Actual nodes pick up the underlying structure at runtime now that the global NODE_CLASS_MAPPINGS has been updated with their information, I pull it directly from there.
A work-around for the loading sequencing problems, but hopefully one that requrires little upkeep as any changes to the underlying structure is picked-up at runtime.
- Added a local_map_name ("NODE_CLASS_MAPPINGS") and retrieve it from the module
immediately after loading.
- If the local dictionary exists, wrap the target nodes from there, rather than
relying on the global dictionary.
- Removed references to GLOBAL_NODE_CLASS_MAPPINGS for custom nodes and replaced
them with the local module mapping lookup.
Code Changes (__init__.py):
- Switches from deepcopy to standard copy for better efficiency
- Initializes current_device from model_management instead of hardcoded "cuda:0"
- Simplifies node class mapping by removing intermediate TARGET_NODE_CLASS_MAPPINGS
- Updates node naming convention: removes underscore from MultiGPU suffix
- Adds new supported nodes: "CheckpointLoaderSimple", "ControlNetLoader", "LoadFluxControlNet"
- Improves code organization with better comment clarity
COMPATIBILITY NOTE: This version restores backward compatibility with workflows
using the previous node naming scheme. Both old and new node names will work.
Documentation Changes (README.md):
- Updates node list to reflect automatic detection system
- Adds proper attribution links for required dependencies (ComfyUI-GGUF, x-flux-comfy)
- Links to example quantized models like flux1-dev-gguf
- Reorganizes loader sections with clear dependency requirements
- Updates support links to new maintainer
- Removes business/commercial references
- Updates credits section to reflect current project status
BREAKING CHANGE: This replaces the existing MultiGPU implementation with a new system
designed by City96 (https://v100s.net/). Users with existing workflows using the older
MultiGPU nodes will need to update their workflows.
The new implementation by City96 significantly improves the codebase:
- Replaces manual class definitions with a dynamic class override system
- Reduces code from 400+ lines to ~50 through smart use of inheritance
- Handles all loader types via TARGET_NODE_NAMES configuration
- Provides consistent behavior across standard and GGUF loaders
- Creates a unified "multigpu" category for better organization
The system creates MultiGPU versions of nodes by wrapping original classes through
an override mechanism, maintaining functionality while adding device selection.
Migration:
- Replace old MultiGPU nodes with new versions (same names with "_MultiGPU" suffix)
- Node functionality remains the same, only the implementation has changed
John Pollock