Craulback
5988532fc2
fix accidental deletion
2022-11-21 18:28:38 -07:00
Craulback
a5fd15e412
change max duration & frames math
2022-11-21 18:06:54 -07:00
Craulback
f47c9c6a82
stop at total_frames, up default fps when saving
2022-11-21 17:47:35 -07:00
ZeroCool940711
ef4cf8bc98
Added global negative prompt on config file.
2022-11-17 10:11:42 -07:00
ZeroCool940711
3736a35e26
Initial conversion of the sd_util.py file into a package with smaller modules in it.
2022-11-03 00:05:54 -07:00
fezeral
10b66cc2b9
Fixed errors when post-processing models aren't installed
...
Fixes #1522 , #1604
2022-11-01 17:26:47 +10:30
ZeroCool940711
2ea2606e83
Reverted txt2vid to use the StableDiffusionPipeline instead of StableDiffusionWalkPipeline when loading the model.
2022-10-31 06:50:21 -07:00
ZeroCool940711
928ce11b51
Changed text on the txt2vid to point people to Settings page where they can add their huggingface token.
2022-10-31 02:31:00 -07:00
ZeroCool940711
f52efdfcd6
Reduced the size of the first column on txt2img and txt2vid to have more available space.
2022-10-28 12:18:46 -07:00
ZeroCool940711
9d3d65fb5b
Moving text to video to the new stable diffusion videos pipeline.
2022-10-28 03:16:27 -07:00
Lucas Czernohorsky
aa3f92b611
floating suggestions area, first context sensitive responses (type by and get artist list), automated recognition of words "of, at, with" to not add a ",".
...
complex pattern matching support, to remove double "," and double text generation in general.
improved key phrase list.
full artist thumbnails support.
2022-10-26 12:42:48 +02:00
ZeroCool940711
ad5597b968
Allow users to set the preview frequency to 0 in case they need to disable it.
2022-10-24 12:35:30 -07:00
ZeroCool940711
cb501565c2
More renaming and changed to links related to the organization, docs and repo names.
2022-10-23 18:54:10 -07:00
ZeroCool940711
97eb1b169b
More renaming and changes to links related to the organization, docs an repo names.
2022-10-23 17:17:50 -07:00
ZeroCool940711
73fadb231f
Fixed links so they point to the new repo and organization names.
2022-10-23 16:22:40 -07:00
ZeroCool940711
b0c7bf0f2b
Fixed redundant backslash.
2022-10-23 15:13:18 -07:00
ZeroCool940711
883fae1501
Improved progress bar info on txt2vid and made sure the update_preview_frenquency worked correctly.
2022-10-23 14:56:00 -07:00
ZeroCool940711
c57b084b4c
Changed max frame to max duration in seconds for the stats on txt2vid
2022-10-23 11:35:54 -07:00
ZeroCool940711
ed0c5f5272
Added unique 16-17 character id to videos so they are not overridden when you create multiple videos with the same prompt and seed.
2022-10-23 03:12:14 -07:00
ZeroCool940711
a772b4c53d
Moved txt2vid to use diffusers custom interpolate_stable_diffusion pipeline instead of StableDiffusionPipeline.
...
- Added safety checker which is disabled by default.
2022-10-23 03:12:14 -07:00
ZeroCool940711
accc6f411e
Changed the default Stable Diffusion model to runwayml/stable-diffusion-v1-5
2022-10-20 19:53:09 -07:00
ZeroCool940711
b96a61be9f
Added default height value to the text are for the prompt on most tabs, this should help with it having the proper height, we still need to change min-height through CSS so it might still break sometimes.
2022-10-20 13:24:56 -07:00
ZeroCool940711
345ea8623f
Added implementation made by @NaMJaG for key phrase suggestions under the prompt.
2022-10-19 07:56:36 -07:00
ZeroCool940711
774073c8c3
Changed CFG scale to be a number_input instead of a slider.
2022-10-17 18:02:51 -07:00
ZeroCool940711
2fcad23c77
Replaced most if not all print statements with loguru to make the console output easier to understand and just look better overall.
