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
doctorpangloss
c34403b574
Fix invalid device here
2024-10-09 11:21:19 -07:00
doctorpangloss
bbe2ed330c
Memory management and compilation improvements
...
- Experimental support for sage attention on Linux
- Diffusers loader now supports model indices
- Transformers model management now aligns with updates to ComfyUI
- Flux layers correctly use unbind
- Add float8 support for model loading in more places
- Experimental quantization approaches from Quanto and torchao
- Model upscaling interacts with memory management better
This update also disables ROCm testing because it isn't reliable enough
on consumer hardware. ROCm is not really supported by the 7600.
2024-10-09 09:13:47 -07:00
doctorpangloss
d25394d386
API now supports fire-and-forget, checking on queue status; prefetch_count now expressly set to 1 for workers
2024-09-27 12:07:54 -07:00
doctorpangloss
fa3176f96f
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2024-09-23 12:50:31 -07:00
comfyanonymous
dc96a1ae19
Load controlnet in fp8 if weights are in fp8.
2024-09-21 04:50:12 -04:00
Simon Lui
de8e8e3b0d
Fix xpu Pytorch nightly build from calling optimize which doesn't exist. ( #4978 )
2024-09-19 05:11:42 -04:00
doctorpangloss
db423f8013
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2024-09-05 09:23:00 -07:00
comfyanonymous
c7427375ee
Prioritize freeing partially offloaded models first.
2024-09-04 19:47:32 -04:00
doctorpangloss
38bcd9fcbd
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2024-09-03 15:28:52 -07:00
comfyanonymous
8d31a6632f
Speed up inference on nvidia 10 series on Linux.
2024-09-01 17:29:31 -04:00
comfyanonymous
b643eae08b
Make minimum_inference_memory() depend on --reserve-vram
2024-09-01 01:18:34 -04:00
comfyanonymous
935ae153e1
Cleanup.
2024-08-30 12:53:59 -04:00
doctorpangloss
fd503d8a96
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2024-08-29 16:37:30 -07:00
comfyanonymous
38c22e631a
Fix case where model was not properly unloaded in merging workflows.
2024-08-27 19:03:51 -04:00
doctorpangloss
5155a3e248
Merge WIP
2024-08-25 18:52:29 -07:00
comfyanonymous
5d8bbb7281
Cleanup.
2024-08-23 04:06:27 -04:00
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
comfyanonymous
7c6bb84016
Code cleanups.
2024-08-22 17:05:12 -04:00
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
comfyanonymous
843a7ff70c
fp16 is actually faster than fp32 on a GTX 1080.
2024-08-21 23:23:50 -04:00
comfyanonymous
a60620dcea
Fix slow performance on 10 series Nvidia GPUs.
2024-08-21 16:39:02 -04:00
comfyanonymous
03ec517afb
Remove useless line, adjust windows default reserved vram.
2024-08-21 00:47:19 -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
1b3eee672c
Fix potential issue with multi devices.
2024-08-20 10:46:36 -04:00
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
doctorpangloss
7500d02af5
Improve language models and performance, adding a translation workflow example
2024-08-15 11:09:55 -07:00
doctorpangloss
0549f35e85
Merge commit '39fb74c5bd13a1dccf4d7293a2f7a755d9f43cbd' of github.com:comfyanonymous/ComfyUI
...
- Improvements to tests
- Fixes model management
- Fixes issues with language nodes
2024-08-13 20:08:56 -07:00
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
doctorpangloss
963ede9867
Fix catastrophic indentation bug
2024-08-06 23:14:24 -07:00
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
doctorpangloss
8ab6b4b697
Fix running on CPU again
2024-08-05 17:20:28 -07:00
doctorpangloss
39c6335331
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2024-08-05 16:13:20 -07:00
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
doctorpangloss
d9ba795385
Fixes for tests and completing merge
...
