comfyanonymous
255edf2246
Lower minimum ratio of loaded weights on Nvidia.
2025-01-27 05:26:51 -05:00
patientx
1442e34d9e
Merge branch 'comfyanonymous:master' into master
2025-01-26 15:27:37 +03:00
comfyanonymous
67feb05299
Remove redundant code.
2025-01-25 19:04:53 -05:00
patientx
c4861c74d4
UPDATED ZLUDA PATCHING METHOD
2025-01-14 19:57:22 +03:00
patientx
a5a09e45dd
Merge branch 'comfyanonymous:master' into master
2025-01-04 15:42:12 +03:00
comfyanonymous
d45ebb63f6
Remove old unused function.
2025-01-04 07:20:54 -05:00
patientx
c523c36aef
Merge branch 'comfyanonymous:master' into master
2025-01-02 19:55:49 +03:00
comfyanonymous
9e9c8a1c64
Clear cache as often on AMD as Nvidia.
...
I think the issue this was working around has been solved.
If you notice that this change slows things down or causes stutters on
your AMD GPU with ROCm on Linux please report it.
2025-01-02 08:44:16 -05:00
patientx
4590f75633
Merge branch 'comfyanonymous:master' into master
2024-12-27 09:59:51 +03:00
comfyanonymous
160ca08138
Use python 3.9 in launch test instead of 3.8
...
Fix ruff check.
2024-12-26 20:05:54 -05:00
Huazhong Ji
c4bfdba330
Support ascend npu ( #5436 )
...
* support ascend npu
Co-authored-by: YukMingLaw <lymmm2@163.com>
Co-authored-by: starmountain1997 <guozr1997@hotmail.com>
Co-authored-by: Ginray <ginray0215@gmail.com>
2024-12-26 19:36:50 -05:00
patientx
49fa16cc7a
Merge branch 'comfyanonymous:master' into master
2024-12-25 14:05:18 +03:00
comfyanonymous
19a64d6291
Cleanup some mac related code.
2024-12-25 05:32:51 -05:00
comfyanonymous
b486885e08
Disable bfloat16 on older mac.
2024-12-25 05:18:50 -05:00
comfyanonymous
0229228f3f
Clean up the VAE dtypes code.
2024-12-25 04:50:34 -05:00
patientx
00afa8b34f
Merge branch 'comfyanonymous:master' into master
2024-12-23 11:36:49 +03:00
comfyanonymous
15564688ed
Add a try except block so if torch version is weird it won't crash.
2024-12-23 03:22:48 -05:00
Simon Lui
c6b9c11ef6
Add oneAPI device selector for xpu and some other changes. ( #6112 )
...
* Add oneAPI device selector and some other minor changes.
* Fix device selector variable name.
* Flip minor version check sign.
* Undo changes to README.md.
2024-12-23 03:18:32 -05:00
patientx
403a081215
Merge branch 'comfyanonymous:master' into master
2024-12-23 10:33:06 +03:00
comfyanonymous
e44d0ac7f7
Make --novram completely offload weights.
...
This flag is mainly used for testing the weight offloading, it shouldn't
actually be used in practice.
Remove useless import.
2024-12-23 01:51:08 -05:00
patientx
e9d8cad2f0
Merge branch 'comfyanonymous:master' into master
2024-12-22 16:56:29 +03:00
comfyanonymous
57f330caf9
Relax minimum ratio of weights loaded in memory on nvidia.
...
This should make it possible to do higher res images/longer videos by
further offloading weights to CPU memory.
Please report an issue if this slows down things on your system.
2024-12-22 03:06:37 -05:00
patientx
37fc9a3ff2
Merge branch 'comfyanonymous:master' into master
2024-12-21 00:37:40 +03:00
Chenlei Hu
d7969cb070
Replace print with logging ( #6138 )
...
* Replace print with logging
* nit
* nit
* nit
* nit
* nit
* nit
2024-12-20 16:24:55 -05:00
patientx
ebf13dfe56
Merge branch 'comfyanonymous:master' into master
2024-12-20 10:05:56 +03:00
comfyanonymous
2dda7c11a3
More proper fix for the memory issue.
2024-12-19 16:21:56 -05:00
comfyanonymous
3ad3248ad7
Fix lowvram bug when using a model multiple times in a row.
