JeLuF
ea07483465
Error handling for models_dir
2023-09-01 22:54:03 +02:00
cmdr2
ab5450bb27
Don't download codeformer and controlnet if not being used
2023-08-30 14:39:43 +05:30
cmdr2
3792a1bc0d
sdkit 2.0.4 - use sd 1.5 fp16 by default, if no model is present
2023-08-29 20:06:54 +05:30
cmdr2
f9f9aba92d
f
2023-08-24 17:39:39 +05:30
cmdr2
3f278cf2ad
Pick the right embedding even if it has an underscore
2023-08-24 17:36:49 +05:30
JeLuF
cb7ba96dad
Fix handling of embeddings with space in their name ( #1402 )
...
* Fix handling of files with space in their name
* Handle embeddings in save files
* Moved get_embedding_token
* Moved get_embedding_token
* Update save_utils.py
2023-08-24 16:32:17 +05:30
JeLuF
31edce4a60
Add ".pt" to the Lora extensions ( #1518 )
...
https://discord.com/channels/1014774730907209781/1014774732018683926/1144179143873929288
There seem to be ".pt" LORA files in the wild.
2023-08-24 16:09:42 +05:30
cmdr2
f2b441d9fc
typo
2023-08-21 19:20:23 +05:30
cmdr2
41d4ad2096
sdkit 1.0.179 - tile controlnet
2023-08-21 14:29:54 +05:30
cmdr2
ac1c65fba1
Move the extraction logic for embeddings-from-prompt, from sdkit to ED's UI
2023-08-17 10:54:47 +05:30
cmdr2
9a528496a3
Reload the model if the path exists in the request but the model has been unloaded
2023-08-03 15:13:41 +05:30
cmdr2
ae34c9e84b
Download known controlnet models if selected; Auto-pick the recommended controlnet model when a filter is selected
2023-08-01 17:39:04 +05:30
cmdr2
eba7bab15e
Allow named models in the dropdown
2023-08-01 16:16:38 +05:30
cmdr2
ee6db85768
Initial support for Controlnet
2023-08-01 15:39:15 +05:30
cmdr2
e61549e0cd
Mega refactor of the task processing and rendering logic; Split filter into a separate task, and add support for running filter tasks individually; Change the format for sending model and filter data from the API, but maintain backwards compatibility for now with the old API
2023-07-28 18:57:28 +05:30
cmdr2
959c1a196e
Allow the UI to send (and resolve) multiple model paths
2023-07-15 12:09:20 +05:30
cmdr2
09f747a68e
Merge pull request #1362 from JeLuF/textualinv
...
Basic embeddings support
2023-07-09 22:03:22 +05:30
cmdr2
37e8158175
Improve responsiveness of UI startup by not waiting for render threads to start up before showing the UI. Errors while starting the render thread will be logged anyway, so there's no need to block the main thread for this
2023-07-08 23:28:47 +05:30
JeLuF
3dc62a8857
Basic embeddings support
2023-06-22 23:48:55 +02:00
cmdr2
9486c03a89
Don't use the default SD model (if the desired model was not found), unless the UI is starting up
2023-06-06 17:10:38 +05:30
cmdr2
c09512bf12
dead code
2023-06-06 16:57:25 +05:30
cmdr2
05c2de9450
Fail with an error if the desired model (non-Stable Diffusion) wasn't found
2023-06-06 16:56:37 +05:30
cmdr2
c72b287c82
Show a more helpful error message in the logs when the system runs out of RAM
2023-06-05 15:22:37 +05:30
cmdr2
a10aa92634
Fix a bug where the realesrgan model would get unloaded after the first request in a batch while using Codeformer with upscaling of faces
2023-06-05 15:08:57 +05:30
cmdr2
dd95df8f02
Refactor the default model download code, remove check_models.py, don't check in legacy paths since that's already migrated during initialization; Download CodeFormer's model only when it's used for the first time
2023-06-02 16:34:29 +05:30
cmdr2
0860e35d17
sdkit 1.0.101 - CodeFormer as an option to improve faces
2023-06-01 16:50:01 +05:30
cmdr2
3e90eafafb
Merge branch 'cf' into beta
2023-06-01 15:27:37 +05:30
cmdr2
8554b0eab2
Better reporting of model load errors - sends the report to the browser UI during the next image rendering task
2023-05-24 16:02:53 +05:30
cmdr2
2bab4341a3
Add 'Latent Upscaler' as an option in the upscaling dropdown
2023-05-23 16:53:53 +05:30
patriceac
a5a1d33589
Fix face restoration model selection
2023-05-21 18:32:48 -07:00
JeLuF
00603ce124
Add Clip Skip support
2023-05-18 13:55:45 +02:00
patriceac
a25364732b
Support for CodeFormer
...