- huggingface cache is now better used on platforms that support
symlinking and the files you are requesting already exist in the
cache
- absolute imports were changed to relative in the correct places
- StringEnumRequestParameter has a special case in validation
- fix model_management whitespace issue
- fix comfy.ops references
2024-08-01 18:28:51 -07:00
doctorpangloss
0a1ae64b0b
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2024-08-01 16:19:11 -07:00
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
doctorpangloss
ce5fe01768
Improve performance and memory management of upscale models, improve messaging on models loaded and unloaded from the GPU
2024-07-30 17:05:53 -07:00
doctorpangloss
72baecad87
Improve logging and tracing for validation errors
2024-07-16 12:26:30 -07:00
doctorpangloss
b6b97574dc
Handle CPU torch more gracefully
2024-07-05 10:47:06 -07:00
doctorpangloss
dbc2a4ba29
Disable this lint warning
2024-06-28 18:45:15 -07:00
doctorpangloss
8cdc246450
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2024-06-17 16:19:48 -07:00
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
Max Tretikov
8b091f02de
Add xformer.ops imports
2024-06-14 14:09:46 -06:00
Max Tretikov
9cf4f9830f
Coalesce directml_enabled and directml_device into one variable
2024-06-14 13:16:05 -06:00
Max Tretikov
a919272e3b
Fix errors in model_management.py
2024-06-14 00:17:47 -06:00
Simon Lui
5eb98f0092
Exempt IPEX from non_blocking previews fixing segmentation faults. ( #3708 )
2024-06-13 18:51:14 -04:00
doctorpangloss
cac6690481
Add known SD3 model files, merge branch 'master' of github.com:comfyanonymous/ComfyUI
2024-06-12 10:56:41 -07:00
comfyanonymous
0e49211a11
Load the SD3 T5xxl model in the same dtype stored in the checkpoint.
2024-06-11 17:03:26 -04:00
doctorpangloss
d778277a68
Merge with upstream and fix tests
2024-06-10 10:01:08 -07:00
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
doctorpangloss
3f559135c6
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2024-06-03 11:42:55 -07:00
comfyanonymous
b249862080
Add an annoying print to a function I want to remove.
2024-06-01 12:47:31 -04:00
doctorpangloss
cb557c960b
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2024-05-31 07:42:11 -07:00
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
doctorpangloss
a79ccd625f
bf16 selection for AMD
2024-05-22 22:45:15 -07:00
doctorpangloss
35cf996b68
ROCm 6.0 seems to require get_device_name to be called before memory methods in order to return valid data
2024-05-22 22:09:07 -07:00
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
doctorpangloss
f69b6225c0
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2024-05-20 12:06:35 -07:00
comfyanonymous
09e069ae6c
Log the pytorch version.
2024-05-20 06:22:29 -04:00
doctorpangloss
519cddcefc
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2024-05-17 14:04:44 -07:00
doctorpangloss
cb45b86b63
Patch torch device code here
2024-05-17 07:19:15 -07:00
comfyanonymous
19300655dd
Don't automatically switch to lowvram mode on GPUs with low memory.
2024-05-17 00:31:32 -04:00
doctorpangloss
3d98440fb7
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2024-05-16 14:28:49 -07:00
doctorpangloss
8741cb3ce8
LLM support in ComfyUI
...
- Currently uses `transformers`
- Supports model management and correctly loading and unloading models
based on what your machine can support
- Includes a Text Diffusers 2 workflow to demonstrate text rendering in
SD1.5
2024-05-14 17:30:23 -07:00
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
doctorpangloss
779ff30c17
Provide a protocol for plugins to declare model-management-manageable models. Docs will be updated to specify that plugin authors should use ModelPatcher generally.
2024-05-09 16:07:18 -07:00
doctorpangloss
330ecb10b2
Merge with upstream. Remove TLS flags, because a third party proxy will do this better
2024-05-02 21:57:20 -07:00
