cmdr2
801a3dd598
sdkit 1.0.160 - Dynamic load/unload of TensorRT engines
2023-08-02 15:34:55 +05:30
cmdr2
d76930c7f4
sdkit 1.0.159 - typo in TensorRT forward
2023-08-02 12:35:44 +05:30
cmdr2
38ab5b090f
TRT ui changes
2023-08-02 00:08:43 +05:30
cmdr2
fa58996f37
sdkit 1.0.157 - tensorRT build configuration from the UI; clamp images to 8 instead of 64 pixels
2023-08-01 23:53:01 +05:30
cmdr2
4e444b418e
sdkit 1.0.156 - missing jsons for controlnet
2023-08-01 18:23:34 +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
9690fd1fa8
sdkit 1.0.154 - restrict tensorrt from 768x768 to 1024x1024, and Unet-only, to avoid going out of memory
2023-08-01 12:45:56 +05:30
cmdr2
8538a684e7
sdkit 1.0.153 - use TensorRT only if enabled in the UI
2023-07-31 13:19:56 +05:30
cmdr2
47d7513dd8
sdkit 1.0.152 - fix for black images with TensorRT, and enable a timing cache
2023-07-31 12:54:05 +05:30
cmdr2
1d6742f463
sdkit 1.0.151 - An option to use strict mask borders
2023-07-30 13:51:19 +05:30
cmdr2
11fb83a2a7
sdkit 1.0.148 - fix watermarking which is causing image artifacts in SDXL; fix SDXL long prompts with compel 2.0.1
2023-07-29 22:03:39 +05:30
cmdr2
13592fae1a
sdkit 1.0.147 - diffusers 0.19.2 - fix red specs in SDXL images
2023-07-29 21:29:24 +05:30
cmdr2
2e3059a7c8
UI for TensorRT installation and conversion
2023-07-29 21:09:27 +05:30
cmdr2
7f32c531d7
sdkit 1.0.143 - Fixes for the new beta
2023-07-28 19:14:40 +05:30
cmdr2
b93c624efa
sdkit 1.0.142 - fix live preview for sdxl
2023-07-27 17:51:52 +05:30
cmdr2
d118443a94
sdkit 1.0.141 - allow sdxl vae
2023-07-27 17:34:41 +05:30
cmdr2
064a55f587
sdkit 1.0.140 - fix broken gfpgan and realesrgan
2023-07-27 16:50:58 +05:30
cmdr2
0b054b58d4
sdkit 1.0.139 - SD-XL full support, diffusers 0.19.0, compel 2.0.0
2023-07-27 15:35:43 +05:30
cmdr2
b408fc7cd2
sdkit 1.0.137 - Fix DPM single step solver with non-unique timesteps
2023-07-24 19:59:57 +05:30
cmdr2
a8ed1ebf52
sdkit 1.0.136 - unify unipc tu and tu2, don't reuse sampler instances between image generation to avoid image artifacts
2023-07-24 16:41:35 +05:30
cmdr2
8857249b48
sdkit 1.0.135 - fix broken inpainting models after the latest diffusers upgrade
2023-07-22 18:22:13 +05:30
cmdr2
ca59866d52
sdkit 1.0.134 - don't prevent a lycoris from loading, use it partially, and warn the user in the logs
2023-07-17 23:30:36 +05:30
cmdr2
4832c67167
sdkit 1.0.133 - some more keys for lora
2023-07-17 21:35:06 +05:30
cmdr2
6ec7b78d96
sdkit 1.0.132 - fix for some loras - #1417
2023-07-17 20:44:30 +05:30
cmdr2
812fc20c39
sdkit 1.0.131 - Fix loras ignoring several layers
2023-07-16 12:58:01 +05:30
cmdr2
66624f4011
sdkit 1.0.130 - 2x multiplier for lora
2023-07-16 02:31:01 +05:30
cmdr2
b58b7660ab
sdkit 1.0.129 - 1.6x multiplier for lora
2023-07-16 02:27:32 +05:30
cmdr2
6f065918e9
sdkit 1.0.128 - don't fail if local alpha is different in loras
2023-07-16 01:12:49 +05:30
cmdr2
0f7f52fbc2
sdkit 1.0.127 - tweak 1.5x multiplier for lora
2023-07-15 23:28:12 +05:30
cmdr2
721f826376
sdkit 1.0.126 - 1.5x multiplier for lora
2023-07-15 23:18:03 +05:30
cmdr2
92ffbb5ed8
sdkit 1.0.125 - remove the 2x multiplier on lora
2023-07-15 19:27:18 +05:30
cmdr2
0cc2d26e97
sdkit 1.0.124 - make loras twice as sensitive to alpha
2023-07-15 18:52:14 +05:30
cmdr2
bb5487efb8
sdkit 1.0.123 - fix for missing network alpha or rank in a lora
2023-07-15 18:38:42 +05:30
cmdr2
025ee49680
Merge branch 'beta' of github.com:cmdr2/stable-diffusion-ui into beta
2023-07-15 10:55:50 +05:30
cmdr2
935c75bcab
sdkit 1.0.122 - multiple lora file support; more SDE samplers; diffusers 0.18.2 upgrade to fix broken SD 2 checkpoint loading
2023-07-15 10:55:09 +05:30
cmdr2
1e4cca54b6
Merge pull request #1405 from JeLuF/bindip
...
