- 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.
- 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
iGavroche