- ROCMSamplerCustomAdvanced: V3 ComfyNode drop-in for stock SamplerCustomAdvanced
with architecture detection, ROCm backend tuning, memory defrag for high-memory
models (LTX 128ch), enhanced per-step callback with ETA
- ROCMSamplerCustomAdvancedBenchmark: A/B comparison node for stock vs ROCm
- docs/SAMPLER_CUSTOM_ADVANCED.md: full documentation for agents and users
- Category: ROCm Ninodes/Sampling
- Bump version to 2.2.0 across all files
- LTX Video VAE detection (128 channels, 32x spatial compression, 8x temporal)
- z-image / z-image-turbo pixel-space VAE passthrough (no decode needed)
- fp16 default on all AMD GPUs (Strix Halo, RDNA 2/3, CDNA)
- Per-architecture tuning with automatic detection (gfx1151/gfx1100/gfx1030/CDNA)
- Temporal tiling for long videos: overlapping chunks with linear blend,
zero frame loss, progress bar in UI (disabled by default)
- Chunked IO bypass for LTX — fixes OOM with max_split_size_mb caps
- Fixed memory estimation: correct for all dims (including 5D temporal) and dtypes
- APU-aware memory management (psutil for unified memory on Strix Halo)
- Tile size floor for high-compression VAEs (min 64 latent pixels)
- 25 unit tests covering all new features
- Updated version to 2.0.11 in pyproject.toml and comfyui_manager.json for consistency.
- Removed video chunking from ROCMOptimizedVAEDecode to ensure full video decoding for temporal/causal VAEs, preventing artifacts.
- Added new ROCm Text Generate LTX2 Prompt node, enhancing generative AI capabilities.
- Updated README to reflect new features and improvements in v2.0.11.
- Enhanced changelog with details on changes and fixes in this release.
- Updated version number to 2.0.10 in the README header.
- Added new section detailing features in v2.0.10, including checkpoint caching and FP8/quantized checkpoint reuse.
- Enhanced clarity on the ROCm Checkpoint Loader's caching mechanism and its benefits for performance.
- Added reliable WAN VAE detection using isinstance() with imported classes
- Added fallback detection using latent_channels (16 for WAN 2.1, 48 for WAN 2.2)
- Disabled chunking for WAN VAEs to preserve causal decoding chain with feature caching
- Matched native ComfyUI behavior exactly for WAN VAE video processing
- Fixed detection logic to use correct file (rocm_nodes/core/vae.py)
- Applied ROCm backend optimizations to video processing
- Added async memory cleanup for WAN VAE videos
- Added gfx1151 architecture detection and logging
- Updated version to 2.0.1 across all files
- Optimized for mature ROCm drivers and libraries
- Added TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL=1 for better performance
- Replaced aggressive memory management with gentle cleanup
- Updated memory allocation settings (256MB chunks, 0.8 threshold)
- Removed performance-penalizing functions and complex memory management
- Cleaned up development files and test workflows
- Enhanced README with clear explanation of what we do and how we do it
- Maintained 9 optimized nodes with gentle memory management
- Restored v1.0.13 with all 9 working nodes (ROCMOptimizedCheckpointLoader, ROCMOptimizedKSampler, etc.)
- Implemented comprehensive debug flag system (ROCM_NINODES_DEBUG=1)
- Created complete test suite with performance and correctness tests
- Added data capture infrastructure for real workflow testing
- Built standalone test runner with mock data support
- Created ComfyUI integration tests for Flux and WAN workflows
- Added comprehensive documentation (ARCHITECTURE.md, RULES.md, TESTING_GUIDE.md)
- Updated README with testing section and performance targets
- All tests passing with proper error handling and data validation
Performance Targets:
- Flux: 78% improvement (≤110s total)
- WAN: 5.6% improvement (≤93s sampling)
- VAE Decode: <10s for any resolution
- Checkpoint Load: <30s for Flux models
Ready for production use with comprehensive testing infrastructure!