Depends on https://github.com/easydiffusion/sdkit/pull/34 .
2023-05-17 02:04:20 -07:00
cmdr2
d18cefc519
Formatting
2023-04-28 16:38:55 +05:30
cmdr2
7fc2ed28b1
Merge pull request #1166 from JeLuF/not_yet
...
Don't save model_path if initial load fails
2023-04-18 16:34:12 +05:30
JeLuF
893b6d985c
Add "Start scanning..." to getModels()
...
Provide a hint to users what ED is currently using.
Use case: User has built an infinite loop using symlinks, ED model scan will never finish.
https://discord.com/channels/1014774730907209781/1097764777553580092
2023-04-18 09:12:26 +02:00
JeLuF
1ba3a139d9
Don't save model_path if initial load fails
...
Fixes #882
If the load of the model fails during the initialization, an attempt to render an
image using the same model fails because ED doesn't notice that the model has to
be loaded. This PR ensures that the model is being reloaded if the initial load
fails. If the second load attempt fails as well, the user will get a more helpful
error message than 'model not loaded yet'.
2023-04-16 21:59:29 +02:00
JeLuF
4192f87d6b
Don't scan safetensors files in load_default_models() ( #1155 )
...
* Don't scan safetensors when loading them
* Don't scan safetensors files
* Update model_manager.py
---------
Co-authored-by: cmdr2 <shashank.shekhar.global@gmail.com>
2023-04-14 17:11:35 +05:30
cmdr2
8ba0b34853
Log the stack trace when the model fails to load
2023-04-11 15:13:41 +05:30
cmdr2
f8bc50871a
sdkit 1.0.49; Use a test_diffusers flag to gate access to the new renderer and LoRA model selection
2023-03-21 17:59:20 +05:30
JeLuF
bdbb741716
Don't scan safetensors files
...
In newer versions of the picklescanner, scanning of .safetensors files creates an error:
21:28:01.067 ERROR MainThread ERROR: parsing pickle in D:\2.35\dev\models\stable-diffusion\dantionrealmix_10.safetensors: at position 1, opcode b'\xce' unknown
To avoid these entries in the logs, skip scanning of safetensors files.
2023-02-20 22:44:10 +01:00
cmdr2
aa70f2849b
NSFW filter setting
2023-02-18 15:01:13 +05:30
cmdr2
2eb317c6b6
Format code, PEP8 using Black
2023-02-14 18:47:50 +05:30
cmdr2
f7b8e000c5
Merge pull request #830 from ogmaresca/sort-models
...
Sort models alphabetically
2023-02-10 17:42:24 +05:30
cmdr2
9e718da70e
Merge pull request #789 from JeLuF/gfpgan-chooser
...
Support multiple GFPGAN models
2023-02-10 17:16:49 +05:30
Olivia Godone-Maresca
ed9f18e22c
Trim lines
2023-02-09 17:56:54 -05:00
cmdr2
0332cc8cb3
Don't force the user to 'low' VRAM usage automatically, if their GPU is less than 4 GB of VRAM. We need a better way to set 'low' as the default in the UI, but the user should be able to override it if they want
2023-02-08 19:41:55 +05:30
Olivia Godone-Maresca
e7bf2ee58b
Show models above folders in child folders to avoid models from appearing to belong the grandchild folder, prevent creating empty <optgroup />s
2023-02-07 21:13:06 -05:00
Olivia Godone-Maresca
e0f22d29e8
Sort models alphabetically
2023-02-06 19:03:03 -05:00
cmdr2
5cd8a732c7
grammar
2023-02-06 16:29:46 +05:30
JeLuF
b044bc1791
Support multiple GFPGAN models
...
Add scanning for models and a dropdown to choose different models from
2023-01-19 20:49:54 +01:00