Add Bind IP option
2023-07-13 14:51:20 +05:30
JeLuF
4b89c3e7a5
fix typo
2023-07-13 10:14:46 +02:00
JeLuF
fa457ad476
Fix uvicorn issues after reloacting install dir
...
Fixes https://discord.com/channels/1014774730907209781/1014774732018683926/1128441748637626499
2023-07-11 23:56:03 +02:00
JeLuF
b005332840
Add Bind IP option
2023-07-11 23:03:11 +02:00
cmdr2
5e0839531e
sdkit 1.0.121 - fix live preview, wasn't decoding the vae
2023-07-10 13:27:48 +05:30
cmdr2
1c7acf7bcf
sdkit 1.0.120 - pick the correct AMD gpu if an integrated GPU exists at device id 0
2023-07-10 13:06:56 +05:30
cmdr2
d143e85760
Use the local profile folder for dev console
2023-07-10 12:37:49 +05:30
cmdr2
2612c274d3
sdkit 1.0.119 - another fix for live preview
2023-07-10 10:50:10 +05:30
cmdr2
764ad1b8db
sdkit 1.0.118 - fix live preview in img2img
2023-07-10 10:40:00 +05:30
cmdr2
b1dcfbd017
sdkit 1.0.117 - fix directml/tensorrt for diffusers 0.18.1
2023-07-10 09:56:28 +05:30
cmdr2
2b9f5eb627
sdkit 1.0.116 - diffusers 0.18.1 upgrade; compel upgrade; embeddings support; AMD-on-Windows and TensorRT acceleration - preliminary support; faster sdkit import time to improve startup time of ED's UI
2023-07-09 20:45:11 +05:30
cmdr2
2dfa482b24
Update get_config.py
2023-06-30 18:33:16 +05:30
cmdr2
d023fd07b0
Move config.yaml to the root folder of ED
2023-06-30 16:36:24 +05:30
cmdr2
45f99ab48a
Include comments in config.yaml even when converting from config.json
2023-06-30 11:53:38 +05:30
cmdr2
26042b1e26
Don't use YAML as a singleton, seems to be stateful; Use ruamel in get_config for consistency
2023-06-30 10:37:25 +05:30
cmdr2
cc475f26f4
sdkit 1.0.115 - check for upcasting precision only if using half-precision (e.g. skip for cpu)
2023-06-28 11:31:52 +05:30
cmdr2
f252ca75e9
temp rollback
2023-06-28 10:52:54 +05:30
cmdr2
05b608831c
sdkit 1.0.113 - check for upcasting precision only if using half-precision (e.g. skip for cpu)
2023-06-28 10:33:41 +05:30
cmdr2
913550295c
Install ruamel.yaml 0.17.21
2023-06-26 17:01:01 +05:30
cmdr2
af7073d9b6
Merge branch 'beta' into yaml
2023-06-26 16:57:35 +05:30
cmdr2
13056f87d3
Merge pull request #1342 from ManInDark/beta
...
Prevent UI freeze caused by intensive prompts
2023-06-26 16:25:18 +05:30
cmdr2
817436b65c
Merge pull request #1361 from JeLuF/patch-28
...
Run dev console in ED directory
2023-06-26 15:53:38 +05:30
JeLuF
c9a5ad9c3a
Update Developer Console.cmd
2023-06-26 12:20:34 +02:00
cmdr2
c480b615ce
Merge pull request #1363 from JeLuF/comspec
...
