e13e0e45fb
fixup prompts param name
2022-12-20 21:15:53 +03:00
9fdb78f122
Save prompts for batch settings
...
Save prompts for batch settings
2022-12-20 06:48:53 -07:00
2c2cc25681
Add support for reading parseq manifest from a remote URL.
2022-12-20 16:56:08 +11:00
b3ac894ebc
kernel size to int
2022-12-20 00:30:26 +03:00
64dbc9649e
fixup reroll dropdown loading from file
...
fixup reroll dropdown loading from file
38th html block fix
2022-12-20 00:26:33 +03:00
78ed389bbb
anti-blur
...
using unsharp mask, from #74
2022-12-19 23:51:00 +03:00
1dcd214623
cadence to number instead of slider
2022-12-19 23:27:40 +03:00
07229b44a0
blank frames reroll model fix from pr74
2022-12-19 23:25:23 +03:00
f99ffe7410
add blank frames reroll
2022-12-19 23:14:21 +03:00
10d4d46086
Merge branch 'deforum-art:automatic1111-webui' into frame-insertion
2022-12-19 10:41:20 -08:00
a4c42e58b1
Merge pull request #156 from phi-line/always-load-midas
...
Always load the midas model on predict_depths
2022-12-19 02:54:05 +03:00
e22d6edc57
Always load the midas model on predict_depths
...
Before, the midas model would only be loaded if the midas_weight
was 1.0 or higher. With this change, we sync the logic between the
main deforum-stable-diffusion v.6 repo and this one.
2022-12-18 13:25:18 -08:00
4a94690fae
fix resume issue w/ depth maps saved in output dir
...
Before, the depth maps would interfere with counting of the number
of frames. This change includes filenames that contain the resume
timestring, but does not include those that are depth maps.
2022-12-18 12:52:37 -08:00
3ff1149173
a better scalable way for the prev commit
2022-12-18 19:43:01 +03:00
0ede3a83da
detach 'deforum_helpers' from 'scripts'
...
Should prevent "No module named 'scripts.deforum_helpers'" error causing Deforum's tab not show up in some cases when you've might've broken the environment with webui packages updates
2022-12-18 19:23:46 +03:00
bf2eed031e
allow for frames to be inserted on any speed > 20
2022-12-17 09:09:26 -08:00
525f6077a8
Merge branch 'deforum-art:automatic1111-webui' into frame-insertion
2022-12-13 10:32:10 -08:00
a5b4b27e66
Merge from master
2022-12-13 15:32:18 +11:00
0542082ccf
Merge from master
2022-12-13 15:21:27 +11:00
535c203b2b
Cleaning up printouts and line numbering
2022-12-12 10:38:32 -08:00
601332c0f8
allowing as many frames as wanted, no 200 lock
2022-12-12 10:28:30 -08:00
992f4b0763
initial form of infinite loop
2022-12-12 09:38:53 -08:00
7b4d7d7eb1
get closer to notebook
2022-12-10 19:09:50 -07:00
0d15fb0c8d
get closer to notebook
2022-12-10 19:09:20 -07:00
f2fd6d553b
get closer to notebook
2022-12-10 19:08:40 -07:00
ff1769dab5
Merge pull request #111 from Funofabot/full-precision-midas
...
Full precision midas
2022-12-08 22:25:54 +03:00
c4b9bf6197
Added state.interrupted to vid2frames
2022-12-07 18:41:52 -07:00
17e7d81766
Update render.py
2022-12-07 18:29:51 -07:00
f37a670c3c
Added import function
2022-12-07 18:25:07 -07:00
cf7f681032
Changed next frame init for video
2022-12-07 18:23:58 -07:00
8466fff816
Fix less frames in mask than init video
...
Fix less frames in mask than init video
2022-12-07 18:21:31 -07:00
8920126faa
Add import
2022-12-07 18:14:20 -07:00
b68146d543
Update vid2frames
...
Changed the way that vid2frames reports problems
vid2frames addresses pathing errors
vid2frames checks if setting are changed.
vid2frames has input name + frame#
2022-12-07 18:12:32 -07:00
1f32a9d52b
Change convert to tensor.
2022-12-07 18:06:39 -07:00
8961efac9a
As discussed in https://github.com/deforum-art/deforum-for-automatic1111-webui/pull/112\#issuecomment-1333896001 , add option for histogram matching.
