...
I wasn't thinking about it quite right before, and I was cancelling the wrong cadence section based on strength 0. This repairs it.
It now looks at the proper strength key (from the tween frame_start_idx) to see if strength is 0 and skip optical flow cadence if it is.
Also, fixes and condenses the reporting of whether it's a cadence frame or an optical flow cadence by combining the info with the tween reporting.
2023-03-13 06:04:17 -07:00
48027d11ed
Fixed color match and optical flow on strength 0
...
I made cadence skip optical flow on frames with strength 0. This won't actually help you unless your cadence start is aligned perfectly with your strength 0.
Made strength 0 reset color match, as if it were the first frame in an animation.
I plan to make a scene change schedule, at which point I can add a strength threshold value for scene changes and replace this code.
2023-03-12 21:53:27 -07:00
f06c222ba7
Merge remote-tracking branch 'upstream/automatic1111-webui' into some_tests_12_03_23
2023-03-13 01:40:08 +02:00
e67339c837
change order to align with other new lines of code
2023-03-13 01:38:05 +02:00
4387ab586d
fix wrong cli printing when not in 3d mode
2023-03-13 01:36:06 +02:00
a3ed3a2a5b
Disabled optical flow cadence in 2D mode
...
I'll have to do some more work to track down a method to warp the flow properly in 2D mode. For now, optical flow cadence is a 3D only thing.
Made it say Optical flow cadence (3D only)
Made it hidden by default
Made it show when you switch to 3D mode
Made it not do the routines on the back end if not in 3D mode
2023-03-12 15:44:48 -07:00
04537641de
auto disable "with img2img do exactly x steps" from general settings
2023-03-12 23:50:37 +02:00
368e471dd8
clean code
2023-03-12 23:35:04 +02:00
71e38815c6
add noise_multiplier scheduling
2023-03-12 23:29:37 +02:00
652bda9e61
drop the last frame if using video mask
2023-03-12 19:13:29 +03:00
60b186e664
Merge branch 'main-mask' of https://github.com/deforum-art/deforum-for-automatic1111-webui into main-mask
2023-03-11 23:28:08 +03:00
caeb0204f4
fix masks not moving
2023-03-11 23:27:59 +03:00
52500d0a0f
Merge remote-tracking branch 'upstream/automatic1111-webui' into main-mask
2023-03-11 22:24:39 +02:00
651ddb9358
Improvement to optical flow cadence
...
slight changes, big improvement
2023-03-11 00:54:52 -08:00
6b28bfc65b
Merge remote-tracking branch 'upstream/automatic1111-webui' into main-mask
2023-03-10 19:07:54 +02:00
2de505e915
Merge remote-tracking branch 'upstream/automatic1111-webui' into pr/443
2023-03-10 11:32:21 +02:00
7a6d814332
revert try 1
2023-03-10 09:26:17 +02:00
37a58a556f
another code clean
2023-03-10 00:04:33 +02:00
79183f8d7c
clean code
2023-03-09 23:57:35 +02:00
7e0110a954
add cli printing before in-between cadence frames
2023-03-09 23:51:29 +02:00
db003c5c97
Merge branch 'automatic1111-webui' of https://github.com/reallybigname/deforum-for-automatic1111-webui into automatic1111-webui
2023-03-09 08:26:22 -08:00
0c8b8e0aff
added optical flow cadence
...
optional checkbox to include optical flow in normal cadence
-starts by getting flow between turbo_prev_image and turbo_next_image.
- after getting the flow, it warps the turbo_next_image with negative flow to match prev
- then, normal image warping during cadence happens
- then it warps the flow field to match the animation, first converting it to relative for warp, then back to absolute flow
- I calculate the flow division for each tween value and divide that by two.
- it then applies that tweened flow to the prev and next image
2023-03-09 08:25:56 -08:00
d209157ad7
use only one mask preset
...
fixes "There is a bug where it is checking the mask_file path for no good reason, when it should only be using video masks" in #386
2023-03-09 13:11:54 +03:00
19aeaa627d
Adding max_f and math to interpolation mode
2023-03-09 00:22:03 -08:00
c91d8b7dfe
Merge remote-tracking branch 'upstream/automatic1111-webui' into automatic1111-webui
2023-03-08 13:24:51 -08:00
61975f68ac
add saving of pos and neg prompts to anim_run sett file
2023-03-08 22:45:33 +02:00
6fe8927499
fix missing prompts in save_settings_from_animation_run(
2023-03-08 22:05:24 +02:00
33b574f776
Merge remote-tracking branch 'upstream/automatic1111-webui' into pr/420
2023-03-07 21:52:36 +02:00
517c45b484
Merge remote-tracking branch 'upstream/automatic1111-webui' into pr/420
2023-03-07 19:28:07 +02:00
1eb345d5a0
done? handle saving when running animations
2023-03-07 18:12:16 +02:00
e8466b6bc2
Merge pull request #427 from hithereai/align_%09d_filenames
...
