Commit Graph

158 Commits

Author SHA1 Message Date
cmdr2
23e7a6b8b0 sdkit 1.0.52 - Use weighted prompt parsing using the Compel library 2023-03-23 13:10:00 +05:30
cmdr2
f5be941a4a sdkit 1.0.51 - convert ckpt was missing the new changes that diffusers hasn't merged in yet. bundling it along for now 2023-03-21 18:56:12 +05:30
cmdr2
eabe4cf58c sdkit 1.0.50 - fix typo 2023-03-21 18:47:25 +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
cmdr2
8aead029a8 temp fix for installations that installed torch 2.0 by mistake 2023-03-17 13:33:13 +05:30
cmdr2
a9da65c2cd Temp fix for macOS installations that installed torch 2.0 by mistake, when torch 2 released yesterday 2023-03-17 13:27:44 +05:30
cmdr2
0324deec60 Use CUDA-specific torch only on Linux, not mac 2023-03-17 13:20:37 +05:30
cmdr2
28338612fa Pin versions: torch 1.13.1 and torchvision 0.14.1, and update stable-diffusion-sdkit which also pins the torch and torchvision versions for macOS 2023-03-17 10:07:22 +05:30
cmdr2
5dd92b1d3f sdkit 1.0.47 - mps buffer fix 2023-03-11 10:40:45 +05:30
cmdr2
7548f7cdbb revert mps buffer fix 2023-03-11 10:27:57 +05:30
cmdr2
44da3d26f3 sdkit 1.0.45 - fix buffers used for mac mps 2023-03-11 10:24:01 +05:30
cmdr2
737a81570a
Merge pull request #975 from michaelgallacher/beta
Add support for MPS when running on Apple silicon
2023-03-08 10:00:10 +05:30
cmdr2
32d8f4d24b sdkit 1.0.44 - mps support for mac 2023-03-08 09:57:45 +05:30
Michael Gallacher
11265c4034 Add support for MPS when running on Apple silicon
Changes:

* autodetect if MPS is available and the pytorch version has MPS support.
* change logic from "is the device CPU?" to "is the device not CUDA?".
* set PYTORCH_ENABLE_MPS_FALLBACK=1

Known issues:

* Some samplers (eg DDIM) will fail on MPS unless forced to CPU-only mode
2023-03-07 14:57:37 -07:00
cmdr2
5e2f31e3bf Merge branch 'main' into beta 2023-03-02 10:15:51 +05:30
cmdr2
91c4b5865c Pin the sdkit version during fresh installs 2023-02-21 10:40:17 +05:30
cmdr2
4f8424c544 sdkit 1.0.43 - unipc samplers on any device, not just cuda 2023-02-20 19:31:47 +05:30
cmdr2
9970e505de sdkit version 1.0.42 - WEBP format support 2023-02-20 18:43:39 +05:30
cmdr2
facfed07fe sdkit 1.0.41 - NSFW filter 2023-02-20 08:44:26 +05:30
cmdr2
b43f9fc4ee Upgrade stable-diffusion-sdkit to 2.1.3, to use transformers 4.26.1 2023-02-18 14:30:37 +05:30
cmdr2
51b6a2fd2a Pin the version of stable-diffusion-sdkit used, to avoid untested releases from getting used 2023-02-18 14:21:24 +05:30
cmdr2
5fffb82b16 Pin the version of stable-diffusion-sdkit used, to avoid untested releases from getting used 2023-02-18 14:17:28 +05:30
cmdr2
23f9bcb38b Upgrade sdkit, moving the experimental parser into a plugin 2023-02-17 15:22:59 +05:30
cmdr2
7fc46f3672 sdkit 1.0.39 - unipc samplers 2023-02-17 09:36:10 +05:30
cmdr2
3d3994bbad sdkit 1.0.38 - experimental parser, requires the prompt to start with an exclamation mark 2023-02-16 21:01:33 +05:30
cmdr2
744c6e4725 sdkit 1.0.37 2023-02-15 21:40:02 +05:30
Jens Frank
b89f689ea3 Fix functions.sh upgrade, change messages to Easy Diffusion 2023-02-14 09:00:02 +01:00
JeLuF
8465bc1bc9 Changes to make things work on MacOS/x64 2023-02-10 22:34:52 +01:00
cmdr2
ad249c4651 sdkit 1.0.36, for the image metadata embedding change 2023-02-10 18:09:23 +05:30
cmdr2
071a4d6f37 Use a fixed sdkit version, to avoid bumping to the latest sdkit version in the main branch 2023-02-10 18:05:17 +05:30
cmdr2
5f2fb19d71 Use a fixed sdkit version, to avoid bumping to the latest sdkit version in the main branch 2023-02-10 18:04:43 +05:30
JeLuF
4c8da67bb1
Use "python -m pip" instead of "pip" (#835)
* Use "python -m pip" instead of "pip"

https://discord.com/channels/1014774730907209781/1072423234676461619

* Use "python -m" instead of "pip" (Linux=
2023-02-07 15:39:02 +05:30
cmdr2
5c6c2303ba Why does this script file keep losing exec permission? 2023-02-06 20:05:40 +05:30
cmdr2
a0a58bcfa8
Merge branch 'main' into beta 2023-02-06 19:42:24 +05:30
cmdr2
493526c478 If downgrading to 2.4 (from 2.5), move the default models back to the legacy location 2022-12-29 13:00:57 +05:30
cmdr2
451ab7e84c Create the folders before moving to them 2022-12-28 19:40:08 +05:30
cmdr2
27d69e2ac3 Upgrade stable-diffusion-sdkit during startup 2022-12-28 19:19:53 +05:30
cmdr2
91274a4df8 Move the mandatory models to the models folder, instead of the legacy location inside the stable-diffusion folder 2022-12-28 19:08:39 +05:30
cmdr2
8cedeb349d Changes to allow rolling back from the upcoming sdkit-based system 2022-12-26 23:04:45 +05:30
cmdr2
5e553dd958 Skip sdkit upgrade if in developer mode 2022-12-26 21:00:46 +05:30
cmdr2
32bab80508 Show sdkit version during startup 2022-12-25 16:38:37 +05:30
cmdr2
a4728190c0 Refactor server.py 2022-12-24 15:29:49 +05:30
cmdr2
e0b33a4feb Install rich 2022-12-24 15:10:46 +05:30
cmdr2
8154a5709b disable the legacy src and ldm folder (otherwise this prevents installing gfpgan and realesrgan) 2022-12-24 14:01:33 +05:30
cmdr2
3a6780bd50 Copy check_modules.py the first time an existing user runs the new version 2022-12-24 13:56:05 +05:30
cmdr2
6662dc66d5 Updated scripts to install sdkit into existing installations, while still working with new installations 2022-12-24 13:37:50 +05:30
cmdr2
6b943f88d1 Set uvicorn log level to 'error' 2022-12-12 15:18:30 +05:30
cmdr2
a2af811ad2 Disable uvicorn access logging in favor of cleaner server-side logging, we already get all that info; Print the request metadata 2022-12-09 22:47:34 +05:30
cmdr2
f1de0be679 Fix integration issues after the refactor 2022-12-09 17:50:33 +05:30
cmdr2
f4a6910ab4 Work-in-progress: refactored the end-to-end codebase. Missing: hypernetworks, turbo config, and SD 2. Not tested yet 2022-12-08 21:39:09 +05:30