* Fix bypass dtype/device moving
* Force offloading mode for training
* training context var
* offloading implementation in training node
* fix wrong input type
* Support bypass load lora model, correct adapter/offloading handling
This was missing the stochastic rounding required for fp8 downcast
to be consistent with model_patcher.patch_weight_to_device.
Missed in testing as I spend too much time with quantized tensors
and overlooked the simpler ones.
If there are non-trivial python objects nested in the model_options, this
causes all sorts of issues. Traverse lists and dicts so clones can safely
overide settings and BYO objects but stop there on the deepclone.
* feat(api-nodes-Kling): add new models (V3, O3)
* remove storyboard from VideoToVideo node
* added check for total duration of storyboards
* fixed other small things
* updated display name for nodes
* added "fake" seed
* revert threaded model loader change
This change was only needed to get around the pytorch 2.7 mempool bugs,
and should have been reverted along with #12260. This fixes a different
memory leak where pytorch gets confused about cache emptying.
* load non comfy weights
* MPDynamic: Pre-generate the tensors for vbars
Apparently this is an expensive operation that slows down things.
* bump to aimdo 1.8
New features:
watermark limit feature
logging enhancements
-O2 build on linux
* refactor: process isolation support for node replacement API
- Move REGISTERED_NODE_REPLACEMENTS global to NodeReplaceManager instance state
- Add NodeReplacement class to ComfyAPI_latest with async register() method
- Deprecate module-level register_node_replacement() function
- Call register_replacements() from comfy_entrypoint()
This enables pyisolate compatibility where extensions run in separate
processes and communicate via RPC. The async API allows registration
calls to cross process boundaries.
Refs: TDD-002
Amp-Thread-ID: https://ampcode.com/threads/T-019c2b33-ac55-76a9-9c6b-0246a8625f21
* fix: remove whitespace and deprecation cruft
Amp-Thread-ID: https://ampcode.com/threads/T-019c2be8-0b34-747e-b1f7-20a1a1e6c9df
