Gavroche
2f9c5af099
- Fixed TypeError: '>' not supported between instances of 'list' and 'float' - Added parameter conversion logic for cfg, steps, seed, denoise, etc. - Applied fix to both ROCMOptimizedKSampler and ROCMOptimizedKSamplerAdvanced - Complete end-to-end workflow now executes successfully (70.41s total) - Performance: Checkpoint 26.05s, Sampling 41.54s, VAE 0.30s - Successfully generates proper images confirming full functionality
27 lines
858 B
JSON
27 lines
858 B
JSON
{
|
|
"name": "rocm-ninodes",
|
|
"display_name": "RocM Ninodes",
|
|
"description": "ROCM Optimized Nodes for ComfyUI - High-performance VAE decode and sampling nodes specifically tuned for AMD GPUs with ROCm support",
|
|
"version": "1.0.12",
|
|
"author": "iGavroche",
|
|
"author_email": "nino2k@proton.me",
|
|
"repository": "https://github.com/iGavroche/rocm-ninodes",
|
|
"license": "MIT",
|
|
"nodes": [
|
|
"ROCMOptimizedCheckpointLoader",
|
|
"ROCMOptimizedVAEDecode",
|
|
"ROCMOptimizedVAEDecodeTiled",
|
|
"ROCMVAEPerformanceMonitor",
|
|
"ROCMOptimizedKSampler",
|
|
"ROCMOptimizedKSamplerAdvanced",
|
|
"ROCMSamplerPerformanceMonitor",
|
|
"ROCMFluxBenchmark",
|
|
"ROCMMemoryOptimizer"
|
|
],
|
|
"dependencies": [
|
|
"numpy>=1.20.0",
|
|
"Pillow>=8.0.0"
|
|
],
|
|
"comfyui_version": ">=1.0.0"
|
|
}
|