0491256d16
Update depth.py
...
fixing not able to use fp32
2022-11-24 05:56:08 -07:00
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
954777dbde
Adapt to A1111 change to expect sampler name rather than sampler index ( cdc8020d13)
2022-11-23 15:26:39 +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
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
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
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
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
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
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
Funofabot
kabachuha
rewbs
Zarxrax