rife426.pth and possibly other new checkpoints contain extra modules
used during training (teacher network, caltime scheduler) that are not
part of the IFNet inference architecture. These cause
load_state_dict to fail with "Unexpected key(s)" errors.
Now export_onnx.py filters the state_dict to keep only keys that match
the model architecture before loading, with strict=True to catch any
real missing keys.
Generated with [Devin](https://devin.ai)
Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Update rife_arch.py with support for new architectures:
- v4.17: Head_417 encoder, IFBlock with 16 extra channels
- v4.26: 5 IFBlocks (block4 extra), lastconv 4*13 channels,
feat_out return, no ensemble, 5 scale levels
- Head/Head_417 classes for v4.17/v4.26 encoders
- warp() fix: MPS padding_mode, dtype mismatch, get_torch_device()
Update export_onnx.py:
- Add rife417.pth and rife426.pth to CKPT_NAME_VER_DICT
- Add CKPT_FALLBACK_URLS with HuggingFace mirrors for all models
- Add export calls for rife49, rife417, rife426, sudo_rife4
Update load_rife_config.json with 3 new ONNX model options.
Generated with [Devin](https://devin.ai)
Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
The frames arrive from generate_frames_rife on CPU, but the engine output
(tile_out) is on CUDA. The accumulator tensors (output, weight, window)
were created on frame_0.device (CPU), causing a RuntimeError when mixing
devices in the feathering blend. Now all tensors are explicitly moved to
the CUDA device at the start of infer_tiled.
Generated with [Devin](https://devin.ai)
Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Ported and adapted from Fannovel16/ComfyUI-Frame-Interpolation:
- gc.collect() after soft_empty_cache() to reduce RAM fragmentation
- Explicit float32 cast in postprocess_frames for fp16 engine safety
- InterpolationStateList class + MakeInterpolationStateList node to
skip/keep specific frame pairs during interpolation
- Per-pair multiplier schedule (comma-separated list) overriding uniform
multiplier, with automatic padding to match the number of pairs
- Automatic tiling with cosine feathering when frame dimensions exceed
the TensorRT engine optimization profile (fixes 1440x2560 with max=1920)
- Padding with replicate mode when frame dimensions are below profile min
- get_input_profile_bounds() on Engine to retrieve min/opt/max shapes
- Batch inference: process multiple (pair, timestep) tasks per GPU call
with dynamic batch axis in ONNX export and engine profile
- Backward compatible: all new features are opt-in via optional inputs
Generated with [Devin](https://devin.ai)
Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
- Auto-install now only installs the matching TensorRT wheels instead of the
multi-GB cuda-toolkit package from PyPI.
- Use a single pip install -r call per requirements file for faster dependency
resolution and better cache reuse.
- Add install-success/failure markers to avoid repeating the install on every
ComfyUI startup.
- Fix pyproject.toml Repository and PublisherId to point to
huchukato/ComfyUI-RIFE-TensorRT-Auto.
Generated with [Devin](https://devin.ai)
Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Requirements updates:
- Default to CUDA 13 with TensorRT 10.14.1.48 (requirements.txt)
- Add cuda-toolkit version constraints (>=13.0.0,<13.1.0)
- Rename requirements_cu13.txt -> requirements_cu12.txt for legacy support
- Add cuda-toolkit constraint for CUDA 12 (>=12.8.0,<13.0.0)
CUDA toolkit detection:
- Add _setup_cuda_dll_path() to auto-detect CUDA installation
- Check CUDA_PATH, CUDA_HOME, and default Windows install paths
- Handle CUDA 13+ bin/x64 subdirectory for cudart64.dll
- Display download link if CUDA not found
Engine building updates:
- Add resolution profiles (small: 480-896px, medium: 720-1280px)
- Add 'custom' profile with CustomResolutionConfig node
- Include profile name in engine filename for separate caching
- Reduce default VRAM usage from ~15GB to ~2-3GB