2022-12-05 12:56:12 +11:00
3ee58dc5ad
Update depth.py
2022-12-02 08:19:42 -05:00
78d0b5615d
add checksum for downloaded models
2022-11-30 20:27:02 -05:00
a05d9341f7
changes where code diverges from defourm main
2022-11-27 09:24:21 -07:00
9a5764cff4
Update render.py
2022-11-24 06:12:48 -07:00
dda94f75ca
Update depth.py
2022-11-24 06:11:18 -07:00
8f00e8b262
Update render.py
...
fix for midas fp32
2022-11-24 06:01:30 -07:00
0491256d16
Update depth.py
...
fixing not able to use fp32
2022-11-24 05:56:08 -07:00
34cc81a32b
Don't require toggle to enable pseudo-3D anim. Don't use deltas for fv.
2022-11-24 13:24:32 +11:00
44070d0fb7
sampler index -> sampler name (due to webui's api change)
...
Adapt to a1111 change to expect sampler name rather than sampler index (fix #102 )
2022-11-23 23:08:29 +03:00
2753859268
Ensure subseed and subseed_strength are correctly honouring in internal processing
2022-11-23 16:35:01 +11:00
66136300ba
Merge branch 'fix-to-use-sampler-name' into parseq-integration
2022-11-23 15:45:24 +11:00
954777dbde
Adapt to A1111 change to expect sampler name rather than sampler index ( cdc8020d13)
2022-11-23 15:26:39 +11:00
f370e9067d
Allow interpolation mode to pick up Parseq seed and subseed declarations.
2022-11-23 15:22:46 +11:00
c8cfab82e4
Merge support for prompt interpolation
2022-11-23 11:18:31 +11:00
d16a8f1e4b
Ensure prompts are sorted numerically by keyframe.
2022-11-23 10:52:41 +11:00
25af0a6dfd
Add prompt interpolation animation mode (using composable diffusion)
2022-11-23 10:38:40 +11:00
2676133b46
Merge branch 'deforum-art:automatic1111-webui' into parseq-integration
2022-11-22 15:07:45 +11:00
6995a16f14
Update depth.py
...
replace wget code
2022-11-19 19:32:38 -05:00
45e77020ec
Update depth.py
...
convert midas_depth to a tensor before adding to adabins_depth
2022-11-13 13:48:41 -05:00
9e55c3fad3
Merge branch 'automatic1111-webui' into parseq-integration
2022-11-10 20:59:14 +11:00
ebad8b06dd
Fix overall Deforum progress bar when using Parseq
2022-11-10 02:02:04 +11:00
53e7b74797
move stuff to deforum_helpers to fix #76
2022-11-09 14:24:18 +03:00
183b331f4d
workaround/fix for apple silicon mps
...
Fixes #7
Co-Authored-By: julianko13 <30486126+julianko13@users.noreply.github.com>
2022-11-07 20:03:10 +03:00
12eff16070
Fix to fix for loading settings file without fill value.
2022-11-06 16:53:53 +11:00
ec78dedff9
Tolerate loading settings if no 'fill' value exists.
2022-11-06 14:19:45 +11:00
c90d02a06b
Move parseq to the bottom of the Keyframes tab.
2022-11-06 11:30:51 +11:00
1f60996220
Merge from master
2022-11-06 11:24:29 +11:00
a9c1a4729c
apple -> cherry not to get the wrong 'Apple'
2022-11-05 02:37:31 +03:00
8db624749f
fixup default prompts weighting
...
add brackets to suit automatic1111's weight format
2022-11-05 02:05:34 +03:00
9f3de6ae09
fixup
...
this series of commits fixes #59
2022-11-05 01:50:52 +03:00
ebc7417bfa
add hide video button
2022-11-05 01:40:02 +03:00
ea57979f14
fix mask fill mode settings loading
2022-11-05 01:39:31 +03:00
1db8688551
Clean up code
...
Removed comments related to masking work
Moved masking assignments to appropriate location
** The open question about shape is narrowed down to the mask image size, the init image size or args W,H **
Moving closer to the notebook
2022-11-04 00:58:37 -06:00
5ead341e61
Remove test code
2022-11-04 14:32:17 +11:00
1663c7dd19
Remove debug logging
2022-11-04 14:28:25 +11:00
0102aee8b9
Add support for delta values, fix save/load settings
2022-11-04 13:24:23 +11:00
8217a36998
Update generate.py
...
