Commit Graph

165 Commits

Author SHA1 Message Date
Marc-Andre Ferland
0a21a69a9f Updated facexlib fix for usage on multi-gpu. 2022-11-20 13:04:22 -05:00
cmdr2
2cf8b2a453
Use the correct device name when moving the model to cpu 2022-11-20 00:43:38 +05:30
cmdr2
c10e773401 Speed up the model move, by using the earlier function to move modelCS and modelFS to the cpu 2022-11-19 11:53:33 +05:30
cmdr2
025d4df774 Don't crash if a VAE file fails to load 2022-11-18 13:11:48 +05:30
cmdr2
97ee085f30 Fix a bug where Face Correction (GFPGAN) would fail on cuda:N (i.e. GPUs other than cuda:0), as well as fail on CPU if the system had an incompatible GPU. 2022-11-17 12:27:06 +05:30
cmdr2
06b41aee58 Fix - reduce the amount of VRAM occupied when the program starts up, this caused a regression and failures on GPUs with 4 gb or less of VRAM 2022-11-16 19:29:04 +05:30
cmdr2
e99d54d1f6 Merge main 2022-11-16 11:19:10 +05:30
cmdr2
9d2b944063 Remove unused variable 2022-11-15 13:18:00 +05:30
cmdr2
8e1ec5903b Don't throw an exception when an invalid device is being checked for compatibility. Report and return false 2022-11-15 12:41:10 +05:30
Marc-Andre Ferland
a108e5067d Typos in comments. 2022-11-14 22:20:21 -05:00
Marc-Andre Ferland
a4a24b1a1a Fixed calling get_device_delta with a single cuda device inside config.json at boot. 2022-11-14 22:14:03 -05:00
Marc-Andre Ferland
ffe0eb1544 Changed update_render_threads to use SetAppConfigRequest to set which devices are active.
Keep ImageRequest.render_device for affinity only. (Send a task to an already active device.)
2022-11-14 21:54:24 -05:00
cmdr2
2967261acb Ensure that we only pick better GPUs than the current one, during the subsequent tasks 2022-11-14 21:13:24 +05:30
cmdr2
8707f88c07 Show mem free info 2022-11-14 20:35:47 +05:30
cmdr2
338ceffa6d Use 'auto' as the default render_device 2022-11-14 15:14:58 +05:30
cmdr2
371e104b00 Pick the device id 2022-11-14 13:43:37 +05:30
cmdr2
d5aba8eaf1 Show free/total mem while starting up 2022-11-14 13:40:55 +05:30
cmdr2
027b2e1b88 Use the 65 percentile of free_mem for GPU selection, instead of 75 percentile 2022-11-14 12:26:21 +05:30
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