extern/easydiffusion
1
0
Fork 1
mirror of https://github.com/easydiffusion/easydiffusion.git synced 2024-11-30 04:04:08 +01:00
Code Issues Packages Projects Releases Wiki Activity
1,763 Commits 14 Branches 38 Tags 64 MiB
27963decc9
Commit Graph

226 Commits

Author SHA1 Message Date
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
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
cmdr2
9fe1709bf7 Catch 16xx cards without the NVIDIA name in them 2022-09-11 11:16:05 +05:30
cmdr2
fec21f1208 Catch 16xx cards without the NVIDIA name in them 2022-09-11 11:10:54 +05:30
cmdr2
1d4b34c0dd Print GPU name 2022-09-11 10:59:45 +05:30
cmdr2
d88e0f16ac Use CPU mode for graphics cards with less than 3 GB of RAM 2022-09-11 10:34:04 +05:30
cmdr2
65b2c056c6 Revert "Revert "Revert "Revert "Merge pull request #112 from cmdr2/develop"""" 
This reverts commit 0dd38870e0.
 2022-09-09 21:05:24 +05:30
cmdr2
0dd38870e0 Revert "Revert "Revert "Merge pull request #112 from cmdr2/develop""" 
This reverts commit 788dcbf471.
 2022-09-08 23:45:21 +05:30
cmdr2
788dcbf471 Revert "Revert "Merge pull request #112 from cmdr2/develop"" 
This reverts commit 9051bf6e68.
 2022-09-08 23:19:35 +05:30
cmdr2
9051bf6e68 Revert "Merge pull request #112 from cmdr2/develop" 
This reverts commit 598de3697d, reversing
changes made to 0eae17075f.
 2022-09-08 22:54:54 +05:30
cmdr2
253e75c747 v2.1 - Face correction (GFPGAN) and Upscaling (RealESRGAN) 2022-09-08 21:20:27 +05:30
cmdr2
1d4e06b884 Use full precision automatically for NVIDIA 1650 and 1660 2022-09-07 15:32:34 +05:30
cmdr2
a29259a8b6 Shorter filenames for saved images; Don't crash other images if one fails to save 2022-09-05 16:51:43 +05:30
cmdr2
21dc2ece1b Store images during a session in the same folder; Store the metadata for each image as a txt file next to it 2022-09-04 00:12:48 +05:30
cmdr2
472b8d0e51 Keep v2 files in the repo, for the updater 2022-09-02 13:58:36 +05:30