holm/easydiffusion
1
0
Fork 0
forked from extern/easydiffusion
Code Issues Pull Requests Packages Projects Releases Wiki Activity
1,727 Commits 12 Branches 36 Tags 62 MiB
8faf6b9f52
Commit Graph

197 Commits

Author SHA1 Message Date
cmdr2
d79eb5e1a6 Typo 2022-11-14 11:51:56 +05:30
cmdr2
f6651b03b5 Workaround to run gfpgan on cuda:0 even if it's not enabled in the multi-gpu setup 2022-11-14 11:51:18 +05:30
cmdr2
5f880a179c Remove idle CPU unloading (when GPUs are active), because now a CPU can never be used along with GPUs 2022-11-14 11:24:30 +05:30
cmdr2
ea03fd22db Start on multiple GPUs by default (top 75 percentile by free_mem); UI selection for 'cpu' or 'auto' or a list of specific GPUs, which is now linked to the backend; Dynamically start/stop render threads for the devices, without requiring a full program restart 2022-11-14 11:23:22 +05:30
cmdr2
a19ba40672
Typo 2022-11-12 13:31:59 +05:30
cmdr2
3983cb001f
Save the VAE model to the metadata text file 2022-11-12 13:29:24 +05:30
Marc-Andre Ferland
aa21115e26 Always return a byte buffer. Sending the picture as URL text fails in some browsers. 2022-11-11 20:44:39 -05:00
cmdr2
a39f845835
current_vae_path needs to be global 2022-11-11 19:30:33 +05:30
cmdr2
3fdd8d91e2 Handle device init failures and record that as an error, if the GPU has less than 3 gb of VRAM 2022-11-11 16:13:27 +05:30
cmdr2
c13bccc7ae Fix the error where a device named 'None' would get assigned for incompatible GPUs 2022-11-11 15:43:20 +05:30
cmdr2
bd56795c62 Switch to using cuda:N instead of N (integer device ids) 2022-11-11 14:46:05 +05:30
cmdr2
b9a12d1562 Restrict device selection id to 'cpu' or integers (and 'auto' in the initial device selection functions) 2022-11-10 20:03:11 +05:30
cmdr2
058ce6fe82 UI-side changes for selecting multiple GPUs, and keeping the Use CPU option synchronized with the backend. This change isn't ready to be shipped, it still needs python-side changes to support the req.render_device config 2022-11-09 19:17:44 +05:30
cmdr2
8f1d214b12 Bring back CPU unloading of models when idle for a while (applies only when GPUs are present) 2022-11-08 19:23:35 +05:30
cmdr2
51fb1a43de Temporarily disable the idle CPU unloading behavior, since it's not clear whether it'll reload the model if a future request for the CPU is received after it has unloaded the model 2022-11-08 19:02:21 +05:30
cmdr2
9bc7521de0 Make custom VAE an Image Setting, rather than a System Setting; Don't load a VAE into memory by default 2022-11-08 16:54:15 +05:30
cmdr2
67cca3bc00 Print the devices for which rendering threads have started; Prettier print of the model data 2022-11-07 18:26:10 +05:30
cmdr2
90b1609d4e device_selection is already a string, since we've used string functions before this line 2022-11-07 18:08:43 +05:30
cmdr2
abbfae2fc0 Simplify the logic used for displaying the GFPGAN warning 2022-11-07 17:55:27 +05:30
JeLuF
59e4c1cf79 Sanitize session id's before using them as path components 2022-11-03 00:43:44 +01:00
Marc-Andre Ferland
b09b80933d Print device name on task start and complete to avoid doubt from users on what device selected the task. 2022-11-01 22:28:10 -04:00
cmdr2
053bce7a8e
Set the correct mimetype in the base64 image 2022-10-31 19:05:57 +05:30
Marc-Andre Ferland
eb596ba866 Allow start_render_thread to proceed faster in case of failure. 2022-10-30 06:04:06 -04:00
