d1dd35a1d2
final tweak to embedded screenshots in WEB.md
2022-10-09 18:21:13 -04:00
400f062771
make initial screenshot even larger
2022-10-09 18:21:13 -04:00
40894d67ac
fixup image sizes in WEB.md
2022-10-09 18:21:13 -04:00
08a0b85111
fix image links in documentation
2022-10-09 18:21:13 -04:00
7da6fad359
add missing doc files
2022-10-09 18:21:05 -04:00
b24d182237
Update README.md
...
Small writing error
2022-10-09 18:17:11 -04:00
2bdcc106f2
Fix markdown typo in WEB.md
2022-10-09 18:16:27 -04:00
7a98387e8d
Updates INSTALL_MAC.md
2022-10-09 18:16:27 -04:00
58d0f14d03
Update references to lstein/stable-diffusion to invoke-ai/InvokeAI
2022-10-09 18:16:27 -04:00
bc9471987b
Update README.md
...
Small writing error
2022-10-09 18:16:27 -04:00
dc6e60cbcc
Update INPAINTING.md
...
Changed Gimp instructions to indicate that partial transparency is better than full transparency.
2022-10-09 18:16:27 -04:00
7dae5fb131
rebuild frontend
2022-10-09 18:16:24 -04:00
542ceb051b
Rework Gallery DIsplay
2022-10-09 08:34:57 -04:00
3473669458
WebUI Bug Fixes & Tweaks
2022-10-09 08:33:18 -04:00
27f62999c9
* Fix for Perlin noise issue for cuda as well.
2022-10-09 08:24:02 -04:00
4c026d9d92
enhance the in-line -h command help text
...
- the prompt argument comes before the optional arguments
- usage statement shows 'invoke>' rather than 'invoke.py'
- use pydoc pager to help display long help message
2022-10-08 13:53:56 -04:00
435231ef08
Get for external TI .bin files to work
...
Issue referenced in https://github.com/invoke-ai/InvokeAI/issues/980#issuecomment-1272162880
Users whose embeddings are trained on a non-regular num_vectors_per_token (e.g. 6), should update this value in their local repo, to get that embedding to work.
2022-10-08 13:18:19 -04:00
7b095f8f97
add realesrgan to requirements.txt, remove nightie for torch and torchvision due to performance issues
2022-10-08 12:01:45 -04:00
f5dfd5b0dc
Fixes CORS handling
2022-10-08 11:57:18 -04:00
47a97f7e97
rebuild front end
2022-10-08 11:50:25 -04:00
3c146ebf9e
Fix Gallery being open by default
2022-10-08 11:47:11 -04:00
efbcbb0d91
Add Image Gallery Drawer
2022-10-08 11:44:42 -04:00
578d8b0cb4
Add Image Gallery Drawer
2022-10-08 11:43:02 -04:00
2b1aaf4ee7
rename all modules from ldm.dream to ldm.invoke
...
- scripts and documentation updated to match
- ran preflight checks on both web and CLI and seems to be working
2022-10-08 11:37:23 -04:00
4a7f5c7469
Merge branch 'release-candidate-2' of github.com:invoke-ai/InvokeAI into release-candidate-2
2022-10-08 09:34:11 -04:00
98fe044dee
rebrand CLI from "dream" to "invoke"
...
- rename dream.py to invoke.py
- create a compatibility script named dream.py that execs() invoke.py
- redo documentation
- change help message in args
- this does **not** rename the libraries, which are still ldm.dream.util, etc
2022-10-08 09:32:06 -04:00
97684d78d3
rebuild webui package
2022-10-07 16:44:23 -04:00
57791834ab
[WebUI] Add Image To Image UI
2022-10-07 16:41:09 -04:00
7a701506a4
restore ability of ksamplers to process -v variation options
...
- supersedes PR #977
- works with both img2img and txt2img
2022-10-07 16:25:58 -04:00
3d7bc074cf
autorotate init images using exif orientation tag
2022-10-07 12:06:50 -04:00
70bb7f4a61
fixed perlin noise generation for mps (macos) - fix for cpu fallback
2022-10-07 10:36:45 -04:00
9c9cb71544
rebuild frontend package
2022-10-07 10:20:02 -04:00
a7515624b2
remove duplicated code
2022-10-07 08:12:55 -04:00
9f34ddfcea
fix crash on len(Nonetype) in k_sampler
2022-10-07 08:05:13 -04:00
c6a7be63b8
fix crash in generate._transparency_check_and_warning()
2022-10-06 21:00:27 -04:00
75165957c9
Revert "realesrgan inherits precision setting from main program"
...
This reverts commit 5f42d08945#939 , in which ESRGAN generates
dark images when upscaling 4X on certain GTX cards. However, the fix
apparently causes conflicts with some versions of the ESRGAN library,
and this fix will have to wait until after release of 2.0.
2022-10-06 20:52:38 -04:00
d60df54f69
fix k_samplers in img2img - probably correct now
2022-10-06 18:53:54 -04:00
82481a6f9c
Merge branch 'release-candidate-2' of github.com:invoke-ai/InvokeAI into release-candidate-2
2022-10-06 13:58:53 -04:00
90d64388ab
Merge branch 'release-candidate-2' into release-candidate-2
...
- This includes #949 "Bug fixes for new Threshold and Perlin Options"
2022-10-06 13:57:43 -04:00
3444c8e6b8
Merge branch 'release-candidate-2' into release-candidate-2
2022-10-06 13:53:27 -04:00
d84321e080
Adds hotkeys to modal
2022-10-06 13:49:09 -04:00
6542556ebd
Adds next/prev image buttons/hotkeys
2022-10-06 13:48:59 -04:00
70bbb670ec
Add Basic Hotkey Support
2022-10-06 13:27:42 -04:00
5f42d08945
realesrgan inherits precision setting from main program
2022-10-06 12:23:30 -04:00
911c99f125
Fix WebUI CORS Issue
2022-10-06 11:17:48 -04:00
2154dd2349
prevent crashes due to uninitialized free_gpu_mem
2022-10-06 10:54:05 -04:00
f3050fefce
bug and warning message fixes
...
- txt2img2img back to using DDIM as img2img sampler; results produced
by some k* samplers are just not reliable enough for good user
experience
- img2img progress message clarifies why img2img steps taken != steps requested
- warn of potential problems when user tries to run img2img on a small init image
2022-10-06 10:39:08 -04:00
183b98384f
set perlin & threshold to zero on generator initialization
2022-10-06 09:35:04 -04:00
6d475ee290
* Bug fixes for new Threshold and Perlin options
2022-10-06 08:46:27 -04:00
2f29b78a00
enable --hires to use k* samplers
2022-10-05 17:18:32 -04:00
