- the model weights generally have to be patched ahead of time for compilation to work
- the model downloader matches the folder_paths API a bit better
- tweak the logging from the execution node
- GGUF now works and included 4 bit quants, this will allow WAN to run on 24GB VRAM GPUs
- logger only shows full stack for errors
- helper functions for colab notebook
- fix nvcr.io auth error
- lora issues are now reported better
- model downloader will use huggingface cache and symlinking if it is supported on your platform
- torch compile node now correctly patches the model before compilation
- deprecate our preview image fork of the frontend because upstream now has the needed functionality
- merge the context executor from upstream into ours
- --panics-when=torch.cuda.OutOfMemory will now correctly panic and
exit the worker, giving it time to reply that the execution failed
and better dealing with irrecoverable out-of-memory errors
- --executor-factory=ProcessPoolExecutor will use a process instead of
a thread to execute comfyui workflows when using the worker. When
this process panics and exits, it will be correctly replaced, making
a more robust worker
- fix#29 str(model) no longer raises exceptions like with
HyVideoModelLoader
- don't try to format CUDA tensors because that can sometimes raise
exceptions
- cudaAllocAsync has been disabled for now due to 2.6.0 bugs
- improve florence2 support
- add support for paligemma 2. This requires the fix for transformers
that is currently staged in another repo, install with
`uv pip install --no-deps "transformers@git+https://github.com/zucchini-nlp/transformers.git#branch=paligemma-fix-kwargs"`
- triton has been updated
- fix missing __init__.py files
- Validation errors that occur early in the lifecycle of prompt
execution now get propagated to their callers in the
EmbeddedComfyClient. This includes error messages about missing node
classes.
- The execution context now includes the node_id and the prompt_id
- Latent previews are now sent with a node_id. This is not backwards
compatible with old frontends.
- Dependency execution errors are now modeled correctly.
- Distributed progress encodes image previews with node and prompt IDs.
- Typing for models
- The frontend was updated to use node IDs with previews
- Improvements to torch.compile experiments
- Some controlnet_aux nodes were upstreamed
- move workflows to distinct json files
- add the comfy-org workflows for testing
- fix issues where workflows from windows users would not be compatible
with backends running on linux or macos in light of separator
differences. Because this codebase uses get_or_download wherever
checkpoints, models, etc. are used, this is the only place where the
comparison is gracefully handled for downloading. Validation code
will correctly convert backslashes to forward slashes, assuming that
100% of the places they are used and when comparing with a list, they
are intended to be paths and not strict symbols
- 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
- Tests now perform faster
- Tests will run on supported GPU platforms
- Configuration has known issues related to setting up a working
directory for an embedded client
- Introduce a Skeletonize node that solves many problems with Canny
- Improve behavior of exception reporting
