e5ecdfdd2d
Make fast previews for SDXL a little better by adding a bias.
2024-10-06 19:27:04 -04:00
7d29fbf74b
Slightly improve the fast previews for flux by adding a bias.
2024-10-06 17:55:46 -04:00
2c641e64ad
IS_CHANGED should be a classmethod ( #5159 )
2024-10-06 05:47:51 -04:00
7d2467e830
Some minor cleanups.
2024-10-05 13:22:39 -04:00
6f021d8aa0
Let --verbose have an argument for the log level.
2024-10-04 10:05:34 -04:00
d854ed0bcf
Allow using SD3 type te output on flux model.
2024-10-03 09:44:54 -04:00
abcd006b8c
Allow more permutations of clip/t5 in dual clip loader.
2024-10-03 09:26:11 -04:00
d985d1d7dc
CLIP Loader node now supports clip_l and clip_g only for SD3.
2024-10-02 04:25:17 -04:00
d1cdf51e1b
Refactor some of the TE detection code.
2024-10-01 07:08:41 -04:00
b4626ab93e
Add simpletuner lycoris format for SD unet.
2024-09-30 06:03:27 -04:00
a9e459c2a4
Use torch.nn.functional.linear in RGB preview code.
...
Add an optional bias to the latent RGB preview code.
2024-09-29 11:27:49 -04:00
3bb4dec720
Fix issue with loras, lowvram and --fast fp8.
2024-09-28 14:42:32 -04:00
8733191563
Flux torch.compile fix ( #5082 )
2024-09-27 22:07:51 -04:00
83b01f960a
Add backend option to TorchCompileModel.
...
If you want to use the cudagraphs backend you need to: --disable-cuda-malloc
If you get other backends working feel free to make a PR to add them.
2024-09-27 02:12:37 -04:00
d72e871cfa
Add a note that the experimental model downloader api will be removed.
2024-09-26 03:17:52 -04:00
037c3159b6
Move some nodes out of _for_testing.
2024-09-25 08:41:22 -04:00
bdd4a22a2e
Fix flux TE not loading t5 embeddings.
2024-09-24 22:57:22 -04:00
fdf37566ef
Add batch size to EmptyLatentAudio.
2024-09-24 04:32:55 -04:00
08c8968482
Internal download API: Add proper validated directory input ( #4981 )
...
* add internal /folder_paths route
returns a json maps of folder paths
* (minor) format download_models.py
* initial folder path input on download api
* actually, require folder_path and clean up some code
* partial tests update
* fix & logging
* also download to a tmp file not the live file
to avoid compounding errors from network failure
* update tests again
* test tweaks
* workaround the first tests blocker
* fix file handling in tests
* rewrite test for create_model_path
* minor doc fix
* avoid 'mock_directory'
use temp dir to avoid accidental fs pollution from tests
2024-09-24 03:50:45 -04:00
479a427a48
Add dpmpp_2m_cfg_pp ( #4992 )
2024-09-24 02:42:56 -04:00
3a0eeee320
Make --listen listen on both ipv4 and ipv6 at the same time by default.
2024-09-23 04:38:19 -04:00
447da7ea86
Support listening on multiple addresses.
2024-09-23 04:36:59 -04:00
9c41bc8d10
Remove useless line.
2024-09-23 02:32:29 -04:00
6ad0ddbae4
Run unit tests on Windows/MacOS as well. ( #5018 )
...
* Run unit tests on Windows as well.
* Test on mac.
* Continue running on error.
* Compared normalized paths to work cross platform.
* Only test common set of mimetypes across operating systems.
2024-09-22 05:01:39 -04:00
a55142f904
Add ws.close() to the websocket examples ( #5020 )
...
* add ws.close() to websocket examples
* add and explain ws.close() in websocket examples
2024-09-22 04:59:10 -04:00
5718ef69bb
Add total and free ram to /system_stats.
2024-09-22 03:42:11 -04:00
13ecf10a92
Added to the websockets_api_example.py to show how to decode latent previews from the binary stream ( #5016 )
...
* Update websockets_api_example.py
* even more simplfied
2024-09-22 02:30:44 -04:00
7a415f47a9
Add an optional VAE input to the ControlNetApplyAdvanced node.
...
Deprecate the other controlnet nodes.
2024-09-22 01:24:52 -04:00
89fa2fca24
Update web content to release v1.2.60 ( #5017 )
...
* Update web content to release v1.2.60
* Remove dist.zip
2024-09-21 23:28:54 -04:00
364b69e931
Make SD3 empty latent image zeros.
...
This shouldn't change anything. The reason it was not zeros is because it
did matter in early versions of the code.
2024-09-21 09:13:10 -04:00
dc96a1ae19
Load controlnet in fp8 if weights are in fp8.
2024-09-21 04:50:12 -04:00
2d810b081e
Add load_controlnet_state_dict function.
2024-09-21 01:51:51 -04:00
9f7e9f0547
Add an error message when a controlnet needs a VAE but none is given.
2024-09-21 01:33:18 -04:00
a355f38ecc
Make the SD3 controlnet node the default one.
2024-09-21 01:32:46 -04:00
38c69080c7
Add docstring
2024-09-20 03:16:23 -04:00
70a708d726
Fix model merging issue.
2024-09-20 02:31:44 -04:00
e7d4782736
add laplace scheduler [2407.03297] ( #4990 )
...
* add laplace scheduler [2407.03297]
* should be here instead lol
* better settings
2024-09-19 23:23:09 -04:00
3326bdfd4e
add internal /folder_paths route ( #4980 )
...
returns a json maps of folder paths
2024-09-19 09:52:55 -04:00
68bb885d22
add 'is_default' to model paths config ( #4979 )
...
* add 'is_default' to model paths config
including impl and doc in example file
* update weirdly overspecific test expectations
* oh there's two
* sigh
2024-09-19 08:59:55 -04:00
ad66f7c7d8
Add model_options to load_controlnet function.
2024-09-19 08:23:35 -04:00
de8e8e3b0d
Fix xpu Pytorch nightly build from calling optimize which doesn't exist. ( #4978 )
2024-09-19 05:11:42 -04:00
a1e71cfad1
very simple strong-cache on model list ( #4969 )
...
* very simple strong-cache on model list
* store the cache after validation too
* only cache object_info for now
* use a 'with' context
2024-09-19 04:40:14 -04:00
0bfc7cc998
Create the temp directory on ComfyUI startup instead.
2024-09-18 09:55:57 -04:00
7183fd1665
Add route to list model types ( #4846 )
...
* Add list models route
* Better readable model types list
2024-09-17 04:22:05 -04:00
254838f23c
add simple error check to model loading ( #4950 )
2024-09-17 03:57:17 -04:00
0b7dfa986d
Improve tiling calculations to reduce number of tiles that need to be processed. ( #4944 )
2024-09-17 03:51:10 -04:00
d514bb38ee
Add some option to model_options for the text encoder.
...
load_device, offload_device and the initial_device can now be set.
2024-09-17 03:49:54 -04:00
0849c80e2a
get_key_patches now works without unloading the model.
2024-09-17 01:57:59 -04:00
56e8f5e4fd
VAEDecodeAudio now does some normalization on the audio.
2024-09-16 00:30:36 -04:00
e813abbb2c
Long CLIP L support for SDXL, SD3 and Flux.
...
Use the *CLIPLoader nodes.
2024-09-15 07:59:38 -04:00
comfyanonymous
Lex
City
Alex "mcmonkey" Goodwin
chaObserv
Robin Huang
RandomGitUser321
Chenlei Hu
yoinked
Simon Lui
Tom
pharmapsychotic