11e422cf29
Ignore two files names instead of the entire folder
...
rather than bypassing any path with diffusers in it, im specifically bypassing model.safetensors and diffusion_pytorch_model.safetensors both of which should be diffusers files in most cases.
2023-02-12 00:13:22 +13:00
7f695fed39
Ignore safetensor or ckpt files inside diffusers model folders.
...
Basically skips the path if the path has the word diffusers anywhere inside it.
2023-02-12 00:03:42 +13:00
310501cd8a
Add support for custom config files
2023-02-11 23:34:24 +13:00
106b3aea1b
Fix incorrect Windows env activation location
...
Change broken link to Contributing inside of Developer Install
Minor format modification to allow for numbered list to appear properly
2023-02-11 00:30:07 -08:00
6e52ca3307
Model Convert Component
2023-02-11 20:41:49 +13:00
94c31f672f
Add Initial Checks for Inpainting
...
The conversion itself is broken. But that's another issue.
2023-02-11 20:41:18 +13:00
240bbb9852
Merge branch 'main' into main
2023-02-11 01:17:42 +01:00
8cf2ed91a9
Merge branch 'main' into update/docker/include-dockerhub
2023-02-10 22:55:54 +01:00
7be5b4ca8b
update Dockerfile
...
- introduce build arg `VOLUME_DIR`
- fix permissions of the Volume
2023-02-10 22:55:19 +01:00
d589ad96aa
fix two bugs in conversion of inpaint models from ckpt to diffusers models
...
- If CLI asked to convert the currently loaded model, the model would crash
on the first rendering. CLI will now refuse to convert a model loaded
in memory (probably a good idea in any case).
- CLI will offer the `v1-inpainting-inference.yaml` as the configuration
file when importing an inpainting a .ckpt or .safetensors file that
has "inpainting" in the name. Otherwise it offers `v1-inference.yaml`
as the default.
2023-02-10 15:06:37 -05:00
097e41e8d2
2.3.0 Documentation Fixes ( #2609 )
...
Found a couple of places where the formatting was messed up. I also
added a "Quick Start Guide" to the README for people who encounter
InvokeAI through PyPi. It features the PyPi install!
2023-02-10 13:00:14 -05:00
4cf43b858d
update 020_INSTALL_MANUAL.md
...
- some formatting changes / fixes
- updates venv creation commands
- remove extra index from Mac Installations
2023-02-10 17:29:12 +01:00
13a4666a6e
update README.md
...
- fix some formatting issues
- fix command to create venv
- some other small updates
2023-02-10 16:27:21 +01:00
9232290950
Initial Implementation - Model Conversion Frontend
2023-02-11 03:53:31 +13:00
f3153d45bc
Initial Implementation - Model Conversion Backend
2023-02-11 03:53:15 +13:00
d9cb6da951
Merge branch 'main' into update/docker/include-dockerhub
2023-02-10 09:42:07 -05:00
17535d887f
Merge branch 'invoke-ai:main' into main
2023-02-10 07:58:28 +01:00
35da7f5b96
Merge branch 'main' into doc/manual-install-fixes
2023-02-09 21:55:21 -05:00
4e95a68582
adding support for ESRGAN denoising strength ( #2598 )
...
pulling in denoising support from upstream (its already there, invoke
just isn't using it). I've enabled this as a command line argument as
construction of the ESRGAN handler happens once. Ideally this would be a
UI option that could be adjusted for each upscaling task. Unfortunately
that is beyond my current level of InvokeAI-foo.
Upstream reference is here, starting on line 99 "use dni to control the
denoise strength"
https://github.com/xinntao/Real-ESRGAN/blob/master/inference_realesrgan.py
2023-02-09 21:55:00 -05:00
9dfeb93f80
add quick install instructions to README
2023-02-09 20:28:20 -05:00
02247ffc79
resolved build (denoise_str)
2023-02-10 14:12:21 +13:00
48da030415
resolving conflicts
2023-02-10 14:03:31 +13:00
817e04bee0
add quickstart instructions for PyPi
2023-02-09 19:37:04 -05:00
e5d0b0c37d
Formatting fixes, Manual Installation docs
...
Found a couple of places where the formatting was messed up. This corrects them.
2023-02-09 17:56:25 -05:00
950f450665
Merge branch 'main' into main
2023-02-10 11:52:26 +13:00
f5d1fbd896
Update main to release v2.3.0 ( #2608 )
...
# Release 2.3.0
This will bring `main` up to date with release 2.3.0. I will need
approvals from @mauwii (docs) and @blessedcoolant (for _version.py).
2023-02-09 17:28:55 -05:00
424cee63f1
Merge branch 'main' into release/2.3.0-last-tweaks
2023-02-09 16:36:51 -05:00
79daf8b039
clean build (esrgan-denoise-str)
2023-02-10 10:20:37 +13:00
383cbca896
lint-resolve
2023-02-10 10:16:55 +13:00
07c55d5e2a
adds upscaling denoising to metadata viewer
2023-02-10 07:30:17 +11:00
156151df45
build (esrgan-denoise-str)
2023-02-10 09:19:55 +13:00
03b1d71af9
Resolving Conflicts
2023-02-10 09:18:02 +13:00
da193ecd4a
ESLint EOL Fix
2023-02-10 09:11:07 +13:00
56fd202e21
builds frontend
2023-02-10 08:24:40 +13:00
29454a2974
Update generationSlice.ts
2023-02-10 08:24:40 +13:00
c977d295f5
Update generationSlice.ts
2023-02-10 08:24:40 +13:00
28eaffa188
Update generationSlice.ts
...
Added perlin noise state restoration.
2023-02-10 08:24:40 +13:00
3feff09fb3
fixes #2049 use threshold not setting correct value
2023-02-10 08:24:40 +13:00
158d1ef384
bump version number; update contributors
2023-02-09 13:01:08 -05:00
f6ad107fdd
Merge branch 'main' into update/ci/prepare-test-invoke-pip-for-queue
2023-02-09 08:48:06 +01:00
e2c392631a
build (esrgan-denoise-str)
2023-02-09 20:21:22 +13:00
4a1b4d63ef
Change denoise_str default to 0.75
2023-02-09 20:21:09 +13:00
83ecda977c
Add frontend UI for denoise_str for ESRGAN
2023-02-09 20:19:25 +13:00
9601febef8
Add denoise_str to ESRGARN - frontend server
2023-02-09 20:16:47 +13:00
0503680efa
Change denoise_str to an arg instead of a class variable
2023-02-09 20:16:23 +13:00
57ccec1df3
remove metadata to summary step since secret use
...
- This PR will also close #2593
2023-02-09 07:24:28 +01:00
22f3634481
Merge branch 'main' into update/docker/include-dockerhub
2023-02-09 07:18:45 +01:00
5590c73af2
Prettified Frontend
2023-02-09 19:16:36 +13:00
1f76b30e54
adding support for ESRGAN denoising strength, which allows for improved detail retention when upscaling photorelistic faces
2023-02-08 22:36:35 -06:00
4785a1cd05
Up version to 2.3.0-rc7 ( #2591 )
...
This brings `main` up to date with 2.3.0 release candidate 7.
2023-02-08 22:06:58 -05:00
