- Add _device_str() helper to normalize MPS variants (mps:0 → MPS)
- Fix device comparison: mps:0 and mps now correctly identified as same device
- Consistent MPS logging across all memory management functions
Fixes#340 - Installation error with PyTorch 2.7+cu126 and triton_windows
Replace diffusers.models.autoencoders.vae imports with local implementations
of DecoderOutput and DiagonalGaussianDistribution to avoid triggering the
bitsandbytes -> triton.ops import chain that fails on newer triton versions.
- Use in-place clamp/mul/add in postprocess normalization
- Use in-place clamp and Normalize in video transform pipeline
- Consolidate optimized channel permute functions in performance.py
- Use native permute() instead of einops rearrange in VAE encode/decode
- In-place wavelet decomposition and reconstruction operations
- Remove unused temporal_latent_blending function
- BlockSwap: Show effective/total blocks (e.g., 32/32) instead of raw requested value
- CLI: Skip CUDA device validation when CUDA_VISIBLE_DEVICES already set (worker process)
- Mac: Use direct processing instead of spawning subprocess (MPS allocator fails in child process)
- Multi-GPU: Set CUDA_VISIBLE_DEVICES before spawn so child inherits it before module-level torch import
- Remove redundant env setup in worker (now inherited from parent)
Replaces torch.mps.is_available() with torch.backends.mps.is_available()
across all files. The torch.backends API is the official PyTorch method
for MPS detection (since PyTorch 1.12) and works reliably on:
- macOS with Apple Silicon (returns True when MPS available)
- macOS without MPS support (returns False)
- Windows/Linux (hasattr guard prevents AttributeError)
Eliminates memory spike for long videos by:
- Pre-allocating final_video in Phase 3 before any batch processing
- Writing VAE-decoded RGB directly to final_video (no batch_samples accumulation)
- For RGBA: allocating 4 channels upfront, writing RGB in Phase 3, alpha in Phase 4
- Processing batches in-place through color correction and normalization
- Moving temporal overlap blending to Phase 3 decode phase
Fixes#130 (DefaultCPUAllocator: not enough memory for long video)
- Use torch.nn.attention.sdpa_kernel() (new API) with CUDNN_ATTENTION backend
- Fallback to torch.backends.cuda.sdp_kernel() when not available
Thanks to @eadwu for the original PR #317
Core Fixes:
- Reset seed per batch to ensure deterministic generation across sessions and batch positions
- Fix temporal overlap logging when automatically reset to prevent incorrect frame counts
- Fix NoneType attribute error in VAE tiled encode/decode at maximum resolution (#296)
BlockSwap & Caching Architecture:
- Move BlockSwap state (_block_swap_config, _blockswap_bypass_protection) from runner to model
- Ensures state survives runner recreation during independent DiT/VAE caching scenarios
- Fix runner template caching to trigger when either DiT or VAE becomes cached (bidirectional)
- Resolves BlockSwap reload failures when only DiT was cached (#297)
Model Discovery:
- Implement case-insensitive YAML path resolution for extra_model_paths.yaml (#289-#295)
- Add debug logging for model discovery (searched paths, validation status, cache hits)
- Support any case variation (seedvr2, SEEDVR2, SeedVR2) in ComfyUI configuration
- Fix: OpenCV memory layout error in tile debug visualization (#283)
- Fix: macOS MPS allocator fallback for safetensors loading (#290)
- Fix: Windows log buffering with flush=True (#278)
- Fix: ComfyUI registry icon URL (raw.githubusercontent)
- Feature: Version display in node name and CLI/ComfyUI header
- Feature: GitHub Sponsors support link
- License: Migrate from MIT to Apache 2.0 to match Bytedance Seed official repo
- Improve output folder naming: batch creates {folder}_upscaled/ sibling with original filenames, single file adds _upscaled suffix
- Add RGBA alpha channel detection and preservation (matches ComfyUI)
- Convert all output paths to absolute for clarity in logs
- Replace dual glob loops with single iterdir scan for cross-platform consistency
- Fixes duplicate file processing in batch mode on Windows case-insensitive filesystem
- Improves directory scanning performance 2-3x by reducing filesystem operations
- Add ComfyUI registry logo
- Add ROCm/HIP detection to prevent NVIDIA-specific cuDNN workaround on AMD systems
- Add defensive hasattr checks for torch.cuda and cudnn.is_available()
- Add try-except fallback in _conv_forward to handle cuDNN call failures gracefully
- Resolves 'GET was unable to find an engine' errors on PyTorch 2.9+ dev builds
- Resolves 'ATen not compiled with cuDNN support' errors on ROCm platforms
- Bump version to 2.5.7
- Replace split-stack-mean with unflatten in unconcat_coalesce
- Corrects computation order to eliminate plastic/high-specular artifacts
- Maintains torch.compile compatibility (no .item() graph breaks)
- Applied to both dit_3b and dit_7b models
- Replace all_transformed_videos storage with lightweight batch_metadata indices
- Reconstruct transformed videos on-demand in Phase 4 only when needed
- Add missing cleanup for input_images tensor in postprocess finally block
- Fix release_tensor_memory to handle CPU/CUDA/MPS consistently
- Extract helper functions for batch preparation and 4n+1 padding
- Remove duplicate interrupt_fn key from context initialization
- Fix AdaIN non-contiguous tensor error by using reshape() instead of view()
- Add cuDNN availability checks to prevent ROCm 'ATen not compiled with cuDNN' error
Add defensive checks for torch.mps.is_available() to handle PyTorch versions where the method doesn't exist on non-Mac platforms. Resolves AttributeError: module 'torch.mps' has no attribute 'is_available'
Adrien Toupet