Alexander Piskun and GitHub
8c26d7bbe6
convert nodes_pixverse.py to V3 schema ( #10177 )
2025-10-03 11:48:21 -07:00
Alexander Piskun and GitHub
d7aa414141
convert nodes_eps.py to V3 schema ( #10172 )
2025-10-03 11:45:02 -07:00
Alexander Piskun and GitHub
3e68bc342c
convert nodes_torch_compile.py to V3 schema ( #10173 )
2025-10-03 11:43:54 -07:00
Alexander Piskun and GitHub
c2c5a7d5f8
fix(api-nodes): bad indentation in Recraft API node function ( #10175 )
2025-10-03 11:41:06 -07:00
Alexander Piskun and GitHub
8a293372ec
fix(api-nodes): reimport of base64 in Gemini node ( #10181 )
2025-10-03 11:40:27 -07:00
Alexander Piskun and GitHub
ed3ca78e08
feat(api-nodes): add kling-2-5-turbo to txt2video and img2video nodes ( #10155 )
2025-10-03 11:26:34 -07:00
Alexander Piskun and GitHub
4ffea0e864
feat(linter, api-nodes): add pylint for comfy_api_nodes folder ( #10157 )
2025-10-02 19:14:28 -04:00
Alexander Piskun and GitHub
1395bce9f7
update example_node to use V3 schema ( #9723 )
2025-10-02 15:20:29 -07:00
comfyanonymous and GitHub
e9364ee279
Turn on TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL by default. ( #10168 )
2025-10-02 17:57:15 -04:00
Alexander Piskun and GitHub
f6e3e9a456
fix(api-nodes): made logging path to be smaller ( #10156 )
2025-10-02 14:50:31 -07:00
Alexander Piskun and GitHub
8f4ee9984c
convert nodes_morphology.py to V3 schema ( #10159 )
2025-10-02 13:53:00 -07:00
comfyanonymous and GitHub
0e9d1724be
Add a .bat to the AMD portable to disable smart memory. ( #10153 )
2025-10-02 00:33:05 -04:00
rattus128 and GitHub
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
rattus128 and GitHub
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
Koratahiu and GitHub
bb32d4ec31
feat: Add Epsilon Scaling node for exposure bias correction ( #10132 )
2025-10-01 17:59:07 -04:00
comfyanonymous and GitHub
a6f83a4a1a
Support the new hunyuan vae. ( #10150 )
2025-10-01 17:19:13 -04:00
Alexander Piskun and GitHub
e4f99b479a
convert nodes_ip2p.pt to V3 schema ( #10097 )
2025-10-01 12:20:30 -07:00
Alexander Piskun and GitHub
d9c0a4053d
convert nodes_lt.py to V3 schema ( #10084 )
2025-10-01 12:19:56 -07:00
Alexander Piskun and GitHub
11bab7be76
convert nodes_pag.py to V3 schema ( #10080 )
2025-10-01 12:18:49 -07:00
Alexander Piskun and GitHub
3af1881455
convert nodes_optimalsteps.py to V3 schema ( #10074 )
2025-10-01 12:18:04 -07:00
Alexander Piskun and GitHub
e0210ce0a7
convert nodes_differential_diffusion.py to V3 schema ( #10056 )
2025-10-01 12:17:33 -07:00
Alexander Piskun and GitHub
7eb7160db4
convert nodes_gits.py to V3 schema ( #9949 )
2025-10-01 12:16:59 -07:00
Alexander Piskun and GitHub
638097829d
convert nodes_audio_encoder.py to V3 schema ( #10123 )
2025-09-30 23:00:22 -07:00
AustinMroz and GitHub
c4a8cf60ab
Bump frontend to 1.27.7 ( #10133 )
2025-09-30 22:12:32 -07:00
comfyanonymous
bab8ba20bf
ComfyUI version 0.3.62.
