Commit Graph
5659 Commits
Author SHA1 Message Date
Alexander PiskunandGitHub 1395bce9f7 update example_node to use V3 schema (#9723) 2025-10-02 15:20:29 -07:00
patientxandGitHub a12b26c630 Merge branch 'comfyanonymous:master' into master 2025-10-03 01:01:55 +03:00
comfyanonymousandGitHub e9364ee279 Turn on TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL by default. (#10168) 2025-10-02 17:57:15 -04:00
Alexander PiskunandGitHub f6e3e9a456 fix(api-nodes): made logging path to be smaller (#10156) 2025-10-02 14:50:31 -07:00
Alexander PiskunandGitHub 8f4ee9984c convert nodes_morphology.py to V3 schema (#10159) 2025-10-02 13:53:00 -07:00
patientxandGitHub 603dfa1a65 Merge branch 'comfyanonymous:master' into master 2025-10-02 14:06:08 +03:00
patientxandGitHub 8dd4ae488f Merge pull request #322 from Rando717/hip-path
echo/print for hip path(s)
2025-10-02 14:05:30 +03:00
comfyanonymousandGitHub 0e9d1724be Add a .bat to the AMD portable to disable smart memory. (#10153) 2025-10-02 00:33:05 -04:00
rattus128andGitHub 4965c0e2ac WAN: Fix cache VRAM leak on error (#10141)
If this suffers an exception (such as a VRAM oom) it will leave the
encode() and decode() methods which skips the cleanup of the WAN
feature cache. The comfy node cache then ultimately keeps a reference
this object which is in turn reffing large tensors from the failed
execution.

The feature cache is currently setup at a class variable on the
encoder/decoder however, the encode and decode functions always clear
it on both entry and exit of normal execution.

Its likely the design intent is this is usable as a streaming encoder
where the input comes in batches, however the functions as they are
today don't support that.

So simplify by bringing the cache back to local variable, so that if
it does VRAM OOM the cache itself is properly garbage when the
encode()/decode() functions dissappear from the stack.
2025-10-01 18:42:16 -04:00
rattus128andGitHub 911331c06c sd: fix VAE tiled fallback VRAM leak (#10139)
When the VAE catches this VRAM OOM, it launches the fallback logic
straight from the exception context.

Python however refs the entire call stack that caused the exception
including any local variables for the sake of exception report and
debugging. In the case of tensors, this can hold on the references
to GBs of VRAM and inhibit the VRAM allocated from freeing them.

So dump the except context completely before going back to the VAE
via the tiler by getting out of the except block with nothing but
a flag.

The greately increases the reliability of the tiler fallback,
especially on low VRAM cards, as with the bug, if the leak randomly
leaked more than the headroom needed for a single tile, the tiler
would fallback would OOM and fail the flow.
2025-10-01 18:40:28 -04:00
Rando717andGitHub cfb3eecdc3 Update comfyui-n.bat, print hip PATH(s)
prints "HIP_PATH" at the very top, 
and all defined "HIP_PATH_xx" paths


