cmdr2
|
eb301a67d4
|
changelog
|
2023-06-23 21:43:36 +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
|
3dc62a8857
|
Basic embeddings support
|
2023-06-22 23:48:55 +02:00 |
|
JeLuF
|
7811929b5b
|
Run dev console in ED directory
|
2023-06-22 01:15:07 +02:00 |
|
cmdr2
|
a43bd2fd3b
|
changelog
|
2023-06-20 10:50:28 +05:30 |
|
cmdr2
|
aac9acf068
|
sdkit 1.0.109 - auto-set fp32 attention precision in diffusers if required
|
2023-06-20 10:49:34 +05:30 |
|
JeLuF
|
65bb01892f
|
remove old code
|
2023-06-19 21:58:58 +02:00 |
|
JeLuF
|
5b35c47360
|
Fix saving of network settings
|
2023-06-19 21:50:56 +02:00 |
|
cmdr2
|
4bf78521ce
|
changelog
|
2023-06-19 19:58:59 +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 |
|
Hakorr
|
ac4651c241
|
Image Modifier UI Overhaul
Additionally also fixed body overflowing when on mobile. This is unrelated to the overhaul.
|
2023-06-19 17:24:31 +03:00 |
|
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
|
31a7e178a1
|
Applied changes suggested by @cmdr2
|
2023-06-14 16:59:30 +02:00 |
|
ManInDark
|
ed59972b03
|
Changed all links as mentioned in #1339
|
2023-06-14 11:57:06 +02:00 |
|
ManInDark
|
6ae4314b79
|
Incorporated proposal by @JeLuF in #1324
|
2023-06-13 16:09:54 +02:00 |
|
ManInDark
|
5e07432ae9
|
Merge branch 'easydiffusion:beta' into beta
|
2023-06-13 15:34:26 +02:00 |
|
cmdr2
|
41d8847592
|
changelog
|
2023-06-13 13:39:58 +05:30 |
|
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
|
324ffdefba
|
changelog
|
2023-06-12 16:58:11 +05:30 |
|
cmdr2
|
9a81d17d33
|
Fix for multi-gpu bug in codeformer
|
2023-06-12 16:57:36 +05:30 |
|
ManInDark
|
3e34cdc884
|
Added sets to the readme
|
2023-06-12 13:25:12 +02:00 |
|
ManInDark
|
e213f6cb95
|
Added calculation as to how many images will be generated with given prompts.
|
2023-06-12 12:50:39 +02:00 |
|
cmdr2
|
0ba9f0549e
|
Merge pull request #1341 from JeLuF/beta
Set PYTHONNOUSERSITE=y in dev console
|
2023-06-12 14:48:00 +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
|
924fee394a
|
A better way to make gfpgan show up at the top
|
2023-06-08 16:09:11 +05:30 |
|
cmdr2
|
e349fb1a23
|
fix
|
2023-06-08 15:55:36 +05:30 |
|
cmdr2
|
4f799a2bf0
|
Use gfpgan as the default model for face restoration
|
2023-06-08 15:52:41 +05:30 |
|
cmdr2
|
5398765fd7
|
Tighten the image editor (to reduce unnecessary empty space and reduce mouse travel) - Thanks @fdwr - #1307
|
2023-06-08 15:21:16 +05:30 |
|
cmdr2
|
48edce72a9
|
Log the version numbers of only a few important modules
|
2023-06-07 16:38:15 +05:30 |
|
cmdr2
|
267c7b85ea
|
Use only realesrgan_x4 (not anime) for upscaling in codeformer
|
2023-06-07 16:37:44 +05:30 |
|
cmdr2
|
e23f66a697
|
Fix #1333 - listen_port isn't always present in the config file
|
2023-06-07 15:45:21 +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
|
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
|
6ae5cb28cf
|
Set the default codeformer strength to 0.5
|
2023-06-06 16:37:17 +05:30 |
|
cmdr2
|
cf6c1add1d
|
Merge branch 'beta' of github.com:cmdr2/stable-diffusion-ui into beta
|
2023-06-06 16:24:42 +05:30 |
|
cmdr2
|
d0184a1598
|
Allow changing the strength of the codeformer model (1 - fidelity); Improve the styling of the sub-settings
|
2023-06-06 16:16:21 +05:30 |
|
cmdr2
|
79d6ab9915
|
Update CHANGES.md
|
2023-06-06 15:22:27 +05:30 |
|
cmdr2
|
047390873c
|
changelog; show labels next to the lora strength slider
|
2023-06-05 16:53:18 +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
|
f7c52b700e
|
Merge pull request #1328 from ogmaresca/negative-lora-strength
Allow LoRA strengths between -2 and 2
|
2023-06-05 16:18:28 +05:30 |
|
cmdr2
|
c81d98ad0f
|
Merge pull request #1325 from JeLuF/tildl
Tiled image download plugin
|
2023-06-05 16:17:23 +05:30 |
|
cmdr2
|
046c00d844
|
changelog
|
2023-06-05 16:13:41 +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
|
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 |
|