2022-10-15 09:32:15 -07:00
ZeroCool940711
8d2cf46fbc
Added first implementation to support the stable horde bridge on the streamlit version.
2022-10-14 12:09:47 -07:00
ZeroCool940711
ffdcbb4504
Fixed issue with the do_loop option after it was removed.
2022-10-12 00:08:38 -07:00
ZeroCool940711
1bc6c9b6db
You can now change the optimized mode, float16 and no_half options without having to restart the app.
2022-10-10 20:45:37 -07:00
ZeroCool940711
84479d88b8
Changed the prompt text_input for a text_area and made it similar in size to the text input.
2022-10-09 03:21:06 -07:00
ZeroCool940711
63b2ff22c6
Added the ability to save the video during mid generation when we hit the stop button.
...
- Fixed GFPGAN not working on txt2vid.
2022-10-07 23:49:19 -07:00
ZeroCool940711
ac2d348f04
Fixed "expected scalar type Half but found Float" on txt2vid.
2022-10-07 20:32:02 -07:00
ZeroCool940711
45976077c0
Changed the image preview frequency field to only allow positive values.
2022-10-07 16:59:29 -07:00
ZeroCool940711
2fa1b07d6f
Changed txt2vid st.slider to st.number_input as its easier to use and more flexible than a slider.
2022-10-06 01:45:24 -07:00
hlky
cd700692eb
KeyError: 'pipe'
2022-10-05 05:29:10 +01:00
hlky
3851fcc537
model manager
...
model manager
2022-10-04 19:39:52 +01:00
ZeroCool940711
f866ffdad4
Fixed multiple settings and default values not working properly.
2022-10-02 21:25:41 -07:00
ZeroCool940711
393a695aef
Fixed LDSR, now it should work both txt2img and img2img
2022-10-02 20:26:01 -07:00
ZeroCool940711
7354c901d2
Fixed LDSR not working on txt2img and img2img.
...
- Removed the checkbox to disable the preview image, instead users should increase the frequency at which it is displayed if they have performance issues, after a certain point it no longer affects performance.
2022-10-02 13:10:17 -07:00
ZeroCool940711
0c03cedeb9
Added LDSR to the UI.
2022-10-01 20:18:09 -07:00
hlky
a3f94d3491
Update txt2vid.py
2022-10-02 00:52:53 +01:00
hlky
babf6c4fc0
Update txt2vid.py
2022-10-02 00:46:51 +01:00
hlky
4b6de58ae4
Update txt2vid.py
2022-10-02 00:27:58 +01:00
hlky
47e340dc2c
Update txt2vid.py
2022-10-01 23:59:50 +01:00
hlky
2a49c28980
docker / local cache paths
2022-10-01 22:50:40 +01:00
ZeroCool940711
625ba555e3
Fixed custom models not loading on txt2img, img2img and txt2vid.
2022-09-29 03:29:44 -07:00
ZeroCool940711
ae263cb55e
Made sure the txt2vid tab shows a loading animation when the models are loading.
2022-09-29 01:07:32 -07:00
Alejandro Gil
3e40bab7f7
Changed the default streamlit import for hydralit as we will be using hydralit as replacement for the default streamlit library, hydralit provides better control over css as well as having a lot more options. ( #1352 )
2022-09-28 09:33:54 -07:00
Alejandro Gil
519d7c661f
Added new implementation of the textual inversion page. ( #1342 )
2022-09-27 11:36:48 -07:00
ZeroCool
8f2ed2f350
Added message on the text to video tab for specifying how to add the huggingface token if its missing. ( #1339 )
...
# Checklist:
- [x] I have changed the base branch to `dev`
- [x] I have performed a self-review of my own code
- [x] I have commented my code in hard-to-understand areas
- [x] I have made corresponding changes to the documentation
2022-09-27 00:57:28 -07:00
ZeroCool
6db88c4673
Merge branch 'dev' into dev
2022-09-26 07:03:59 -07:00
