abe26f4fdd
Changed callback function to an object. Added printing/saving of intermediate steps.
2022-09-24 10:49:10 -05:00
e47464d72d
Automate checking if value is number or expr
2022-09-24 12:59:20 +03:00
0913e8b944
Evaluate schedule parameters as functions of t
...
examples and troubleshooting at https://gist.github.com/kabachuha/5e165322382848114a59d2a855f49330
2022-09-24 01:39:53 +03:00
6fbfd19f05
fix dev branch by reverting
2022-09-21 19:41:42 -07:00
93fd972fe8
minor fixes sync py and ipynb fix change ui
2022-09-21 07:37:48 -07:00
b972bb1a4a
Merge pull request #65 from kabachuha/settings
...
Add custom settings import from file
2022-09-18 10:39:26 -05:00
79eb5436c0
Merge pull request #64 from kabachuha/main
...
Add perspective flipping to 2D animation mode
2022-09-17 21:25:37 -05:00
1e4eae6e97
Update: cv2-based frame unpacking (vid2frames)
...
Updated frames unpacking by cv2 with the option to overwrite / skip reunpacking.
overwrite option added under video_input settings.
2022-09-17 21:15:54 -04:00
96278d68e3
Add custom settings import from file
...
The file format is just the same as the settings dump, so you can feed your 20220908095753_settings.txt file generated after a run
2022-09-18 02:38:18 +03:00
927876517d
Merge pull request #63 from johnnypeck/main
...
Print some useful anim_args
2022-09-17 13:16:14 -05:00
4dea8dacae
Add perspective flipping to 2D animation mode
...
That way the camera angle can be adjusted for more dramatic compositions without enabling the 3D mode
2022-09-17 01:59:00 +03:00
ab3e80d251
Print some useful anim_args
...
Print some usefule anim_args
2022-09-13 02:20:27 -04:00
2ed011e10d
Prep dev branch for further development
2022-09-11 13:48:59 -05:00
a1f1632010
Minor patch
...
- small change to allow saving depths even with init video
- garbage collect and empty cuda cache at start of batch
2022-09-11 13:45:19 -05:00
1f4fa58a40
Update main repo to grab main branch of helpers
2022-09-11 11:54:41 -05:00
92263c9a2d
Hidden parameter: strength_0_no_init bool, force set strength to zero when no init image is being used
2022-09-11 00:10:34 -05:00
945f001fcc
Merge branch 'dev' of https://github.com/deforum/stable-diffusion into dev
2022-09-10 23:18:29 -05:00
ff3557b0a2
New secret setting use_alpha_as_mask to use the alpha channel of the init image as the mask
2022-09-10 23:10:23 -05:00
b8c7598009
Depth saving improvements
...
Make things more orthogonal. Depth saving now works even with depth warping off and in 2D mode. Special handling for first frame. Big ups to ScottieFox for testing help and bug reports!
2022-09-10 17:20:07 -05:00
cf95125226
Depth saving and updates
...
- Move depth inference to new file helpers/depth.py
- Merge depth stuff into new DepthModel class instead of passing around things separately
- New option to save the depth maps
- Use same depth map for warp of both prev and next for turbo
- Small fixes and clean ups
2022-09-10 14:28:00 -05:00
7ce3316dba
Fix to sanitize, clean up some unused imports and precision handling
2022-09-05 19:59:34 -05:00
a3d4320d4a
Support for turbo with 2D anims, resume support, compat with video init
2022-09-05 10:24:48 -05:00
76a32a1620
Turbo mode! diffusion_cadence param to diffuse every N frames
...