Align img filenames to be of length %09d.extension
2023-03-06 23:12:04 +03:00
acb9012f21
fix video input not using input frames with negative prompt present
2023-03-05 23:35:14 +02:00
6e255f97c8
align img filenames to be of length 09.extension
2023-03-05 22:30:22 +02:00
46577bd3aa
Merge remote-tracking branch 'upstream/automatic1111-webui' into automatic1111-webui
2023-03-05 00:25:08 -08:00
177ec8aa1b
Revert "Merge remote-tracking branch 'upstream/automatic1111-webui' into automatic1111-webui"
...
This reverts commit c14e03f0aa80546752b3
2023-03-03 23:49:33 -08:00
1e91c01f57
Revert "reimplementation of max_f and t"
...
This reverts commit b222ca54f9
2023-03-03 23:48:42 -08:00
b222ca54f9
reimplementation of max_f and t
2023-03-03 23:47:45 -08:00
fde2ea6cf6
p
2023-03-04 04:15:47 +02:00
37a5665363
clean
2023-03-04 04:07:38 +02:00
415a544c94
Merge remote-tracking branch 'upstream/automatic1111-webui' into combine_cli_tables
2023-03-04 03:54:50 +02:00
686ea3c71e
Revert "Merge pull request #410 from MatissesProjects/automatic1111-webui"
...
This reverts commit 5ab8cb21f617692459e9
2023-03-04 03:50:57 +02:00
9da7930ead
Revert "Merge pull request #416 from MatissesProjects/automatic1111-webui"
...
This reverts commit 37d3e210f15016fb3163
2023-03-04 03:50:36 +02:00
96b24b3b36
Merge remote-tracking branch 'upstream/automatic1111-webui' into combine_cli_tables
2023-03-04 03:06:59 +02:00
1a86431098
initial
2023-03-04 03:00:39 +02:00
f4f8518906
so much for the pretty 1 liner haha
2023-03-03 16:16:47 -08:00
007ceb6e4d
fix for prompt now showing fully in cli
2023-03-03 15:42:29 -08:00
1558d17062
initial combine cli tables to one
2023-03-04 01:39:53 +02:00
ed38f9a202
Merge remote-tracking branch 'upstream/automatic1111-webui' into automatic1111-webui
2023-03-02 23:54:36 -08:00
e8cfb5039f
Merge remote-tracking branch 'upstream/automatic1111-webui' into pr/408
2023-03-02 01:39:56 +02:00
19a92fa6e2
adding back midas changes
2023-03-01 14:55:37 -08:00
23c0863ddf
attempt 2
...
added s & max_f. Variable schedule planner, and prompt printout uses numbers instead of variables t/60 = .6 (at t=6)
2023-03-01 14:49:05 -08:00
0384fa29f6
Merge branch 'automatic1111-webui' into parseq-optional-prompts
2023-03-02 06:38:48 +11:00
ebcb75a0a7
Fix 'UnboundLocalError: local variable 'parseqName' referenced before assignment'. Allow Parseq to delegate prompt management back to Deforum. Summary table in console showing who's doing what between Deforum & Parseq. Initial unit test.
2023-03-02 06:36:33 +11:00
1a8e18e92f
Merge remote-tracking branch 'upstream/automatic1111-webui' into pr/405
2023-03-01 19:00:46 +02:00
83e9be7a77
Revert "Merge pull request #358 from MatissesProjects/automatic1111-webui"
...
This reverts commit ff7201b5a56215a44d79
2023-03-01 18:45:12 +02:00
eca026fefb
print aspect ratio in cli's table if it's not static 1 for the whole animation
2023-03-01 18:12:15 +02:00
285a98f375
fix missed midas_weight in depth predict calls
2023-02-27 12:11:44 +03:00
74fc34e37e
Revert "Revert "Merge pull request #339 from deforum-art/bad_apple!!""
...
This reverts commit 483a973e0a
2023-02-27 11:56:23 +03:00
483a973e0a
Revert "Merge pull request #339 from deforum-art/bad_apple!!"
...
This reverts commit 6215a44d7927b508bd42
2023-02-27 00:58:47 +02:00
cf0872ecae
Merge branch 'automatic1111-webui' of https://github.com/MatissesProjects/deforum-extensions into pr/358
2023-02-26 18:16:05 +03:00
1b7a78af1d
Merge branch 'automatic1111-webui' into pr/358
2023-02-26 18:15:53 +03:00
513d6b7b65
Merge branch 'automatic1111-webui' into bad_apple!!
2023-02-26 13:57:45 +03:00
6297e84a98
small cleanup, seems easier to understand
2023-02-25 17:45:59 -08:00
12d01950d8
adding max_f into prompt setup
2023-02-25 17:24:54 -08:00
bca9cb0cd5
fix ) not showing up on where
...
this is due to it being not appended previously, now we can!
2023-02-25 16:34:05 -08:00
1943459b99
Merge branch 'deforum-art:automatic1111-webui' into automatic1111-webui
2023-02-25 15:30:29 -08:00
07be6b01ed
Fixed issue that prevented resume when using video mask
...
- unsharp_mask function was calling args.mask_image when mask_image is a local var at that point
- then, I realized that the routine shouldn't even be called if the amount is 0, so I added an if amount > 0 statement.