Marc-Andre Ferland
c687091ce9 Only return valid data for alive threads. 2022-10-30 01:38:32 -04:00
Marc-Andre Ferland
eb994716e6 Indentation... 2022-10-30 01:33:17 -04:00
Marc-Andre Ferland
099727d671 Added auto unload to CPU if GPUs are active. 2022-10-29 18:57:10 -04:00
Marc-Andre Ferland
6229cdb1ba Added a missing device_name 2022-10-29 17:47:45 -04:00
Marc-Andre Ferland
b7a663ed20 Implement complete device selection in the backend. 2022-10-29 17:34:53 -04:00
Marc-Andre Ferland
86da27a7a1 Moved wait outside lock and now returns false on failure. 2022-10-28 22:52:00 -04:00
Marc-Andre Ferland
fc2a6567da Moved import before use of runtime.thread_data.device 2022-10-28 22:51:04 -04:00
cmdr2
a8c16e39b8 Support custom VAE files; Use vae-ft-mse-840000-ema-pruned as the default VAE, which can be overridden by putting a .vae.pt file inside models/stable-diffusion with the same name as the ckpt model file. The UI / System Settings allows setting the default VAE model to use 2022-10-28 20:06:44 +05:30
Marc-Andre Ferland
26562e445f Set online after preload. Move ident to include in if check. 2022-10-28 04:09:34 -04:00
Marc-Andre Ferland
c52fc843f6 Comment... 2022-10-28 02:09:11 -04:00
Marc-Andre Ferland
02240bda25 Moved up to not duplicate if statement. 2022-10-28 02:05:48 -04:00
Marc-Andre Ferland
0185ef7c83 Apply force_full_precision if was set on device_select. 2022-10-28 02:02:09 -04:00
Marc-Andre Ferland
71c6beadb4 Only default to cpu on auto or current. 
Not when a specific device was requested.
 2022-10-28 01:09:38 -04:00
Marc-Andre Ferland
22a11769fa Enable preload on cpu when no other devices are alive. 2022-10-27 21:57:50 -04:00
Marc-Andre Ferland
7f4786f9dd Wait until device is fully ready before proceding. 2022-10-27 20:27:21 -04:00
cmdr2
0dfaf9159d Put back the check to only preload on GPU 2022-10-28 00:04:33 +05:30
cmdr2
389e3397ec Preload the model even in the CPU mode 2022-10-27 23:17:41 +05:30
cmdr2
284b95213e Fix a bug where the device wouldn't get set if no cuda-compatible hardware was found 2022-10-27 22:59:55 +05:30
cmdr2
952854f64e Revert 554650c18d 2022-10-27 22:59:17 +05:30
cmdr2
554650c18d Fix a bug where the device wouldn't get set if no cuda-compatible hardware was found 2022-10-27 22:51:45 +05:30
cmdr2
3fb5d886dc
Merge pull request #398 from madrang/mGpu-crashHandling 
mGpu crash handling
 2022-10-27 13:44:26 +05:30
Marc-Andre Ferland
d3df113fb0 When reduced_memory is True, on crash only move model back to Cpu. 2022-10-26 16:52:31 -04:00
Marc-Andre Ferland
06c2ab045a Fix TypeError: string indices must be integers 2022-10-26 16:14:29 -04:00
Marc-Andre Ferland
ae40b6ba8c Missed a is_alive check in the conversion. 2022-10-25 03:00:50 -04:00
Marc-Andre Ferland
c41baf3aeb Moved img_id creation inside save image loop. 2022-10-25 02:10:52 -04:00
Marc-Andre Ferland
fc875651d3 Removed unused vars 2022-10-23 05:00:21 -04:00
Marc-Andre Ferland
0d62123a0b Replaced missing gpu_name by device_name 2022-10-22 21:28:12 -04:00
Marc-Andre Ferland
8adf965d0b Formatting changes. 2022-10-22 19:02:02 -04:00
Marc-Andre Ferland
364e364429 Added get_cached_task to replace task_cache.tryGet in server.py 
Now updated cache TTL on /stream and temp images endpoints.
Keep images alive longer when browser keeps reading the endpoints.
