188 Commits

Author	SHA1	Message	Date
cmdr2	426f92595e	Merge pull request #520 from madrang/fix-gfpgan ... Fix the gfpgan fix for multi-gpu	2022-11-30 13:08:10 +05:30
cmdr2	ac605e9352	Typos and minor fixes for sd 2	2022-11-29 13:30:08 +05:30
cmdr2	e37be0f954	Remove the need to use yield in the core loop for streaming results. This removes the need to patch the Stable Diffusion code, which can be fragile	2022-11-29 13:03:57 +05:30
cmdr2	36249874bc	Revert "Patching patch again"	2022-11-26 01:42:16 +05:30
Jens Sülwald	b2922741c9	Patching patch again	2022-11-25 21:06:19 +01:00
cmdr2	d7330b80a9	Revert "Update ddim_callback_sd2.patch"	2022-11-26 01:22:35 +05:30
jsuelwald	8114fa3f5d	Update ddim_callback_sd2.patch	2022-11-25 20:46:24 +01:00
cmdr2	4bc5508f38	Rollback	2022-11-26 01:07:55 +05:30
cmdr2	e503c6092e	Ddim decode for img2img	2022-11-26 00:55:39 +05:30
cmdr2	6a8985d8dd	Update ddim_callback_sd2.patch	2022-11-26 00:49:15 +05:30
cmdr2	bee67fd883	Shape	2022-11-25 23:54:08 +05:30
cmdr2	a1d75d40aa	Update runtime.py	2022-11-25 23:36:43 +05:30
cmdr2	29484867ca	Typo	2022-11-25 23:32:56 +05:30
cmdr2	7fa983b971	Img2img sd2 attempt 2	2022-11-25 23:28:31 +05:30
cmdr2	617a8b2814	Fix for make_schedule error in sd2	2022-11-25 23:15:22 +05:30
cmdr2	b924d323d4	img2img attempt for sd2	2022-11-25 22:36:02 +05:30
cmdr2	642c114501	Working txt2img	2022-11-25 14:29:24 +05:30
cmdr2	02dd3e457d	Tweaks to load sd1 models in sd2 code, typos	2022-11-25 13:57:15 +05:30
cmdr2	ea7b28c9d5	Placeholder changes for SD 2.0 support, haven't tested yet	2022-11-25 12:17:44 +05:30
cmdr2	7cbf62cf12	Revert whitespace fix	2022-11-22 23:30:03 +05:30
cmdr2	5af84b8e90	Fix whitespace during git apply	2022-11-22 22:21:54 +05:30
cmdr2	93bbfac29a	Change the backend to a custom fork of SD, since basujindal's fork is no longer under development. This fork is intended to include the common models/tools used like RealESRGAN, GFPGAN, Codeformer etc, and is meant to be a community-developed project	2022-11-22 16:38:39 +05:30
cmdr2	9499685dda	Check for enqueued tasks more frequently	2022-11-21 14:06:26 +05:30
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