Show COMSPEC variable in logs
2023-06-26 15:41:13 +05:30
cmdr2
c74be07c33
sdkit 1.0.112 - fix broken inpainting in low vram mode
2023-06-24 15:46:03 +05:30
cmdr2
4dd1a46efa
sdkit 1.0.111 - don't apply a negative lora when testing a newly loaded SD model
2023-06-24 15:21:13 +05:30
cmdr2
d9bddffc42
sdkit 1.0.110 - don't offload latent upscaler to the CPU if not running on a GPU
2023-06-23 21:42:11 +05:30
JeLuF
a5898aaf3b
Show COMSPEC variable in logs
2023-06-22 23:54:45 +02:00
JeLuF
7811929b5b
Run dev console in ED directory
2023-06-22 01:15:07 +02:00
cmdr2
aac9acf068
sdkit 1.0.109 - auto-set fp32 attention precision in diffusers if required
2023-06-20 10:49:34 +05:30
cmdr2
2a5b3040e2
sdkit 1.0.108 - potential fix for multi-gpu bug while rendering - the sampler instances weren't thread-local
2023-06-19 19:58:17 +05:30
cmdr2
2c4cd21c8f
sdkit 1.0.107 - fix a bug where low VRAM usage mode wasn't working with multiple GPUs
2023-06-16 16:46:32 +05:30
ManInDark
ed59972b03
Changed all links as mentioned in #1339
2023-06-14 11:57:06 +02:00
cmdr2
eb96bfe8a4
sdkit 1.0.106 - fix errors with multi-gpu in low vram mode
2023-06-13 13:39:23 +05:30
cmdr2
3037cceab3
Merge branch 'beta' of github.com:cmdr2/stable-diffusion-ui into beta
2023-06-12 17:22:29 +05:30
cmdr2
9a81d17d33
Fix for multi-gpu bug in codeformer
2023-06-12 16:57:36 +05:30
JeLuF
f83af28e42
Set PYTHONNOUSERSITE=y in dev console
...
Make behaviour consistent with on_env_start.sh
2023-06-11 21:12:22 +02:00
cmdr2
48edce72a9
Log the version numbers of only a few important modules
2023-06-07 16:38:15 +05:30
cmdr2
9a0031c47b
Don't copy check_models.py, it doesn't exist anymore
2023-06-07 15:21:16 +05:30
cmdr2
0d8e73b206
sdkit 1.0.104 - Not all pipelines have vae slicing
2023-06-07 15:10:57 +05:30
cmdr2
4b36ca75cb
Merge pull request #1313 from JeLuF/cloudflared
...
Share ED via Cloudflare's ArgoTunnel
2023-06-05 16:20:40 +05:30
cmdr2
b14653cb9e
sdkit 1.0.103 - Pin the versions of diffusers models used; Use cpu offloading for balanced and low while upscaling using latent upscaler
2023-06-05 16:11:48 +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
JeLuF
2080d6e27b
Share ED via Cloudflare's ArgoTunnel
...
Shares the Easy Diffusion instance via https://try.cloudflare.com/
2023-05-28 00:50:23 +02:00
cmdr2
a0b3b5af53
sdkit 1.0.98 - seamless tiling
2023-05-25 15:36:27 +05:30
cmdr2
29ec34169c
Merge branch 'beta' of github.com:cmdr2/stable-diffusion-ui into beta
2023-05-22 18:07:00 +05:30
cmdr2
d60cb61e58
sdkit 1.0.97 - flatten arguments sent to latent upscaler
2023-05-22 18:06:38 +05:30
JeLuF
0f6caaec33
get_config: return default value if conf file is corrupted
2023-05-22 10:21:19 +02:00
cmdr2
bdf36a8dab
sdkit 1.0.96 - missing xformers import
2023-05-19 18:36:37 +05:30
cmdr2
107323d8e7
sdkit 1.0.95 - lower vram usage for high mode
2023-05-19 17:42:47 +05:30
cmdr2
83557d4b3c
Merge branch 'beta' of github.com:cmdr2/stable-diffusion-ui into beta
2023-05-19 17:29:20 +05:30
cmdr2
415213878d
sdkit 1.0.94 - vram optimizations - perform softmax in half precision
2023-05-19 17:28:54 +05:30
JeLuF
b77036443f
Fail gracefully if proc access isn't possible
2023-05-18 16:04:28 +02:00
cmdr2
7562a882f4
sdkit 1.0.93 - lower vram usage for balanced mode, by using attention slice of 1
2023-05-16 16:02:20 +05:30
cmdr2
45db4bb036
sdkit 1.0.92 - more vram optimizations for low,balanced,high - reduces VRAM usage by 20% (especially with larger images)
2023-05-12 16:49:13 +05:30
cmdr2
add05228bd
sdkit 1.0.91 - use slice size 1 for low vram usage mode, to reduce VRAM usage
2023-05-11 16:30:06 +05:30
cmdr2
566a83ce3f
sdkit 1.0.89 - use half precision in test diffusers for low vram usage mode'
2023-05-11 14:49:15 +05:30
cmdr2
2d1be6186e
sdkit 1.0.88 - Fix LoRA in low VRAM mode
2023-05-10 20:19:17 +05:30
JeLuF
c0dcf1633c
Unset PYTHONHOME in start.sh
2023-05-09 18:07:46 +02:00
JeLuF
d8447ef1a9
Unset PYTHONHOME in Start Stable Diffusion UI.cmd
...