...
The memory system would load an extra 64MB each time until either the
model was completely in memory or OOM.
2024-12-19 16:04:56 -05:00
patientx
c062723ca5
Merge branch 'comfyanonymous:master' into master
2024-12-18 10:16:43 +03:00
comfyanonymous
37e5390f5f
Add: --use-sage-attention to enable SageAttention.
...
You need to have the library installed first.
2024-12-18 01:56:10 -05:00
patientx
3218ed8559
Merge branch 'comfyanonymous:master' into master
2024-12-13 11:21:47 +03:00
Chenlei Hu
d9d7f3c619
Lint all unused variables ( #5989 )
...
* Enable F841
* Autofix
* Remove all unused variable assignment
2024-12-12 17:59:16 -05:00
patientx
5d059779d3
Merge branch 'comfyanonymous:master' into master
2024-12-12 15:26:42 +03:00
comfyanonymous
fd5dfb812c
Set initial load devices for te and model to mps device on mac.
2024-12-12 06:00:31 -05:00
patientx
b826d3e8c2
Merge branch 'comfyanonymous:master' into master
2024-12-03 14:51:59 +03:00
comfyanonymous
57e8bf6a9f
Fix case where a memory leak could cause crash.
...
Now the only symptom of code messing up and keeping references to a model
object when it should not will be endless prints in the log instead of the
next workflow crashing ComfyUI.
2024-12-02 19:49:49 -05:00
patientx
1d7cbcdcb2
Update model_management.py
2024-12-03 01:35:06 +03:00
patientx
9dea868c65
Reapply "Merge branch 'comfyanonymous:master' into master"
...
This reverts commit f3968d1611
2024-12-03 00:45:31 +03:00
patientx
f3968d1611
Revert "Merge branch 'comfyanonymous:master' into master"
...
This reverts commit 605425bdd674e6ad95f7
2024-12-03 00:10:22 +03:00
patientx
605425bdd6
Merge branch 'comfyanonymous:master' into master
2024-12-02 23:10:52 +03:00
comfyanonymous
79d5ceae6e
Improved memory management. ( #5450 )
...
* Less fragile memory management.
* Fix issue.
* Remove useless function.
* Prevent and detect some types of memory leaks.
* Run garbage collector when switching workflow if needed.
* Fix issue.
2024-12-02 14:39:34 -05:00
patientx
fc8f411fa8
Merge branch 'comfyanonymous:master' into master
2024-11-25 13:31:28 +03:00
comfyanonymous
61196d8857
Add option to inference the diffusion model in fp32 and fp64.
2024-11-25 05:00:23 -05:00
patientx
4526136e42
Merge branch 'comfyanonymous:master' into master
2024-11-01 13:16:45 +03:00
comfyanonymous
1af4a47fd1
Bump up mac version for attention upcast bug workaround.
2024-10-31 15:15:31 -04:00
patientx
5a425aeda1
Merge branch 'comfyanonymous:master' into master
2024-10-20 21:06:24 +03:00
comfyanonymous
471cd3eace
fp8 casting is fast on GPUs that support fp8 compute.
2024-10-20 00:54:47 -04:00
patientx
d4b509799f
Merge branch 'comfyanonymous:master' into master
2024-10-18 11:14:20 +03:00
comfyanonymous
67158994a4
Use the lowvram cast_to function for everything.
2024-10-17 17:25:56 -04:00
patientx
f9eab05f54
Merge branch 'comfyanonymous:master' into master
2024-10-10 10:30:17 +03:00
Jonathan Avila
4b2f0d9413
Increase maximum macOS version to 15.0.1 when forcing upcast attention ( #5191 )
2024-10-09 22:21:41 -04:00
comfyanonymous
e38c94228b
Add a weight_dtype fp8_e4m3fn_fast to the Diffusion Model Loader node.
...
This is used to load weights in fp8 and use fp8 matrix multiplication.
2024-10-09 19:43:17 -04:00
patientx
ae611c9b61
Merge branch 'comfyanonymous:master' into master
2024-09-21 13:51:37 +03:00
comfyanonymous
dc96a1ae19
Load controlnet in fp8 if weights are in fp8.