optional print under Build Tools with check for MSVC in PATH,
assuming default path:
<drive>\<program files>\Microsoft Visual Studio\<year>\BuildTools\VC\Tools\MSVC\<version>\bin\Hostx64\x64
2025-10-02 00:22:02 +02:00
KoratahiuandGitHub bb32d4ec31 feat: Add Epsilon Scaling node for exposure bias correction (#10132) 2025-10-01 17:59:07 -04:00
Rando717andGitHub 129d2c3d2e Updated comfyui.bat, print hip PATH(s)
added echo for "HIP_PATH" at the top
and all "HIP_PATH_xx" paths that are defined: 57, 61, 62, 64, 70
2025-10-01 23:34:03 +02:00
comfyanonymousandGitHub a6f83a4a1a Support the new hunyuan vae. (#10150) 2025-10-01 17:19:13 -04:00
patientxandGitHub 3ca4f4985f Merge branch 'comfyanonymous:master' into master 2025-10-01 23:01:53 +03:00
Alexander PiskunandGitHub e4f99b479a convert nodes_ip2p.pt to V3 schema (#10097) 2025-10-01 12:20:30 -07:00
Alexander PiskunandGitHub d9c0a4053d convert nodes_lt.py to V3 schema (#10084) 2025-10-01 12:19:56 -07:00
Alexander PiskunandGitHub 11bab7be76 convert nodes_pag.py to V3 schema (#10080) 2025-10-01 12:18:49 -07:00
Alexander PiskunandGitHub 3af1881455 convert nodes_optimalsteps.py to V3 schema (#10074) 2025-10-01 12:18:04 -07:00
Alexander PiskunandGitHub e0210ce0a7 convert nodes_differential_diffusion.py to V3 schema (#10056) 2025-10-01 12:17:33 -07:00
Alexander PiskunandGitHub 7eb7160db4 convert nodes_gits.py to V3 schema (#9949) 2025-10-01 12:16:59 -07:00
patientxandGitHub beec1dcd98 Update README.md 2025-10-01 21:00:08 +03:00
patientxandGitHub 1e2069a1e8 Merge branch 'comfyanonymous:master' into master 2025-10-01 20:59:54 +03:00
patientxandGitHub 460e676bb8 Update README.md 2025-10-01 20:59:47 +03:00
Alexander PiskunandGitHub 638097829d convert nodes_audio_encoder.py to V3 schema (#10123) 2025-09-30 23:00:22 -07:00
AustinMrozandGitHub c4a8cf60ab Bump frontend to 1.27.7 (#10133) 2025-09-30 22:12:32 -07:00
comfyanonymous bab8ba20bf ComfyUI version 0.3.62. v0.3.62 2025-09-30 15:12:07 -04:00
patientxandGitHub 124da71754 Update cfz_caching_condition.py 2025-09-30 20:55:06 +03:00
Alexander PiskunandGitHub b682a73c55 enable Seedance Pro model in the FirstLastFrame node (#10120) 2025-09-30 10:43:41 -07:00
Alexander PiskunandGitHub 631b9ae861 fix(Rodin3D-Gen2): missing "task_uuid" parameter (#10128) 2025-09-30 10:21:47 -07:00
comfyanonymousandGitHub f48d7230de Add new portable links to readme. (#10112) 2025-09-30 12:17:49 -04:00
patientxandGitHub 8bf9f903ea Update README.md 2025-09-30 15:15:12 +03:00
patientxandGitHub 70a4d930a5 Merge branch 'comfyanonymous:master' into master 2025-09-30 15:14:42 +03:00
patientxandGitHub 834dfb6b22 Update README.md 2025-09-30 15:14:35 +03:00
comfyanonymousandGitHub 6e079abc3a Workflow permission fix. (#10110) 2025-09-29 23:11:37 -04:00
comfyanonymous 977a4ed8c5 ComfyUI version 0.3.61 v0.3.61 2025-09-29 23:04:42 -04:00
comfyanonymousandGitHub 414a178fb6 Add basic readme for AMD portable. (#10109) 2025-09-29 23:03:02 -04:00
comfyanonymousandGitHub 447884b657 Make stable release workflow callable. (#10108) 2025-09-29 20:37:51 -04:00
comfyanonymousandGitHub bed4b49d08 Add action to do the full stable release. (#10107) 2025-09-29 20:31:15 -04:00
comfyanonymousandGitHub 342cf644ce Add a way to have different names for stable nvidia portables. (#10106) 2025-09-29 20:05:44 -04:00
comfyanonymousandGitHub 3758848423 Different base files for nvidia and amd portables. (#10105) 2025-09-29 19:54:37 -04:00
comfyanonymousandGitHub 0db6aabed3 Different base files for different release. (#10104) 2025-09-29 19:54:05 -04:00
comfyanonymousandGitHub 1673ace19b Make the final release test optional in the stable release action. (#10103) 2025-09-29 19:08:42 -04:00
comfyanonymousandGitHub 7f38e4c538 Add action to create cached deps with manually specified torch. (#10102) 2025-09-29 17:27:52 -04:00
Alexander PiskunandGitHub 8accf50908 convert nodes_mahiro.py to V3 schema (#10070) 2025-09-29 12:35:51 -07:00
Christian ByrneandGitHub ed0f4a609b dont cache new locale entry points (#10101) 2025-09-29 12:16:02 -07:00
Alexander PiskunandGitHub 041b8824f5 convert nodes_perpneg.py to V3 schema (#10081) 2025-09-29 12:05:28 -07:00
Alexander PiskunandGitHub b1111c2062 convert nodes_mochi.py to V3 schema (#10069) 2025-09-29 12:03:35 -07:00
Alexander PiskunandGitHub 05a258efd8 add WanImageToImageApi node (#10094) 2025-09-29 12:01:04 -07:00
ComfyUI WikiandGitHub c8276f8c6b Update template to 0.1.91 (#10096) 2025-09-29 11:59:42 -07:00