ComfyUI Video Anti-Aliasing Pack
Advanced anti-aliasing nodes for videos and images. VideoTAADLAA combines TAA with a DLAA-inspired pipeline for sharp, stable results, while VideoAdaptiveAA targets specific aliasing-prone regions. The system utilizes temporal accumulation, jittered sampling, and CNN-based refinement for superior edge quality.
Important
Disclaimer This node does not use NVIDIA's closed-source SDKs or native DLAA/DLSS binaries. Instead, it is a custom adaptation of Temporal and Spatial Anti-Aliasing techniques commonly found in modern game engines, rebuilt entirely from scratch using PyTorch tensor architecture specifically for ComfyUI video post-processing.
Preview
| TAA + DLAA Anti-Aliasing | Adaptive Anti-Aliasing |
|---|---|
 |
 |
Features
- Temporal Anti-Aliasing (TAA): Stabilizes flickering in video sequences using frame history.
- DLAA-inspired neural refinement: Neural-based cleanup of residual aliasing without losing texture detail.
- Ghosting-Free Logic: Advanced history clamping prevents trailing artifacts in fast motion.
- Halton Sequence Jittering: Improves sub-pixel sampling for cleaner edges.
- Edge-Aware Weighting: Preserves fine details while blending.
- Adaptive Anti-Aliasing (AdaptiveAA): Targets only aliasing-prone regions for localized smoothing.
Comparison
AdaptiveAA Comparison
 |
 |
TAA + DLAA Comparison
Parameters
🚀 TAA & DLAA Parameters
taa_strength: Controls the impact of past frames. (Rec: 0.9 | Fast motion: 0.7 | Static: 0.95)taa_alpha: Determines how quickly history updates. (Rec: 0.1 | Aggressive AA: 0.3 | Ghost-free: 0.05)jitter_scale: Amount of sub-pixel shifting for edge detection. (Rec: 0.5 | Off: 0.0 | Maximum: 1.0)dlaa_strength: Strength of the deep learning sharpening. (Rec: 0.7 | Pure AA: 0.0 | Aggressive: 1.0)
🎨 Edge AA & Control
edge_threshold: Determines which pixels are detected as edges. (Rec: 0.08 | Hard edges: 0.2 | All: 0.02)blur_radius: The radius of the blur applied to edges. (Rec: 1 | Softer: 2–3 | Very soft: 4–5)reset_history: Clears temporal history memory. (Normal: False | On scene change: True)
Installation
Recommended: Install via ComfyUI-Manager.
Manual installation:
cd ComfyUI/custom_nodes/
git clone https://github.com/MSXYZ-GenAI/comfyui-msxyz.git
License
This project is licensed under the MIT License - see the LICENSE file for details.