Revert to OP's assumption that we need image size. Still not convinced that the args.W and H are the correct answer but I want to make a point that I help with this little line of code.
2022-11-03 11:38:27 -06:00
8891c25f4d
More mask args
...
More mask args
2022-11-02 21:10:45 -06:00
ad06dc4a51
added function
...
added render_animation_with_video_mask
allows a mask video to be used when video init is not wanted.
The purpose is to be able to apply an animated masks when not using init video.
Work can be done to delete the old directory and replace it. Currently you have to delete mask frames independently. That will be for another session of fixes however.
2022-11-02 21:10:05 -06:00
3405569836
More masking arguments from img2img
...
More work with mask args.
function call to prepare_mask changed again with the addition of more available masking options.
These are some of the inpainting mask options.
2022-11-02 21:04:44 -06:00
0fa9407f2c
Additional mask args exposed
...
Added ui elements for some inpaint masking arguments.
2022-11-02 21:01:55 -06:00
5a8d7854d2
Add more masking arguments
...
Exposes some of img2img inpaint arguments to the init tab in Deforum.
Full res mask, full res padding, and fill action type.
Added the ability to use video mask without using video for init image. Just check the use video mask box.
2022-11-02 20:57:11 -06:00
8ca73e6882
Added mask_contrast_adjust arguments
...
Added mask_contrast_adjust arguments in appropriate locations.
2022-11-02 13:47:57 -06:00
c6488a66d5
Added mask_contrast_adjust arguments
...
Added mask_contrast_adjust arguments in appropriate locations
2022-11-02 13:47:07 -06:00
f2233a7930
Add argument for mask_contrast_adjust
...
Added argument for mask_contrast_adjust in appropriate locations.
2022-11-02 13:45:24 -06:00
d104536412
fixes for masking arguments
...
Returned call to prepare_mask to use mask args instead of constants that were used to get masking working initially.
2022-11-02 13:41:32 -06:00
e51fa8e7f1
Negative mask
...
needed to import PIL
2022-11-01 21:43:16 -06:00
449d74a15e
fix for masking
...
Comments added in changed lines of code as an explanation. #HOTFIXISSUE33 provides lookup to code that has been changed. Very simple fix for functionality which should not affect anything beyond masking.
2022-11-01 21:40:09 -06:00
8041097f9f
Ensure subseed and subseed strength are not ignored.
2022-11-02 13:37:41 +11:00
4b07ae5e65
Merge branch 'automatic1111-webui' of https://github.com/deforum-art/deforum-for-automatic1111-webui into parseq-integration
2022-11-02 10:30:48 +11:00
04eb7fff15
add a notice about 'Generate' until #53 is fixed
2022-11-01 17:13:23 +03:00
82a3708461
unreset sd_model
...
auto's webui now resets the sampler and the model after each generation for some reason resulting in #55 . This attempts to fix it
2022-11-01 16:51:44 +03:00
52f496ab24
add deforum-for-automatic1111-webui also to path
2022-11-01 16:44:41 +03:00
41a2cb5394
Don't force histogram matching. Add quick access to normal deforum anim series inside parseq datastructure (for debugging).
2022-10-29 00:16:58 +11:00
16490176ad
[wip] Initial support for mapping animation series from a Parseq manifest into Deforum. You can play with a UI that generates the manifest here: https://sd-parseq--staging-idlaaizi.web.app/ . Currently generates garbage from frame 2.
2022-10-28 16:25:32 +11:00
2f2bf94dda
ceil the steps count
2022-10-27 21:41:26 +03:00
6f7743e818
fixup
2022-10-27 21:13:15 +03:00
7713d4d329
fix args forwarding
2022-10-27 21:05:40 +03:00
cd662e4dc9
attempt to fix the progressbar
2022-10-27 20:56:05 +03:00
ccc1963fc4
fix cfg_scale for the first frame
2022-10-26 18:28:45 +03:00
3550312c46
deduplicate code
2022-10-26 18:28:27 +03:00
7a089c1344
move info and links under collapsible cell
2022-10-26 02:01:50 +03:00
10d7e37d27
fixed load settings button!
