rbertus2000
|
01fb1bde8b
|
fix seed for parallel renders with filters applied
|
2022-10-19 23:16:51 +02:00 |
|
rbertus2000
|
d2d9c2dd0f
|
fixed corresponding txt file id
|
2022-10-19 01:17:44 +02:00 |
|
rbertus2000
|
4241fb9386
|
fixed img_id for parallel renders
|
2022-10-18 22:38:37 +02:00 |
|
cmdr2
|
83d6c3ba88
|
Fix the broken 'time remaining' counter
|
2022-10-18 16:12:17 +05:30 |
|
cmdr2
|
926e3e2712
|
Merge pull request #351 from madrang/fix-bug332
Force encoding to utf-8 on text file operations Fixes #332
|
2022-10-18 09:40:54 +05:30 |
|
Marc-Andre Ferland
|
5b0b582039
|
Force encoding to utf-8 on text file operations Fixes #332
|
2022-10-17 22:38:29 -04:00 |
|
Marc-Andre Ferland
|
ffe40fa3a3
|
Fixed file path bugs introduced by mistake and made img_id sequential based on time for better sorting of renders.
|
2022-10-17 21:27:15 -04:00 |
|
cmdr2
|
cb82170187
|
Fix the bug where custom models weren't getting picked up
|
2022-10-17 21:22:05 +05:30 |
|
Marc-Andre Ferland
|
cbdf03450d
|
Added timeout to critical locking tasks with matching exception
|
2022-10-15 05:31:17 -04:00 |
|
Marc-Andre Ferland
|
8fdb1e7ec9
|
Improved locking and logging when cleaning old cached sessions.
|
2022-10-15 04:39:45 -04:00 |
|
Marc-Andre Ferland
|
d3b28c42e6
|
Better error handling with cache.put
|
2022-10-15 04:08:17 -04:00 |
|
Marc-Andre Ferland
|
7de699c7fa
|
Moved a lot of code into task_manager.py
|
2022-10-15 03:28:20 -04:00 |
|
Marc-Andre Ferland
|
c7f6763c48
|
Runtime cleanup and moved apply_filters to it's own function
|
2022-10-14 23:20:57 -04:00 |
|
cmdr2
|
7ae70d5a4d
|
Don't delete the model variables twice
|
2022-10-08 13:58:44 +05:30 |
|
cmdr2
|
883dc72fc6
|
Unload the previous model while reloading
|
2022-10-08 13:19:18 +05:30 |
|
cmdr2
|
3b923e0d37
|
Didn't fix the ckpt bug properly
|
2022-10-08 12:48:37 +05:30 |
|
cmdr2
|
a208564f06
|
Wait for the model to load before changing the global 'model loaded' state
|
2022-10-08 12:35:23 +05:30 |
|
cmdr2
|
cec203a6db
|
Allow saving in jpeg or png format; Default to saving in jpeg
|
2022-10-06 15:05:34 +05:30 |
|
cmdr2
|
cf8bb9efb0
|
Don't reload the model when using an initial image; Work in half-precision for txt2img as well, no change in the output image noticed
|
2022-10-06 14:42:47 +05:30 |
|
cmdr2
|
201a053025
|
Support an arbitrary number of custom models, placed in the models/stable-diffusion folder. Shows an option in the UI to select which model to use
|
2022-10-06 14:28:02 +05:30 |
|
cmdr2
|
b4c68a8ae5
|
Save the negative prompt in the text file
|
2022-09-28 18:33:08 +05:30 |
|
cmdr2
|
008b4228d2
|
Support negative prompts. Credit for the approach: https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Negative-prompt
|
2022-09-27 19:41:21 +05:30 |
|
cmdr2
|
ca704e1d51
|
Revert "Merge pull request #250 from cmdr2/win-installer-no-activate"
This reverts commit 04eb356c89, reversing
changes made to 300159c03b.
