Commit Graph

2663 Commits

Author SHA1 Message Date
patientx
bdd77b243b
Merge branch 'comfyanonymous:master' into master 2024-08-27 21:29:27 +03:00
Chenlei Hu
6bbdcd28ae
Support weight padding on diff weight patch (#4576) 2024-08-27 13:55:37 -04:00
patientx
2feaa21954
Merge branch 'comfyanonymous:master' into master 2024-08-27 20:24:31 +03:00
patientx
7b7bf6e785
Merge branch 'comfyanonymous:master' into master 2024-08-27 13:51:35 +03:00
comfyanonymous
ab130001a8 Do RMSNorm in native type. 2024-08-27 02:41:56 -04:00
Chenlei Hu
ca4b8f30e0
Cleanup empty dir if frontend zip download failed (#4574) 2024-08-27 02:07:25 -04:00
Robin Huang
70b84058c1
Add relative file path to the progress report. (#4621) 2024-08-27 02:06:12 -04:00
patientx
4193c15afe
Merge branch 'comfyanonymous:master' into master 2024-08-26 22:56:02 +03:00
comfyanonymous
2ca8f6e23d Make the stochastic fp8 rounding reproducible. 2024-08-26 15:12:06 -04:00
comfyanonymous
7985ff88b9 Use less memory in float8 lora patching by doing calculations in fp16. 2024-08-26 14:45:58 -04:00
patientx
d7f28efe8d
Update cuda_malloc.py 2024-08-26 14:42:12 +03:00
patientx
58594a0b47
Merge branch 'comfyanonymous:master' into master 2024-08-26 14:29:57 +03:00
comfyanonymous
c6812947e9 Fix potential memory leak. 2024-08-26 02:07:32 -04:00
patientx
902d97af7d
Merge branch 'comfyanonymous:master' into master 2024-08-25 23:35:11 +03:00
comfyanonymous
9230f65823 Fix some controlnets OOMing when loading. 2024-08-25 05:54:29 -04:00
patientx
1a3e0f7646
Update README.md 2024-08-24 22:58:56 +03:00
patientx
1c5cd5b02d
Merge branch 'comfyanonymous:master' into master 2024-08-24 22:58:22 +03:00
patientx
a7ee560c21
Update README.md 2024-08-24 22:58:15 +03:00
guill
6ab1e6fd4a
[Bug #4529] Fix graph partial validation failure (#4588)
Currently, if a graph partially fails validation (i.e. some outputs are
valid while others have links from missing nodes), the execution loop
could get an exception resulting in server lockup.

This isn't actually possible to reproduce via the default UI, but is a
potential issue for people using the API to construct invalid graphs.
2024-08-24 15:34:58 -04:00
patientx
c60a87396b
Merge branch 'comfyanonymous:master' into master 2024-08-24 11:31:17 +03:00
comfyanonymous
07dcbc3a3e Clarify how to use high quality previews. 2024-08-24 02:31:03 -04:00
comfyanonymous
8ae23d8e80 Fix onnx export. 2024-08-23 17:52:47 -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
7df42b9a23 Fix dora. 2024-08-23 04:58:59 -04:00
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
Scorpinaus
9465b23432
Added SD15_Inpaint_Diffusers model support for unet_config_from_diffusers_unet function (#4565) 2024-08-23 03:57:08 -04:00
patientx
1ef90b7ac8
Merge branch 'comfyanonymous:master' into master 2024-08-23 00:55:19 +03:00
Chenlei Hu
bb4416dd5b
Fix task.status.status_str caused by #2666 (#4551)
* Fix task.status.status_str caused by 2666 regression

* fix

* fix
2024-08-22 17:38:30 -04:00
comfyanonymous
c0b0da264b Missing imports. 2024-08-22 17:20:51 -04:00
comfyanonymous
c26ca27207 Move calculate function to comfy.lora 2024-08-22 17:12:00 -04:00
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
comfyanonymous
c7ee4b37a1 Try to fix some lora issues. 2024-08-22 15:32:18 -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
8f60d093ba Fix issue. 2024-08-22 10:38:24 -04:00
patientx
0cd8a740bb
Merge branch 'comfyanonymous:master' into master 2024-08-22 14:01:42 +03:00
guill
dafbe321d2
Fix a bug where cached outputs affected IS_CHANGED (#4535)
This change fixes a bug where non-constant values could be passed to the
IS_CHANGED function. This would result in workflows taking an extra
execution before they acted as if they were cached.

The actual change is like 4 characters -- the rest is adding unit tests.
2024-08-21 23:38:46 -04:00
comfyanonymous
5f84ea63e8 Add a shortcut to the nightly package to run with --fast. 2024-08-21 23:36:58 -04:00
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
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