patientx
febf8601dc
Merge branch 'comfyanonymous:master' into master
2024-08-22 00:07:14 +03:00
comfyanonymous
a60620dcea
Fix slow performance on 10 series Nvidia GPUs.
2024-08-21 16:39:02 -04:00
comfyanonymous
015f73dc49
Try a different type of flux fp16 fix.
2024-08-21 16:17:15 -04:00
comfyanonymous
904bf58e7d
Make --fast work on pytorch nightly.
2024-08-21 14:01:41 -04:00
patientx
0774774bb9
Merge branch 'comfyanonymous:master' into master
2024-08-21 19:19:41 +03:00
Svein Ove Aas
5f50263088
Replace use of .view with .reshape ( #4522 )
...
When generating images with fp8_e4_m3 Flux and batch size >1, using --fast, ComfyUI throws a "view size is not compatible with input tensor's size and stride" error pointing at the first of these two calls to view.
As reshape is semantically equivalent to view except for working on a broader set of inputs, there should be no downside to changing this. The only difference is that it clones the underlying data in cases where .view would error out. I have confirmed that the output still looks as expected, but cannot confirm that no mutable use is made of the tensors anywhere.
Note that --fast is only marginally faster than the default.
2024-08-21 11:21:48 -04:00
patientx
ac75d4e4e0
Merge branch 'comfyanonymous:master' into master
2024-08-21 09:49:29 +03:00
Alex "mcmonkey" Goodwin
5e806f555d
add a get models list api route ( #4519 )
...
* get models list api route
* remove copypasta
2024-08-21 02:04:42 -04:00
Robin Huang
f07e5bb522
Add GET /internal/files. ( #4295 )
...
* Create internal route table.
* List files.
* Add GET /internal/files.
Retrieves list of files in models, output, and user directories.
* Refactor file names.
* Use typing_extensions for Python 3.8
* Fix tests.
* Remove print statements.
* Update README.
* Add output and user to valid directory test.
* Add missing type hints.
2024-08-21 01:25:06 -04:00
comfyanonymous
03ec517afb
Remove useless line, adjust windows default reserved vram.
2024-08-21 00:47:19 -04:00
Chenlei Hu
f257fc999f
Add optional deprecated/experimental flag to node class ( #4506 )
...
* Add optional deprecated flag to node class
* nit
* Add experimental flag
2024-08-21 00:01:34 -04:00
Chenlei Hu
bb50e69839
Update frontend to 1.2.30 ( #4513 )
2024-08-21 00:00:49 -04:00
comfyanonymous
510f3438c1
Speed up fp8 matrix mult by using better code.
2024-08-20 22:53:26 -04:00
patientx
5656b5b956
Merge branch 'comfyanonymous:master' into master
2024-08-20 23:07:54 +03:00
comfyanonymous
ea63b1c092
Simpletrainer lycoris format.
2024-08-20 12:05:13 -04:00
comfyanonymous
9953f22fce
Add --fast argument to enable experimental optimizations.
...
Optimizations that might break things/lower quality will be put behind
this flag first and might be enabled by default in the future.
Currently the only optimization is float8_e4m3fn matrix multiplication on
4000/ADA series Nvidia cards or later. If you have one of these cards you
will see a speed boost when using fp8_e4m3fn flux for example.
2024-08-20 11:55:51 -04:00
comfyanonymous
d1a6bd6845
Support loading long clipl model with the CLIP loader node.
2024-08-20 10:46:36 -04:00
comfyanonymous
83dbac28eb
Properly set if clip text pooled projection instead of using hack.
2024-08-20 10:46:36 -04:00
comfyanonymous
538cb068bc
Make cast_to a nop if weight is already good.
2024-08-20 10:46:36 -04:00
comfyanonymous
1b3eee672c
Fix potential issue with multi devices.