...
closes #23
2022-10-26 00:39:05 +03:00
053a94e46f
add warning
2022-10-24 19:35:47 +03:00
f960d2375b
fix json loading
2022-10-24 19:25:00 +03:00
62b013fdc6
finally fix in-ui load settings!
2022-10-24 17:27:00 +03:00
f97eb75f22
fix for subseed
2022-10-24 16:53:16 +03:00
0d5668048f
import gradio
2022-10-24 16:50:59 +03:00
fe7baed2b9
path fixup
2022-10-24 16:43:47 +03:00
65d031fc25
in-ui settings IO
2022-10-24 16:32:50 +03:00
330243415a
remove more of the useless margin
2022-10-24 15:15:04 +03:00
6dc6b8666e
make fov, near, far params keyframable
2022-10-24 15:07:14 +03:00
682c70f0c8
video settings dump fixup
2022-10-24 14:49:23 +03:00
a6d803a146
save video settings
2022-10-24 14:25:50 +03:00
63d66c39f6
increase default noise schedule for better details
2022-10-24 14:04:18 +03:00
8a84c19516
remove extra margins
2022-10-24 14:01:39 +03:00
5eb5029411
add math-less negative prompt example
2022-10-24 13:58:08 +03:00
5a0a8a8de9
deprecate the script in favor of extension format
2022-10-24 13:57:47 +03:00
c54e7f6876
hide 'prompts' to avoid confusion
2022-10-24 13:17:41 +03:00
4daf9ae437
hide the buttons while they're unused
2022-10-24 03:53:07 +03:00
9872d5a65c
info display fixup
2022-10-24 03:42:58 +03:00
a6b4886808
run animation in extension
2022-10-24 03:41:09 +03:00
89130497e0
wrap the submit function
2022-10-24 02:53:49 +03:00
dc175f53a4
add subseed
2022-10-24 01:54:34 +03:00
97d3dad97e
fixup shared
2022-10-24 01:52:23 +03:00
2ecb80a0ed
arghs!
2022-10-24 01:50:45 +03:00
a29490e97b
var name fixup
2022-10-24 01:49:16 +03:00
77ec26db1a
add more args from webui
2022-10-24 01:43:32 +03:00
ec8756a97d
moving closer to extension launch
2022-10-24 00:29:14 +03:00
b7de563d35
test if the button works
2022-10-23 23:25:53 +03:00
2c3237fbf0
move to javascript
2022-10-23 23:08:48 +03:00
b4707a4066
add progressbar and other stuff
...
also move stuff around so script.js fits within the dir
2022-10-23 22:46:04 +03:00
393620b08c
Delete scripts directory
2022-10-05 10:09:26 -07:00
a1fbe55f85
Set model to half
...
Set model to half in txt2img and img2img for less memory usage.
2022-09-06 09:09:49 +02:00
69ae4b35e0
Release under CreativeML Open RAIL M License
...
Update license, readme, models, model card, requirements and sampling
script.
2022-08-22 16:57:55 +00:00
673b0ab3a3
update safety model id
2022-08-22 16:11:52 +00:00
b9851783e5
fix to numpy
2022-08-19 17:14:29 +00:00
239ed0fd02
fix more
2022-08-19 17:09:41 +00:00
f3f60fccc3
correct merg
2022-08-19 17:08:10 +00:00
eef5da90db
finish
2022-08-19 17:05:39 +00:00
536eb1a8ba
Apply suggestions from code review
2022-08-19 18:03:22 +02:00
d0c714ae4a
[Safety Checker] Add Safety Checker Module
2022-08-19 16:01:56 +00:00
2ff270f4e0
stable diffusion
2022-08-10 16:30:49 +02:00
171cf29fb5
add configs for training unconditional/class-conditional ldms
2021-12-22 15:57:23 +01:00
32a9661b4e
add inpainting model
2021-12-21 11:35:45 +00:00
e66308c7f2
add code
2021-12-21 03:23:41 +01:00
kabachuha
Funofabot
rewbs
Matisse
kishan
Zarxrax
deforum
Doggettx
Patrick Esser
Patrick von Platen
Robin Rombach
ablattmann