2023-02-24 14:02:09 -08:00
f6c581e8c0
fix video mask loading
...
works with totally blank mask frames too
closes #89 and closes #281
2023-02-24 14:54:11 +03:00
43b1e863be
Merge remote-tracking branch 'upstream/automatic1111-webui' into pr/358
2023-02-23 23:11:21 +02:00
d4f1fc9b7e
Merge remote-tracking branch 'upstream/automatic1111-webui' into pr/358
2023-02-20 09:13:46 +02:00
077c769890
resolving variables in the prompts for cli
2023-02-19 22:25:16 -08:00
b6accfe79c
move parsing into class. r to seed passed
2023-02-19 22:23:02 -08:00
434b29cef4
redirect to WIP conditional processing
2023-02-19 19:40:55 +03:00
af5171b004
unpack controlnet input vids
2023-02-19 19:26:20 +03:00
9d6c3fbbe9
pass controlnet args to renders
2023-02-19 18:35:09 +03:00
cecca529d6
Merge branch 'automatic1111-webui' into bad_apple!!
2023-02-19 13:18:13 +03:00
8044d45f47
wrap hijacking
2023-02-19 01:22:00 +03:00
b2dc72387e
ofc do these tricks only in 3D mode
2023-02-19 01:21:40 +03:00
7a39b4cab3
infer low vram depth mode from cmd opts
2023-02-19 01:08:41 +03:00
9c6bffe45b
option to unload main ckpt while getting depth
2023-02-18 23:38:27 +03:00
0d15d953c5
remove prettytable, move to rich tables instead, fix subseed val now showing in tables
2023-02-17 07:17:33 +02:00
bcf23c02db
add vid2depth
...
need fixing some thresh modes
2023-02-14 13:43:15 +03:00
16b1ce243c
finally, handle reg save sett when generating an animation
2023-02-12 20:17:43 +02:00
10b6d20b3b
Merge remote-tracking branch 'upstream/automatic1111-webui' into subseed_schds
2023-02-11 19:05:15 +02:00
85837a65e1
show neg prompt if given as sep field in cli (p1)
...
Interpolation cli printing is done in a diff file, will be changed soon as well.
No issues with updating this one ofc.
2023-02-11 18:25:18 +02:00
aa2f7de4dd
progress
2023-02-11 12:47:43 +02:00
365aac73b7
Update render.py
2023-02-10 22:37:06 +02:00
2ec90a75ef
done?
2023-02-10 22:30:13 +02:00
437a30bc81
Update render.py
2023-02-10 22:13:52 +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
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
5dea4577fd
initial commit
2023-02-10 02:27:08 +02:00
a69eb50395
fix video mask loading
...
closes #287
2023-02-07 12:43:03 +03:00
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
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
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
73f211371b
Merge branch 'automatic1111-webui' into pr/275
2023-02-01 22:49:59 +03:00
94b270ce7d
Merge remote-tracking branch 'upstream/automatic1111-webui' into rife_standalone_buttons
2023-02-01 01:20:16 +02:00
17e1d1aaa0
clipskip schedule
...
closes #188
2023-02-01 01:59:52 +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
c2d3ea3ca8
rename vid2frames.py to video_audio_utilities.py
...
more functions coming soon
2023-01-30 16:27:27 +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
64f79d3b71
don't try to fetch masks with use_mask=False
2023-01-28 22:58:40 +02:00
b3c407a3ec
fix types
2023-01-28 20:36:18 +03:00
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
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
c1ef1cc125
fixup word mask sample format
...
fixup
2023-01-28 16:33:56 +03:00
51b1e8d0c5
fixup
...
fixupx2
fixupx3
fixupx4
fixupx5
fixupx11
2023-01-28 16:06:14 +03:00
2d8fa220a2
Merge branch 'automatic1111-webui' into reduce-torch-cv2-conversions
2023-01-28 15:26:50 +03:00
3ae0103246
Merge branch 'automatic1111-webui' into masking-overhaul
2023-01-28 14:53:03 +03:00
4165fdedf4
no more redundant cv2 torch conversions in render
2023-01-28 02:09:44 +03:00
9c67bee3a6
remove return_sample
2023-01-28 01:58:39 +03:00
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
f940610716
sync the main branch and masking-overhaul
2023-01-25 22:26:02 +03:00
96a6329466
Merge remote-tracking branch 'upstream/automatic1111-webui' into frame-insertion
2023-01-24 15:09:59 -08:00
7bdf40734b
prevent overwriting of mask presets
...
instead of reloading them every frame
2023-01-24 20:11:19 +03:00
5974a15d1e
reset mask vals every frame
2023-01-24 19:28:24 +03:00
c10c98c894
add use_noise_mask to the args
2023-01-24 16:42:15 +03:00
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
e874b451bd
fixup imports
2023-01-22 15:18:05 +03:00
9ba8462efd
add defaults so the var keys are always found
2023-01-16 19:31:52 +03:00
reallybigname
kabachuha
hithereai
Matisse
rewbs
Ryan Scarbery