aeab8d8a9d
v0.2
2022-08-30 20:09:49 -07:00
09d78d50bf
Some cleanup of model config and load
...
- Group all setup cells in Setup section that can be collapsed
- Merge the model settings and model loading cells
- Remove unused code
- Use os.path.join
- No need to copy the yaml file around, use in place
2022-08-30 13:42:23 -05:00
cc122ea38f
Clear display with large batches, display grids when makin them.
2022-08-30 12:28:44 -05:00
3e02512265
Change color_coherence to default to LAB
...
Thanks to makeitrad for doing comparison tests!
2022-08-30 11:51:27 -05:00
6484022cde
change version
2022-08-30 08:36:06 -07:00
ff1fdabc38
add resume from timestring
2022-08-30 08:10:50 -07:00
3b2714dbcf
add resume animation
2022-08-29 22:10:25 -07:00
1b9f205e03
if check_sha256 and model_checkpoint != "custom":
2022-08-29 20:18:34 -07:00
cbcda88a82
Clean up
2022-08-29 17:38:44 -05:00
78dbba6b46
Color match modes for none, rgb, hsv, lab
2022-08-29 13:57:21 -05:00
356102dc3f
Merge branch 'dev' of https://github.com/deforum/stable-diffusion into dev
2022-08-29 13:01:20 -05:00
b3f21f660f
Restore defaults settings of anim mode None, prompts, and notebook name
2022-08-29 13:00:16 -05:00
c5aaf7688e
key framing interpolation
2022-08-28 17:12:00 -04:00
213491ab43
Adding strength/noise/scale schdules for animation
2022-08-28 13:48:44 -04:00
bd59516d40
Adding k-samplers file in helpers & colab convert script
2022-08-28 12:32:07 -04:00
0ed1c391a3
Update Deforum_Stable_Diffusion.py
2022-08-27 20:42:22 -07:00
8964516505
Update Deforum_Stable_Diffusion.py
2022-08-27 17:48:59 -07:00
fdadbf6afb
Add files via upload
2022-08-27 17:47:26 -07:00
80e868bd93
add grids, fix warning
2022-08-27 17:44:26 -07:00
46265de4fb
grid with loop inversion
2022-08-27 11:05:00 +02:00
78e86bd2b4
half precision toggle does not work with init
2022-08-26 22:19:12 -07:00
648b375dc2
fix link inits
2022-08-26 22:16:25 -07:00
d78bb699cc
Update Deforum_Stable_Diffusion.py
2022-08-26 19:42:14 -07:00
7bcae4a19c
Update Deforum_Stable_Diffusion.py
2022-08-26 19:40:51 -07:00
627af98f35
init_image batching
...
Batches init images by entering a directory path into the `init_image` variable instead of an image path (both methods can be used in the same paramater field).
It iterates over the `init_array` list that contains the image paths. If `use_init` is False, the list will countain an empty string so that it runs the prompts loop once without any initial images (so as if it would usually).
2022-08-27 01:10:21 +02:00
50a453ceaa
add half_precision
2022-08-26 14:58:14 -07:00
28f3735479
fix prompts in settings batchdir make2d add 4ema
2022-08-26 08:51:51 -07:00
220a71d076
Fixed Seed Interpolation
2022-08-26 10:48:47 -04:00
0b73a81bd1
Rename batchdir to batch_name, include in filename for image and video, use 5 digits for index/frame
...
Lots of differing opinions on preferences for filenames so we probably want a drop down with a few options in the future. For now match the v0.0 names more closely.
2022-08-25 21:17:10 -05:00
bb0feb7c6d
Move model section up to top by request
2022-08-25 18:58:02 -05:00
a16fff38e4
Border mode option for animations, lower default previous_frame_noise setting
2022-08-25 18:44:03 -05:00
3b9c7409c1
Continue video input merge, combine with main animation loop
2022-08-25 18:08:22 -05:00
43655f9b4c
Merge branch 'video_inits' of https://github.com/nonlethalart/stable-diffusion into nonlethalart-video_inits
2022-08-25 16:59:50 -05:00
1dafeb9ade
Color coherence for animations!
...
The model tends to drift towards purples and saturated colors. Stayed up late collaborating with the zippy twins and coming up with techniques to keep nice colors. This adds color_coherence setting with MatchFrame0 that maintains rgb and hsv histogram match to first frame. Also setting to add bit of noise each frame to keep new details coming. More options and modes coming!
Also put animation options in anim_args object and include them in settings.txt
2022-08-25 16:33:22 -05:00
2106ad4fc8
adding input video
2022-08-25 13:36:38 -07:00
b50d1b3c21
.
2022-08-24 13:23:23 -05:00
abb0c49f45
Support for inits and outputs of raw latent vector and sample tensors
...
This prevents repeated precision loss going out to 8bit per channel images while doing the video transforms.
2022-08-24 12:56:55 -05:00
e37533ad8b
Couple animation fixes and cell to create and preview mp4
2022-08-24 05:06:24 -05:00
ce54e9cd87
Code cleanup and 2D animations
2022-08-24 03:56:44 -05:00
b687b7cdcc
Update Deforum_Stable_Diffusion.py
2022-08-23 22:09:31 -07:00
28fc64d0c7
Update Deforum_Stable_Diffusion.py
2022-08-23 20:40:15 -07:00
80d06c4651
Add files via upload
2022-08-23 20:23:51 -07:00
6d49717fb2
Fix for colab restart runtime getting proper import paths
2022-08-23 22:10:29 -05:00
61ab1ccea1
Update Deforum_Stable_Diffusion.py
2022-08-23 20:02:00 -07:00
97bd8123ca
Add files via upload
2022-08-23 19:06:03 -07:00
3bf47ee32f
Add files via upload
2022-08-23 18:48:26 -07:00
e65787140e
Add files via upload
2022-08-23 18:35:09 -07:00
25313d9997
Add files via upload
2022-08-23 18:21:04 -07:00
e02bdd6290
Add files via upload
2022-08-23 18:10:58 -07:00
62174da269
Support for urls for init image, fix args.prompts issue
2022-08-23 18:06:14 -05:00
deforum
pharmapsychotic
viztopia
aredden
thibaudart
Thor
unknown