2025-09-30 15:12:07 -04:00
Alexander Piskun and GitHub
b682a73c55
enable Seedance Pro model in the FirstLastFrame node ( #10120 )
2025-09-30 10:43:41 -07:00
Alexander Piskun and GitHub
631b9ae861
fix(Rodin3D-Gen2): missing "task_uuid" parameter ( #10128 )
2025-09-30 10:21:47 -07:00
comfyanonymous and GitHub
f48d7230de
Add new portable links to readme. ( #10112 )
2025-09-30 12:17:49 -04:00
comfyanonymous and GitHub
6e079abc3a
Workflow permission fix. ( #10110 )
2025-09-29 23:11:37 -04:00
comfyanonymous
977a4ed8c5
ComfyUI version 0.3.61
2025-09-29 23:04:42 -04:00
comfyanonymous and GitHub
414a178fb6
Add basic readme for AMD portable. ( #10109 )
2025-09-29 23:03:02 -04:00
comfyanonymous and GitHub
447884b657
Make stable release workflow callable. ( #10108 )
2025-09-29 20:37:51 -04:00
comfyanonymous and GitHub
bed4b49d08
Add action to do the full stable release. ( #10107 )
2025-09-29 20:31:15 -04:00
comfyanonymous and GitHub
342cf644ce
Add a way to have different names for stable nvidia portables. ( #10106 )
2025-09-29 20:05:44 -04:00
comfyanonymous and GitHub
3758848423
Different base files for nvidia and amd portables. ( #10105 )
2025-09-29 19:54:37 -04:00
comfyanonymous and GitHub
0db6aabed3
Different base files for different release. ( #10104 )
2025-09-29 19:54:05 -04:00
comfyanonymous and GitHub
1673ace19b
Make the final release test optional in the stable release action. ( #10103 )
2025-09-29 19:08:42 -04:00
comfyanonymous and GitHub
7f38e4c538
Add action to create cached deps with manually specified torch. ( #10102 )
2025-09-29 17:27:52 -04:00
Alexander Piskun and GitHub
8accf50908
convert nodes_mahiro.py to V3 schema ( #10070 )
2025-09-29 12:35:51 -07:00
Christian Byrne and GitHub
ed0f4a609b
dont cache new locale entry points ( #10101 )
2025-09-29 12:16:02 -07:00
Alexander Piskun and GitHub
041b8824f5
convert nodes_perpneg.py to V3 schema ( #10081 )
2025-09-29 12:05:28 -07:00
Alexander Piskun and GitHub
b1111c2062
convert nodes_mochi.py to V3 schema ( #10069 )
2025-09-29 12:03:35 -07:00
Alexander Piskun and GitHub
05a258efd8
add WanImageToImageApi node ( #10094 )
2025-09-29 12:01:04 -07:00
ComfyUI Wiki and GitHub
c8276f8c6b
Update template to 0.1.91 ( #10096 )
2025-09-29 11:59:42 -07:00
Changrz and GitHub
6ec1cfe101
[Rodin3d api nodes] Updated the name of the save file path (changed from timestamp to UUID). ( #10011 )
...
* Update savepath name from time to uuid
* delete lib
2025-09-29 11:59:12 -07:00
comfyanonymous and GitHub
b60dc31627
Update command to install latest nighly pytorch. ( #10085 )
2025-09-28 13:41:32 -04:00
comfyanonymous and GitHub
555f902fc1
Fix stable workflow creating multiple draft releases. ( #10067 )
2025-09-27 22:43:25 -04:00
1364548c72
feat: ComfyUI can be run on the specified Ascend NPU ( #9663 )
...
* feature: Set the Ascend NPU to use a single one
* Enable the `--cuda-device` parameter to support both CUDA and Ascend NPUs simultaneously.
* Make the code just set the ASCENT_RT_VISIBLE_DEVICES environment variable without any other edits to master branch
---------
Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com >
2025-09-27 22:36:02 -04:00
Alexander Piskun and GitHub
2dadb34860
convert nodes_hypertile.py to V3 schema ( #10061 )
2025-09-27 19:16:22 -07:00
Alexander Piskun and GitHub
1cf86f5ae5
convert nodes_lumina2.py to V3 schema ( #10058 )
2025-09-27 19:12:51 -07:00