- run diffusion every N frames and do interpolation between trailing frames warped forward through time
- improves speed and coherence of animation videos
- supports just 3D at the moment
2022-09-03 17:56:58 -05:00
299fe5ae6b
Add files via upload
2022-09-02 18:12:17 -07:00
4f8fe15ccf
v0.3
2022-09-02 18:10:41 -07:00
1c0afbf103
change version and branch
2022-09-02 18:08:38 -07:00
bed13ed034
QoL changes
2022-09-02 17:58:53 -07:00
0f39e28dcc
Merge branch 'dev' of https://github.com/deforum/stable-diffusion into dev
2022-09-02 11:21:32 -05:00
2ca25f255a
During batches it will only clear the output at multiples of 32
2022-09-02 11:21:25 -05:00
f59357af56
Merge branch 'dev' of https://github.com/pharmapsychotic/stable-diffusion into dev
2022-09-02 10:48:54 -05:00
3c37400b64
Updated pinned pip dependencies to default versions on Colab runtime
...
Also add matplotlib which AdaBins uses in utils and remove CFGDenoiser from main notebook since it has moved to helper library.
2022-09-02 10:48:51 -05:00
ca945acd8f
Merge branch 'deforum:dev' into dev
2022-09-01 21:31:13 -05:00
78cb0e00b4
.
2022-09-01 21:28:07 -05:00
3ad6c0c826
3D animation and depth warping!
...
- bring in AdaBins, MiDaS, and pytorch3d-lite
- parallel anim_frame_warp_2d and anim_frame_warp_3d for 2D and 3D frame transformations
- transform_image_3d adapted from disco and optimized: eliminate round trips to disk, eliminate extra movement of tensors between cpu and gpu, avoid unnecessary trips through PIL and back
- move the *_series variables out of global scope and into DeformAnimKeys object
2022-09-01 19:16:59 -05:00
9487b60abf
add prompt print statement
2022-09-01 09:15:47 -07:00
63d00e125f
Prepared for dev branch
2022-08-31 15:49:32 -05:00
7eb1d8d593
Brightness/contrast adjustments to mask image.
2022-08-31 15:47:12 -05:00
e5f4b8383c
Merge branch 'dev' of https://github.com/deforum/stable-diffusion into inpainting_1.0
2022-08-31 00:30:44 -05:00
04b56c84a1
Added a new ddim discretization method called fill that fixes out of bounds errors. Embracing k-diffusion sigmas for the mask schedule
2022-08-31 00:29:49 -05:00
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
aec7d58c76
Merge branch 'dev' of https://github.com/deforum/stable-diffusion into inpainting_1.0
2022-08-30 11:06:07 -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
6569c1619c
Fixed error when using k-diffusion and no init. PLMS runs without decode function
2022-08-29 22:35:39 -05:00
1b9f205e03
if check_sha256 and model_checkpoint != "custom":
2022-08-29 20:18:34 -07:00
15f1c48903
Merge branch 'dev' of https://github.com/deforum/stable-diffusion into inpainting_1.0
2022-08-29 18:03:21 -05:00
da2e4755a5
Merge branch 'dev' of https://github.com/deforum/stable-diffusion into inpainting_1.0
2022-08-29 17:43:07 -05:00
cbcda88a82
Clean up
2022-08-29 17:38:44 -05:00
a761290917
Indexing errors fixed when masking. Default mask image added.
2022-08-29 16:33:32 -05:00
78dbba6b46
Color match modes for none, rgb, hsv, lab
2022-08-29 13:57:21 -05:00
695431b51d
changing git clone to deforum inpainting repo
2022-08-29 13:36:18 -05:00
fe8810319b
Fixed missmatching steps. Strength can be used without an init image.
2022-08-29 13:18:17 -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
8531bfaafa
Removed masked_noise_modifier from args
2022-08-29 11:28:54 -05:00
242dd6db4a
Inpainting method added
2022-08-29 11:28:48 -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
eacae5f0d6
Fix for Google Colab ui showing "self." on all the args
2022-08-23 16:58:12 -05:00
dc6cd1a6f6
Add files via upload
2022-08-23 13:11:28 -07:00
enzymezoo-code
kabachuha
deforum
deforum
enzymezoo-code
Bardia Shahrestani
Johnny Peck
pharmapsychotic
pharmapsychotic
viztopia
aredden
thibaudart
Thor
unknown