PYTHONHOME needs to be deleted before conda gets called for the first time.
2023-05-09 18:04:45 +02:00
cmdr2
64cfd55065
sdkit 1.0.87 - typo
2023-05-04 16:31:40 +05:30
cmdr2
f9cfe1da45
sdkit 1.0.86 - don't use cpu offload for mps/mac, doesn't make sense since the memory is shared between GPU/CPU
2023-05-04 16:09:28 +05:30
cmdr2
b27a14b1b4
sdkit 1.0.85 - torch.Generator fix for mps/mac
2023-05-04 16:04:45 +05:30
cmdr2
75f0780bd1
sdkit 1.0.84 - VRAM optimizations for the diffusers version
2023-05-03 16:12:11 +05:30
cmdr2
07f52c38ef
sdkit 1.0.83 - formatting
2023-04-28 16:35:30 +05:30
cmdr2
a46ff731d8
sdkit 1.0.82 - VAE slicing for pytorch 2.0, don't fail to hash files smaller than 3 MB
2023-04-28 16:03:35 +05:30
cmdr2
6a6ea5009a
Merge pull request #1182 from JeLuF/get_config
...
Don't write config.bat and config.sh any more
2023-04-26 16:35:52 +05:30
cmdr2
24d0e7566f
Copy get_config.py in on_sd_start for the first run, when on_env_start hasn't yet been updated
2023-04-26 16:34:27 +05:30
cmdr2
fe8c208e7c
Copy get_config.py in on_sd_start for the first run, when on_env_start hasn't yet been updated
2023-04-26 16:33:43 +05:30
JeLuF
9399fb5371
Don't use python packages from the user's home directory
...
PYTHONNOUSERSITE is required to ignore packages installed to `/home/user/.local/`. Since these folders are outside of our control, they can cause conflicts in ED's python env.
https://discord.com/channels/1014774730907209781/1100375010650103808
Fixes #1193
2023-04-25 21:02:36 +02:00
cmdr2
3ae851ab1f
Revert "Revert "Stop messing with %USERPROFILE%""
2023-04-24 14:32:18 +05:30
cmdr2
6fbb24ae3d
Revert "Stop messing with %USERPROFILE%"
2023-04-24 14:30:52 +05:30
JeLuF
bb607927d0
Stop messing with %USERPROFILE%
...
Set HF_HOME, so that the models don't get downloaded again.
2023-04-23 12:54:20 +02:00
cmdr2
5acf5949a6
sdkit 1.0.81 - use tf32 = True for ampere GPUs
2023-04-22 15:42:24 +05:30
cmdr2
3d740555c3
Force mac to downgrade from torch 2.0
2023-04-22 14:54:52 +05:30
cmdr2
eb16296873
Restrict AMD cards on Linux to torch 1.13.1 and ROCm 5.2. Avoids black images on some AMD cards. Temp hack until AMD works properly on torch 2.0
2023-04-21 19:08:51 +05:30
cmdr2
1864921d1d
Don't copy bootstrap.bat unnecessarily
2023-04-21 16:09:32 +05:30
cmdr2
2e84a421f3
Show sdkit installation progress during the first run
2023-04-21 15:49:38 +05:30
cmdr2
fea77e97a0
actually fix the img2img error in the new diffusers version
2023-04-21 15:26:14 +05:30
cmdr2
e1b6cc2a86
typo
2023-04-21 15:13:29 +05:30
cmdr2
0921573644
sdkit 1.0.78 - fix the 'astype' error with the new diffusers version
2023-04-21 15:11:26 +05:30
JeLuF
5eec05c0c4
Don't write config.bat and config.sh any more
2023-04-21 00:09:27 +02:00
cmdr2
526fc989c1
Allow any version of torch/torchvision
2023-04-20 18:40:45 +05:30
cmdr2
023b78d1c9
Allow rocm5.2
2023-04-20 17:46:34 +05:30
cmdr2
670410b539
sdkit 1.0.77 - fix inpainting bug on diffusers
2023-04-20 17:42:12 +05:30
cmdr2
76e379d7e1
Don't install xformers, it downgrades the torch version. Still need to fix this
2023-04-20 17:07:10 +05:30
cmdr2
6c148f1791
Don't install xformers for AMD on Linux; changelog
2023-04-20 16:48:38 +05:30
cmdr2
534bb2dd84
Use xformers 0.0.16 to speed up image generation
2023-04-20 16:44:06 +05:30
cmdr2