 2022-10-22 13:52:13 -04:00
Marc-Andre Ferland
cd6d49860f Missing a 'r' in progress 2022-10-22 01:23:39 -04:00
Marc-Andre Ferland
8a10fcf7ea updated print statement. 2022-10-22 00:34:33 -04:00
Marc-Andre Ferland
3b5f96a133 Fixed stopping tasks and more cleaning. 2022-10-21 22:45:19 -04:00
Marc-Andre Ferland
ce2b711b1f Newlines... 2022-10-21 21:44:15 -04:00
Marc-Andre Ferland
7befa94e6d More comments and cleanup. 2022-10-21 20:56:24 -04:00
Marc-Andre Ferland
88ef1a3c5b Moved time before model.to 2022-10-21 20:22:34 -04:00
Marc-Andre Ferland
ccb7a553c2 Memory improvements 2022-10-21 19:34:29 -04:00
Marc-Andre Ferland
56ed4fe6f2 Fix VisualStudio Type Warning. 2022-10-21 01:30:49 -04:00
Marc-Andre Ferland
849d1d7ebd Merge branch 'beta' of https://github.com/cmdr2/stable-diffusion-ui.git into multi-gpu 
# Conflicts:
#	ui/media/js/main.js
#	ui/sd_internal/runtime.py
#	ui/server.py
 2022-10-20 20:08:23 -04:00
cmdr2
090dfff730 Refactor the time delays into constants and mention the units 2022-10-20 17:22:01 +05:30
cmdr2
9d16898926
Merge branch 'beta' into merge 2022-10-20 15:57:46 +05:30
rbertus2000
01fb1bde8b fix seed for parallel renders with filters applied 2022-10-19 23:16:51 +02:00
Marc-Andre Ferland
4e5ddca3bd Display the failure detail when there is one at that step. 
Was checking the json object, not the server response.
 2022-10-19 05:10:37 -04:00
Marc-Andre Ferland
3bdc90451a Dont preload on cpu. 2022-10-19 04:34:54 -04:00
Marc-Andre Ferland
21afe077d7 Removed Cpu from the devices allowed to run GFPGANer. 
Added clear error for the user.
 2022-10-19 03:02:26 -04:00
cmdr2
0922ba938c Remove unnecessary tabs 2022-10-19 09:59:18 +05:30
Marc-Andre Ferland
3fc66ec525 Removed empty lines left over from merge. 2022-10-19 00:27:51 -04:00
cmdr2
44191cd908 Merge pull request #357 from rbertus2000/beta 
fixed img_id for parallel renders
 2022-10-19 09:57:05 +05:30
Marc-Andre Ferland
0da0c6bd77 Merge branch 'beta' of https://github.com/cmdr2/stable-diffusion-ui.git into multi-gpu 2022-10-19 00:26:09 -04:00
Marc-Andre Ferland
6098b196dc Text header, comments and better validations. 2022-10-18 23:58:55 -04:00
Marc-Andre Ferland
53cdeeff03 More fixes to devices changing names. 2022-10-18 21:08:04 -04:00
Marc-Andre Ferland
fcdb086daf Fixed is_alive to work with devices that can change name after init. 2022-10-18 20:33:37 -04:00
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
Marc-Andre Ferland
cfd6751777 Merge branch 'beta' of https://github.com/cmdr2/stable-diffusion-ui.git into multi-gpu 2022-10-18 13:21:26 -04:00
Marc-Andre Ferland
5e461e9b6b Fixed is_alive with render_threads that can update the device name after starting. 2022-10-18 13:21:15 -04:00
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
578b3ba4f4 Force encoding to utf-8 on text file operations Fixes #332 
# Conflicts:
#	ui/server.py
 2022-10-17 23:15:36 -04:00
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
e24be913e5 Merge branch 'beta' into multi-gpu 2022-10-17 21:35:24 -04:00
Marc-Andre Ferland
4d3358ba66 Fixed file path bugs introduced by mistake and made img_id sequential based on time for better sorting of renders. 2022-10-17 21:29:14 -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
c92129ac63 Improved detection of missing cuda:0 and added warning to console about how to fix. 2022-10-17 03:32:23 -04:00
Marc-Andre Ferland
554b67a2f0 Fixing bug in is_alive. 2022-10-17 01:05:51 -04:00
Marc-Andre Ferland
012243a880 Process GPU tasks on CPU when there are no cuda devices at all. 2022-10-17 01:05:27 -04:00
Marc-Andre Ferland
d4a348a2b2 Process GFPGANer on cuda:0 when possible, otherwise use cpu. 2022-10-16 23:12:46 -04:00
Marc-Andre Ferland
41bfb96b6b Fixed bug in task_manager.is_alive and added way to check for first device. 2022-10-16 23:06:41 -04:00
Marc-Andre Ferland
7c72608e1c First draft for Multi-GPU support 2022-10-16 21:41:39 -04:00
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