2024-08-20 10:46:36 -04:00
patientx
c65daa891b
Update README.md
2024-08-20 12:35:48 +03:00
patientx
9727da93ea
Merge branch 'comfyanonymous:master' into master
2024-08-20 12:35:06 +03:00
patientx
68fa90e4e2
Update README.md
2024-08-20 12:34:58 +03:00
Chenlei Hu
5a69f84c3c
Update README.md (Add shield badges) ( #4490 )
2024-08-19 18:25:20 -04:00
comfyanonymous
9eee470244
New load_text_encoder_state_dicts function.
...
Now you can load text encoders straight from a list of state dicts.
2024-08-19 17:36:35 -04:00
patientx
b20f5b1e32
Merge branch 'comfyanonymous:master' into master
2024-08-20 00:31:41 +03:00
comfyanonymous
045377ea89
Add a --reserve-vram argument if you don't want comfy to use all of it.
...
--reserve-vram 1.0 for example will make ComfyUI try to keep 1GB vram free.
This can also be useful if workflows are failing because of OOM errors but
in that case please report it if --reserve-vram improves your situation.
2024-08-19 17:16:18 -04:00
comfyanonymous
4d341b78e8
Bug fixes.
2024-08-19 16:28:55 -04:00
patientx
9baf36e97b
Merge branch 'comfyanonymous:master' into master
2024-08-19 22:54:45 +03:00
comfyanonymous
6138f92084
Use better dtype for the lowvram lora system.
2024-08-19 15:35:25 -04:00
comfyanonymous
be0726c1ed
Remove duplication.
2024-08-19 15:26:50 -04:00
comfyanonymous
766ae119a8
CheckpointSave node name.
2024-08-19 15:06:12 -04:00
Yoland Yan
fc90ceb6ba
Update issue template config.yml to direct frontend issues to frontend repos ( #4486 )
...
* Update config.yml
* Typos
2024-08-19 13:41:30 -04:00
comfyanonymous
4506ddc86a
Better subnormal fp8 stochastic rounding. Thanks Ashen.
2024-08-19 13:38:03 -04:00
comfyanonymous
20ace7c853
Code cleanup.
2024-08-19 12:48:59 -04:00
patientx
e863115df2
Update README.md
2024-08-19 17:21:04 +03:00
patientx
74c8545fa6
Merge branch 'comfyanonymous:master' into master
2024-08-19 17:20:41 +03:00
patientx
902ff65ce8
Update README.md
2024-08-19 17:20:34 +03:00
Chenlei Hu
b29b3b86c5
Update README to include frontend section ( #4468 )
...
* Update README to include frontend section
* nit
2024-08-19 07:12:32 -04:00
comfyanonymous
22ec02afc0
Handle subnormal numbers in float8 rounding.
2024-08-19 05:51:08 -04:00
patientx
eb8d7f86d1
Merge branch 'comfyanonymous:master' into master
2024-08-19 10:02:52 +03:00
comfyanonymous
39f114c44b
Less broken non blocking?
2024-08-18 16:53:17 -04:00
patientx
a09513099a
Merge branch 'comfyanonymous:master' into master
2024-08-18 23:49:55 +03:00
comfyanonymous
6730f3e1a3
Disable non blocking.
...
It fixed some perf issues but caused other issues that need to be debugged.
2024-08-18 14:38:09 -04:00
comfyanonymous
73332160c8
Enable non blocking transfers in lowvram mode.
2024-08-18 10:29:33 -04:00
patientx
30b7af51e9
Update README.md
2024-08-18 11:33:32 +03:00
patientx
b397f02669
Merge branch 'comfyanonymous:master' into master
2024-08-18 11:33:07 +03:00
patientx
5f467a5de8
Update README.md
2024-08-18 11:33:01 +03:00
comfyanonymous
2622c55aff
Automatically use RF variant of dpmpp_2s_ancestral if RF model.
2024-08-18 00:47:25 -04:00
Ashen
1beb348ee2
dpmpp_2s_ancestral_RF for rectified flow (Flux, SD3 and Auraflow).
2024-08-18 00:33:30 -04:00