2024-09-21 04:50:12 -04:00
patientx
9e8686df8d
Merge branch 'comfyanonymous:master' into master
2024-09-19 19:57:21 +03:00
Simon Lui
de8e8e3b0d
Fix xpu Pytorch nightly build from calling optimize which doesn't exist. ( #4978 )
2024-09-19 05:11:42 -04:00
patientx
6fdbaf1a76
Merge branch 'comfyanonymous:master' into master
2024-09-05 12:04:05 +03:00
comfyanonymous
c7427375ee
Prioritize freeing partially offloaded models first.
2024-09-04 19:47:32 -04:00
patientx
894c727ce2
Update model_management.py
2024-09-05 00:05:54 +03:00
patientx
93fa5c9ebb
Merge branch 'comfyanonymous:master' into master
2024-09-02 10:03:48 +03:00
comfyanonymous
8d31a6632f
Speed up inference on nvidia 10 series on Linux.
2024-09-01 17:29:31 -04:00
patientx
f02c0d3ed9
Merge branch 'comfyanonymous:master' into master
2024-09-01 14:34:56 +03:00
comfyanonymous
b643eae08b
Make minimum_inference_memory() depend on --reserve-vram
2024-09-01 01:18:34 -04:00
patientx
acc3d6a2ea
Update model_management.py
2024-08-30 20:13:28 +03:00
patientx
51af2440ef
Update model_management.py
2024-08-30 20:10:47 +03:00
patientx
3e226f02f3
Update model_management.py
2024-08-30 20:08:18 +03:00
comfyanonymous
935ae153e1
Cleanup.
2024-08-30 12:53:59 -04:00
patientx
7056a6aa6f
Merge branch 'comfyanonymous:master' into master
2024-08-28 09:36:30 +03:00
comfyanonymous
38c22e631a
Fix case where model was not properly unloaded in merging workflows.
2024-08-27 19:03:51 -04:00
patientx
134569ea48
Update model_management.py
2024-08-23 14:10:09 +03:00
patientx
c98e8a0a55
Merge branch 'comfyanonymous:master' into master
2024-08-23 12:31:51 +03:00
comfyanonymous
5d8bbb7281
Cleanup.
2024-08-23 04:06:27 -04:00
patientx
9f87d61bfe
Merge branch 'comfyanonymous:master' into master
2024-08-23 11:04:56 +03:00
comfyanonymous
2c1d2375d6
Fix.
2024-08-23 04:04:55 -04:00
Simon Lui
64ccb3c7e3
Rework IPEX check for future inclusion of XPU into Pytorch upstream and do a bit more optimization of ipex.optimize(). ( #4562 )
2024-08-23 03:59:57 -04:00
patientx
1ef90b7ac8
Merge branch 'comfyanonymous:master' into master
2024-08-23 00:55:19 +03:00
comfyanonymous
7c6bb84016
Code cleanups.
2024-08-22 17:05:12 -04:00
patientx
dec75f11e4
Merge branch 'comfyanonymous:master' into master
2024-08-22 23:36:58 +03:00
comfyanonymous
c54d3ed5e6
Fix issue with models staying loaded in memory.
2024-08-22 15:58:20 -04:00
David
7b70b266d8
Generalize MacOS version check for force-upcast-attention ( #4548 )
...
This code automatically forces upcasting attention for MacOS versions 14.5 and 14.6. My computer returns the string "14.6.1" for `platform.mac_ver()[0]`, so this generalizes the comparison to catch more versions.
I am running MacOS Sonoma 14.6.1 (latest version) and was seeing black image generation on previously functional workflows after recent software updates. This PR solved the issue for me.
See comfyanonymous/ComfyUI#3521
2024-08-22 13:24:21 -04:00
patientx
0cd8a740bb
Merge branch 'comfyanonymous:master' into master
2024-08-22 14:01:42 +03:00
comfyanonymous
843a7ff70c
fp16 is actually faster than fp32 on a GTX 1080.
2024-08-21 23:23:50 -04:00
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
patientx
ac75d4e4e0
Merge branch 'comfyanonymous:master' into master
2024-08-21 09:49:29 +03:00
comfyanonymous
03ec517afb
Remove useless line, adjust windows default reserved vram.