- Fixed AttributeError: 'dict' object has no attribute 'shape'
- Fixed IndexError: tuple index out of range in WAN VAE memory calculation
- Fixed ValueError: Expected numpy array with ndim 3 but got 4 in video output
- Added comprehensive test suite with 9 test cases covering all error scenarios
- Added debug data collection and optimization testing framework
- Updated documentation with testing section and performance benchmarks
- Cleaned up unused files and improved code quality
- WAN video workflows now work end-to-end without errors
- Fixed blessed workflow using diffusion-model-only file instead of full checkpoint
- Resolved 'clip input is invalid: None' error caused by flux1-dev-fp8.safetensors
- Enhanced error handling with comprehensive validation for model, CLIP, and VAE outputs
- Updated troubleshooting guide to explain diffusion-model-only files issue
- Added Flux model guidance for separate file structure
- Blessed workflow now uses user-selectable checkpoint for maximum compatibility
- Fixed flux_dev_optimized.json to use user-selectable checkpoint instead of hardcoded flux1-dev-fp8.safetensors
- Updated troubleshooting guide to explain diffusion-model-only files issue
- Added guidance for Flux models that come as separate files
- Resolves CLIP input invalid error caused by using diffusion model only file
- Created flux_dev_optimized_generic.json with no hardcoded checkpoint
- Added comprehensive troubleshooting section for CLIP input errors
- Provides solutions for missing/invalid checkpoint issues
- Added generic workflow download link for users without specific checkpoints
- Enhanced error handling and validation in checkpoint loader
- Added GitHub web interface links as alternatives to raw.githubusercontent.com
- Provides immediate access while CDN propagates
- Ensures users can access flux_dev_optimized.json workflow
- Fixed critical ROCMOptimizedCheckpointLoader errors causing noise output
- Resolved torch.pickle and comfy.model_management.ModelPatcher errors
- Streamlined checkpoint loader implementation for maximum reliability
- Enhanced with lazy_loading, optimize_for_flux, and precision_mode parameters
- Performance within 2-3% of standard loader (28.32s vs 29.07s)
- Verified proper 512x512 PNG image generation with both standard and ROCM nodes
- Updated blessed workflow with enhanced checkpoint loader parameters
- Comprehensive testing confirms stable end-to-end workflow execution
- Increment version in pyproject.toml and comfyui_manager.json from 1.0.7 to 1.0.9
- Add new nodes: ROCMOptimizedCheckpointLoader, ROCMFluxBenchmark, and ROCMMemoryOptimizer
- Implement Flux-specific optimizations and adaptive tile sizing in VAE decode
- Introduce memory management improvements and performance benchmarks
- Update README with new features and installation methods for enhanced user experience
- Add comprehensive benchmark results for 320x320px, 17 frames WAN 2.2 i2v
- Show 8.1% overall performance improvement (93.05s vs 101.17s average)
- Include detailed breakdown of KSampler and VAE Decode timings
- Update version to 1.2.1 for ComfyUI registry submission
- Add consistency metrics showing stable performance across runs
- Introduced a new node.zip file for plugin distribution
- Updated README to include new installation methods for the plugin via ComfyUI CLI and manual installation
- Renumbered installation methods for clarity
This enhances the installation experience for users by providing clear and updated instructions.
- Add WindowsPaginationDiagnostic node for automatic detection and fixes
- Add Windows-specific memory management and optimizations
- Add 6 different methods to fix pagination errors
- Add PowerShell and Batch scripts for automatic fixes
- Add psutil dependency for memory diagnostics
- Update documentation with comprehensive troubleshooting guide
- Version bump to 1.2.0
- Removed unnecessary additional dependencies installation step for torchvision and torchaudio
- Streamlined the installation process for ROCm PyTorch nightly on gfx1151
This simplifies the setup instructions for users, ensuring clarity and efficiency in the installation process.
- Added 4 different methods to fix Windows pagination errors
- Environment variable, batch file, PowerShell profile, and system variable solutions
- Advanced troubleshooting for memory and ROCm issues on Windows
- Updated performance results with 480x480px video generation success
- Comprehensive Windows-specific guidance for users
This addresses the common pagination errors Windows users encounter
when using ROCm with PyTorch on AMD GPUs.
- Added quick fix section for common Windows PowerShell errors
- Clarified git pull vs git clone usage in update instructions
- Added specific troubleshooting for 'fatal: couldn't find remote ref' error
- Added troubleshooting for 'does not appear to be a git repository' error
- Added virtual environment activation troubleshooting
- Separated installation methods: existing vs new installations
- Added Method 3 for when git pull fails completely
- Made Windows instructions more step-by-step and foolproof
This addresses the specific errors shown in the user's screenshot:
- git pull before cloning
- virtual environment activation issues
- incorrect git command syntax
- Added complete ComfyUI setup guide with uv for Linux and Windows
- Documented tested setup on Manjaro Linux with GMTek Evo-X2 Strix Halo
- Added detailed plugin update instructions (git pull and fresh install)
- Included uv-specific troubleshooting for common issues
- Added update notifications and changelog references
- Covered both Linux (Manjaro/Ubuntu/Arch) and Windows (PowerShell) setups
- Included ROCm PyTorch nightly installation steps
- Added virtual environment management with uv
- Comprehensive troubleshooting for uv, git, and permission issues
This makes the plugin much more accessible to users who want to set up
ComfyUI from scratch or update the plugin easily.
- Added video_wan2_2_14B_i2v_rocm_optimized.json workflow
- Replaced VAE Decode nodes with ROCMOptimizedVAEDecode (2 nodes)
- Replaced KSamplerAdvanced nodes with ROCMOptimizedKSamplerAdvanced (6 nodes)
- Total of 8 ROCM optimizations in the video workflow
- Updated README with both Flux and WAN video workflow downloads
- Ready for testing on gfx1151 architecture
- Added prominent download link in main features section
- Added detailed Quick Start section with workflow download
- Direct link to example_workflow.json for easy testing
- Clear instructions for using the optimized workflow
- Users can now easily test the 78% performance improvement
- Updated post-installation instructions to show 'RocM Ninodes' folder structure
- Clarified node categories: VAE and Sampling subfolders
- Better user guidance for finding nodes in ComfyUI interface
iGavroche