Commit Graph
6 Commits
Author SHA1 Message Date
John Pollock c60771ace4 docs: update README to include new MultiGPU loaders and clarify workflow steps 2024-12-23 16:54:01 -06:00
John Pollock 19c0abd5ec Updated example workflows, added additional experimental workflows, added coverage for LTX loader 2024-12-23 15:39:23 -06:00
John Pollock 56e2e61e52 refactor: streamline MultiGPU node initialization
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
2024-12-22 22:36:59 -06:00
John Pollock a652a7f264 refactor: adopt City96's streamlined MultiGPU implementation
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
2024-12-22 08:28:35 -06:00
John Pollock 186723f34d Add mochi and ltxv support to CLIPLoaderMultiGPU 2024-12-18 17:01:01 -06:00
Alexander Dzhoganov b5462877f3 Initial commit 2024-08-04 19:36:59 +03:00