2024-08-21 00:47:19 -04:00
patientx
5656b5b956
Merge branch 'comfyanonymous:master' into master
2024-08-20 23:07:54 +03:00
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
1b3eee672c
Fix potential issue with multi devices.
2024-08-20 10:46:36 -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
be0726c1ed
Remove duplication.
2024-08-19 15:26:50 -04:00
patientx
7bd86b0896
Update model_management.py
2024-08-16 00:53:38 +03:00
comfyanonymous
39fb74c5bd
Fix bug when model cannot be partially unloaded.
2024-08-13 03:57:55 -04:00
comfyanonymous
74e124f4d7
Fix some issues with TE being in lowvram mode.
2024-08-12 23:42:21 -04:00
comfyanonymous
b8ffb2937f
Memory tweaks.
2024-08-12 15:07:11 -04:00
comfyanonymous
ad76574cb8
Fix some potential issues with the previous commits.
2024-08-12 00:23:29 -04:00
comfyanonymous
5c69cde037
Load TE model straight to vram if certain conditions are met.
2024-08-11 23:52:43 -04:00
comfyanonymous
1de69fe4d5
Fix some issues with inference slowing down.
2024-08-10 16:21:25 -04:00
comfyanonymous
55ad9d5f8c
Fix regression.
2024-08-09 03:36:40 -04:00
comfyanonymous
037c38eb0f
Try to improve inference speed on some machines.
2024-08-08 17:29:27 -04:00
comfyanonymous
66d4233210
Fix.
2024-08-08 15:16:51 -04:00
comfyanonymous
08f92d55e9
Partial model shift support.
2024-08-08 14:45:06 -04:00
comfyanonymous
6969fc9ba4
Make supported_dtypes a priority list.
2024-08-07 15:00:06 -04:00
comfyanonymous
b334605a66
Fix OOMs happening in some cases.
...
A cloned model patcher sometimes reported a model was loaded on a device
when it wasn't.
2024-08-06 13:36:04 -04:00
comfyanonymous
c14ac98fed
Unload models and load them back in lowvram mode no free vram.
2024-08-06 03:22:39 -04:00
comfyanonymous
8edbcf5209
Improve performance on some lowend GPUs.
2024-08-05 16:24:04 -04:00
comfyanonymous
f7a5107784
Fix crash.
2024-08-03 16:55:38 -04:00
comfyanonymous
91be9c2867
Tweak lowvram memory formula.
2024-08-03 16:44:50 -04:00
comfyanonymous
03c5018c98
Lower lowvram memory to 1/3 of free memory.
2024-08-03 15:14:07 -04:00
comfyanonymous
2ba5cc8b86
Fix some issues.
2024-08-03 15:06:40 -04:00
comfyanonymous
1e68002b87
Cap lowvram to half of free memory.
2024-08-03 14:50:20 -04:00
comfyanonymous
ba9095e5bd
Automatically use fp8 for diffusion model weights if:
...
Checkpoint contains weights in fp8.
There isn't enough memory to load the diffusion model in GPU vram.
2024-08-03 13:45:19 -04:00
comfyanonymous
d965474aaa
Make ComfyUI split batches a higher priority than weight offload.
2024-08-01 16:39:59 -04:00
comfyanonymous
a6decf1e62
Fix bfloat16 potentially not being enabled on mps.
2024-08-01 16:18:44 -04:00
comfyanonymous
1aa9cf3292
Make lowvram more aggressive on low memory machines.
2024-08-01 12:11:57 -04:00
comfyanonymous
5f98de7697
Load flux t5 in fp8 if weights are in fp8.
2024-08-01 11:05:56 -04:00
comfyanonymous
7ad574bffd
Mac supports bf16 just make sure you are using the latest pytorch.
2024-08-01 09:42:17 -04:00
comfyanonymous
e2382b6adb
Make lowvram less aggressive when there are large amounts of free memory.
2024-08-01 03:58:58 -04:00
comfyanonymous
6425252c4f
Use fp16 as the default vae dtype for the audio VAE.
2024-06-16 13:12:54 -04:00
comfyanonymous
0ec513d877
Add a --force-channels-last to inference models in channel last mode.
2024-06-15 01:08:12 -04:00
Simon Lui
5eb98f0092
Exempt IPEX from non_blocking previews fixing segmentation faults. ( #3708 )
2024-06-13 18:51:14 -04:00
comfyanonymous
0e49211a11
Load the SD3 T5xxl model in the same dtype stored in the checkpoint.
