feat(convert): consolidate into one auto-detecting converter node

.gitignore

@@ -3,3 +3,4 @@ __pycache__/
 models/
 .venv/
 test_results/
+.claude/

__init__.py

@@ -11,9 +11,6 @@
     CoreMLConverter,
     COREML_LOAD_LORA,
 )
-from coreml_suite.lcm import (
-    COREML_CONVERT_LCM,
-)
 
 NODE_CLASS_MAPPINGS = {
     "CoreMLUNetLoader": CoreMLLoaderUNet,
@@ -22,7 +19,6 @@
     "CoreMLModelAdapter": CoreMLModelAdapter,
     "Core ML LoRA Loader": COREML_LOAD_LORA,
     "Core ML Converter": CoreMLConverter,
-    "Core ML LCM Converter": COREML_CONVERT_LCM,
 }
 NODE_DISPLAY_NAME_MAPPINGS = {
     "CoreMLUNetLoader": "Load Core ML UNet",
@@ -31,5 +27,4 @@
     "CoreMLModelAdapter": "Core ML Adapter (Experimental)",
     "Core ML LoRA Loader": "Load LoRA to use with Core ML",
     "Core ML Converter": "Convert Checkpoint to Core ML",
-    "Core ML LCM Converter": "Convert LCM to Core ML",
 }

coreml_suite/lcm/__init__.py

@@ -1,3 +1,8 @@
-from .nodes import COREML_CONVERT_LCM
+"""LCM runtime support (sampler-side).
 
-__all__ = ["COREML_CONVERT_LCM"]
+The dedicated LCM converter node was removed once the standard ``CoreMLConverter``
+gained model-version auto-detection (full-distill LCM is detected from the
+checkpoint). What remains here is runtime sampling support — ``utils`` patches the
+model sampling and supplies the guidance embedding when a converted UNet exposes
+``timestep_cond``.
+"""