|
2022-09-26 20:07:04 +05:30 |
|
cmdr2
|
b3e9b266fa
|
Use python 3.8.13 instead of 3.8.5, since 3.8.5 seems to be missing openssl in some pip repositories
|
2022-09-26 12:05:07 +05:30 |
|
cmdr2
|
661cf440f3
|
Remove debugging log
|
2022-09-24 14:11:26 +05:30 |
|
cmdr2
|
3822058daf
|
More debugging
|
2022-09-24 14:05:45 +05:30 |
|
cmdr2
|
9bb091d31e
|
Fix a bug where DDIM wouldn't get the correct steps from the UI after the first run
|
2022-09-23 21:22:44 +05:30 |
|
cmdr2
|
8cb340be9d
|
Merge branch 'main' into beta
|
2022-09-23 20:19:12 +05:30 |
|
cmdr2
|
5c827703a1
|
Report the steps for img2img correctly
|
2022-09-23 13:38:33 +05:30 |
|
cmdr2
|
a3de0820b3
|
Fix the 'Expected all tensors to be on the same device' error
|
2022-09-23 11:44:50 +05:30 |
|
cmdr2
|
83cb473a45
|
Fix the ddim_timesteps attribute missing error for txt2img with the ddim sampler
|
2022-09-23 11:14:06 +05:30 |
|
cmdr2
|
e7f9db5e56
|
Fix blurry img2img
|
2022-09-23 11:05:35 +05:30 |
|
cmdr2
|
c675caf3f9
|
Fix a missing ddim_steps error for the DDIM sampler
|
2022-09-23 00:54:35 +05:30 |
|
cmdr2
|
956b3d89db
|
New samplers for txt2img: "ddim", "plms", "heun", "euler", "euler_a", "dpm2", "dpm2_a", "lms"
|
2022-09-23 00:19:05 +05:30 |
|
cmdr2
|
7b520942dc
|
Update to the latest commit on basujindal's SD fork; More VRAM garbage-collection; Speed up live preview by displaying only every 5th step
|
2022-09-22 22:14:25 +05:30 |
|
cmdr2
|
f98225cdb6
|
Better errors when the server fails
|
2022-09-22 18:04:11 +05:30 |
|
cmdr2
|
f42eaaea86
|
Fix incorrect patch for env
|
2022-09-22 12:48:11 +05:30 |
|
cmdr2
|
bfdb74979f
|
Restrict to pandas 1.4.4, the new 1.5 version breaks the numpy dependency
|
2022-09-22 12:25:57 +05:30 |
|
cmdr2
|
7d12dbd4b2
|
Free up VRAM when possible
|
2022-09-21 21:53:25 +05:30 |
|
cmdr2
|
16c842366a
|
Don't apply filters if the user stops a task
|
2022-09-21 19:29:27 +05:30 |
|
cmdr2
|
18f452d968
|
Fix another bug with placeholder images; Move the logic for whether show_only_filtered is applied to the server
|
2022-09-21 17:41:42 +05:30 |
|
cmdr2
|
108e516b80
|
Don't use colorama
|
2022-09-16 21:32:08 +05:30 |
|
cmdr2
|
1c5097b81b
|
Hotfix for pywavelet version, attempt 1
|
2022-09-16 00:36:31 +05:30 |
|
cmdr2
|
7e7c110851
|
Image mask (inpainting)
|
2022-09-15 17:54:03 +05:30 |
|
cmdr2
|
27071cfa29
|
Live preview of images
|
2022-09-14 22:29:42 +05:30 |
|
cmdr2
|
9f48d5e5ff
|
Show the progress percentage while generating images
|
2022-09-14 16:52:03 +05:30 |
|
cmdr2
|
3b47eb3b07
|
Bug fix - tasks with an initial image were not resizing the initial image to the desired dimension
|
2022-09-14 11:36:55 +05:30 |
|
cmdr2
|
885759abc5
|
Return the image metadata and disk path in the response
|
2022-09-14 10:15:35 +05:30 |
|
cmdr2
|
e59c66ae26
|
Backend changes to support stopping a task mid-way. Uses a custom patch for the stable-diffusion codebase, to make it call a callback for DDIM
|
2022-09-13 19:59:41 +05:30 |
|
cmdr2
|
246ceebe0e
|
Merge branch 'main' into beta
|
2022-09-12 11:12:41 +05:30 |
|