2024-06-11 17:03:26 -04:00
comfyanonymous
104fcea0c8
Add function to get the list of currently loaded models.
2024-06-05 23:25:16 -04:00
comfyanonymous
b1fd26fe9e
pytorch xpu should be flash or mem efficient attention?
2024-06-04 17:44:14 -04:00
comfyanonymous
b249862080
Add an annoying print to a function I want to remove.
2024-06-01 12:47:31 -04:00
comfyanonymous
bf3e334d46
Disable non_blocking when --deterministic or directml.
2024-05-30 11:07:38 -04:00
comfyanonymous
0920e0e5fe
Remove some unused imports.
2024-05-27 19:08:27 -04:00
comfyanonymous
6c23854f54
Fix OSX latent2rgb previews.
2024-05-22 13:56:28 -04:00
comfyanonymous
8508df2569
Work around black image bug on Mac 14.5 by forcing attention upcasting.
2024-05-21 16:56:33 -04:00
comfyanonymous
09e069ae6c
Log the pytorch version.
2024-05-20 06:22:29 -04:00
comfyanonymous
19300655dd
Don't automatically switch to lowvram mode on GPUs with low memory.
2024-05-17 00:31:32 -04:00
Simon Lui
f509c6fe21
Fix Intel GPU memory allocation accuracy and documentation update. ( #3459 )
...
* Change calculation of memory total to be more accurate, allocated is actually smaller than reserved.
* Update README.md install documentation for Intel GPUs.
2024-05-12 06:36:30 -04:00
comfyanonymous
fa6dd7e5bb
Fix lowvram issue with saving checkpoints.
...
The previous fix didn't cover the case where the model was loaded in
lowvram mode right before.
2024-05-12 06:13:45 -04:00
comfyanonymous
49c20cdc70
No longer necessary.
2024-05-12 05:34:43 -04:00
comfyanonymous
e1489ad257
Fix issue with lowvram mode breaking model saving.
2024-05-11 21:55:20 -04:00
Simon Lui
a56d02efc7
Change torch.xpu to ipex.optimize, xpu device initialization and remove workaround for text node issue from older IPEX. ( #3388 )
2024-05-02 03:26:50 -04:00
comfyanonymous
258dbc06c3
Fix some memory related issues.
2024-04-14 12:08:58 -04:00
comfyanonymous
0a03009808
Fix issue with controlnet models getting loaded multiple times.
2024-04-06 18:38:39 -04:00
comfyanonymous
5d8898c056
Fix some performance issues with weight loading and unloading.
...
Lower peak memory usage when changing model.
Fix case where model weights would be unloaded and reloaded.
2024-03-28 18:04:42 -04:00
comfyanonymous
c6de09b02e
Optimize memory unload strategy for more optimized performance.
2024-03-24 02:36:30 -04:00
comfyanonymous
4b9005e949
Fix regression with model merging.
2024-03-20 13:56:12 -04:00
comfyanonymous
c18a203a8a
Don't unload model weights for non weight patches.
2024-03-20 02:27:58 -04:00
comfyanonymous
db8b59ecff
Lower memory usage for loras in lowvram mode at the cost of perf.
2024-03-13 20:07:27 -04:00
comfyanonymous
0ed72befe1
Change log levels.
...
Logging level now defaults to info. --verbose sets it to debug.
2024-03-11 13:54:56 -04:00
comfyanonymous
65397ce601
Replace prints with logging and add --verbose argument.
2024-03-10 12:14:23 -04:00
comfyanonymous
dce3555339
Add some tesla pascal GPUs to the fp16 working but slower list.
2024-03-02 17:16:31 -05:00
comfyanonymous
88f300401c
Enable fp16 by default on mps.
2024-02-19 12:00:48 -05:00
comfyanonymous
929e266f3e
Manual cast for bf16 on older GPUs.
2024-02-17 09:01:17 -05:00
comfyanonymous
0b3c50480c
Make --force-fp32 disable loading models in bf16.
2024-02-16 23:01:54 -05:00
comfyanonymous
f83109f09b
Stable Cascade Stage C.
2024-02-16 10:55:08 -05:00
