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): Reduces flickering using frame history blending with motion-aware masking.
• Neural Refinement (DLAA-style): Lightweight CNN residual enhancement inspired by DLAA-like reconstruction
• Ghosting Reduction Logic: History clamping with motion-based alpha suppression to minimize trailing artifacts.
• Fixed Pattern Jittering: Deterministic 4-offset sub-pixel jitter for improved sampling stability (not Halton).
• Edge-Aware Weighting: Sobel edge detection for selective blurring to suppress aliasing while preserving details.
• Selective Edge-Based Anti-Aliasing: Applies blur to high-gradient areas using edge threshold masks.

---

Comparison

---

AdaptiveAA Comparison

TAA + DLAA Comparison

---

🚀 How to use

• Test the effect by increasing dlaa_strength to 0.8 or 1.0.
• If you use it in videos with fast motion, try increasing motion_sensitivity or decreasing taa_alpha.

Parameters

• taa_strength: Controls the impact of past frames. (Default: 0.6 | Fast motion: 0.7 | Static: 0.95)
• taa_alpha: Determines how quickly history updates. (Default: 0.4 | Aggressive AA: 0.3 | Ghost-free: 0.05)
• motion_sensitivity: For high-speed videos, try decreasing. (Default: 0.08 | Flicker-prone: 0.0 | Ghosting Risk: 0.3)
• jitter_scale: Amount of sub-pixel shifting for edge detection. (Default: 0.02 | Off: 0.0 | Maximum: 0.08)
• dlaa_strength: Strength of the deep learning sharpening. (Default: 0.3 | Pure AA: 0.0 | Aggressive: 1.0)
• edge_threshold: Determines which pixels are detected as edges. (Default: 0.2 | Hard edges: 0.35 | All: 0.05)
• blur_radius: The radius of the blur applied to edges. (Default: 0 | Softer: 2–3 | Very soft: 4–5)
• reset_history: Clears temporal history memory. (Default: False | Enable 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.