d0f4476ba5
Suggest downloading a model downloading in the troubleshooting steps. Thanks JeLuf
2023-04-20 16:22:42 +05:30
cmdr2
6287bcd00a
sdkit 1.0.76 - use 256 as the tile size for realesrgan, instead of 128. slightly more VRAM, but faster upscaling
2023-04-20 16:17:27 +05:30
cmdr2
cb527919a2
sdkit 1.0.75 - upgrade to diffusers 0.15.1
2023-04-19 16:45:28 +05:30
cmdr2
83c34ea52f
Remove unnecessary hotfix
2023-04-19 16:31:04 +05:30
cmdr2
35c75115de
Log errors during module and model initialization
2023-04-19 16:20:08 +05:30
cmdr2
7c75a61700
Typo
2023-04-19 16:15:15 +05:30
cmdr2
34ea49147c
Update the check_models.py script during startup
2023-04-19 16:13:29 +05:30
cmdr2
c1e8637a9f
Re-implement the code for downloading models in python. Save some eyeballs from bleeding
2023-04-19 16:11:16 +05:30
cmdr2
becbef4fac
Include ROCm in the list of allowed versions
2023-04-18 17:36:52 +05:30
cmdr2
bf3df097b8
Don't use ROCm on Linux if an NVIDIA card is present
2023-04-18 17:14:24 +05:30
cmdr2
30a133bad9
Allow torch 1.11 to continue being installed
2023-04-18 16:10:46 +05:30
cmdr2
d8d44c579c
Typo
2023-04-18 15:43:56 +05:30
cmdr2
80384e6ee1
Install PyTorch 2.0 by default, but allow existing PyTorch 1.13.1 installations to continue running; Unify and streamline the installation of dependencies
2023-04-18 15:42:33 +05:30
cmdr2
0898f98355
Merge branch 'beta' of github.com:cmdr2/stable-diffusion-ui into beta
2023-04-18 15:05:53 +05:30
Diana
e7dc41e271
Automatic AMD GPU detection on Linux ( #1078 )
...
* Automatic AMD GPU detection on Linux
Automatically detects AMD GPUs and installs the ROCm version of PyTorch instead of the cuda one
A later improvement may be to detect the GPU ROCm version and handle GPUs that dont work on upstream ROCm, ether because they're too old and need a special patched version, or too new and need `HSA_OVERRIDE_GFX_VERSION=10.3.0` added, possibly check through `rocminfo`?
* Address stdout suppression and download failure
* If any NVIDIA GPU is found, always use it
* Use /proc/bus/pci/devices to detect GPUs
* Fix comparisons
`-eq` and `-ne` only work for numbers
* Add back -q
---------
Co-authored-by: JeLuF <jf@mormo.org>
2023-04-18 15:02:39 +05:30
cmdr2
0f0f475241
Merge branch 'beta' of github.com:cmdr2/stable-diffusion-ui into beta
2023-04-18 14:44:23 +05:30
cmdr2
127ee68486
Merge pull request #1171 from JeLuF/p0417
...
Don't download 1.4 if other models are available
2023-04-18 14:43:45 +05:30
JeLuF
44824fb5f9
Don't download 1.4 if other models are available
2023-04-17 23:22:44 +02:00
cmdr2
dc21cbe59d
Typo
2023-04-17 16:25:49 +05:30
cmdr2
e16d9f4742
Merge branch 'torch2' into beta
2023-04-17 16:24:41 +05:30
cmdr2
f2b5843e6c
merge beta
2023-04-17 15:50:51 +05:30
cmdr2
0c0525e11b
sdkit 1.0.72 - use the extra attn precision yaml code for diffusers, which doesn't auto-detect black images yet
2023-04-17 15:43:08 +05:30
cmdr2
80bcfabc48
Upgrade to PyTorch 2.0; Doesn't use a special repo url for pytorch on Linux
2023-04-14 17:32:27 +05:30
cmdr2
03c8a0fca5
sdkit 1.0.70 - use plms for warming up the model, avoiding any non-deterministic effects from the default ancestral sampler
2023-04-12 15:31:10 +05:30
cmdr2
a3d2c71ed6
sdkit 1.0.69 - allow loading models without vae weights in diffusers
2023-04-11 15:34:44 +05:30