FLSampler (BSS) for ComfyUI 🔬
A high-performance custom sampler inspired by the physiology of human sight (**Foveated Vision**). Engineered to deliver stunning cinematic clarity, rich micro-textures (skin, hair, fabrics), and precise depth-of-detail control inside the latent space—with zero performance overhead.
> ⚡ Ultimate Speed & Quality Combo:
> To achieve the ultimate balance of breathtaking visual clarity and extreme speed, we highly recommend pairing this node with our optimization suite ANIMA_BOOSTER
🔗 GitHub Repository (Full Guide & Physics): https://github.com/BlackSnowSkill/ComfyUI-BSS_FLSampler
🔬 How it Works
Instead of uniform denoising, FLSampler selectively enhances latent focus zones:
Differential Latent Analysis: Dynamically tracks where structures and object boundaries are forming.
Local Contrast (Sharpness Boost): Unsharp-masks active focus zones directly in latent space for ultra-sharp details (safe default 0.5, range 0.0–3.0).
Stochastic Texture Injection: Adds controlled micro-noise to focus areas, naturally resolving into skin pores, clothing fabrics, wood grains, or hair, preventing flat plastic surfaces.
BSS Premium UI: Integrated dark-matte & gold custom theme.
📂 Quick Installation
1. Open ComfyUI Manager -> Install via Git URL.
2. Paste this URL: https://github.com/BlackSnowSkill/ComfyUI-BSS_FLSampler
3. Click Install and restart ComfyUI.
For detailed parameters, mathematics, and recommended workflows, please check the GitHub README
☕ Support & License
Support Development: Support me and get exclusive models on Boosty!
License & Usage: © 2026 blacksnowskill (BSS). All rights reserved. This project is protected by copyright. Copying, distribution, merging, or use on other websites/repositories without explicit written permission is prohibited.
Description
What's New
🔧 Live Preview Support FLS now displays a real-time step-by-step preview during generation, just like the standard KSampler. You can watch your image form in real time directly in the ComfyUI interface.
📋 Full Metadata Compatibility Images generated with FLS now save complete generation metadata (seed, steps, CFG, sampler, scheduler, etc.) in a format fully compatible with CivitAI and other metadata parsers. Previously, images generated through FLS were missing readable generation data when uploaded to external platforms.
🔄 Seed Control The seed input now includes the standard "control_after_generate" behavior (randomize / fixed / increment buttons), matching the KSampler experience.
📦 Latent Metadata Preservation FLS now correctly preserves all input latent metadata (batch_index, noise_mask, etc.) through the sampling pipeline, matching the exact behavior of ComfyUI's built-in common_ksampler. This fixes potential issues with downstream nodes that depend on latent metadata.
🏗️ Modern Architecture Compatibility Fixed compatibility with modern DiT-based architectures (Anima, Flux, etc.) that output 5D latent tensors. The foveated mask pipeline now correctly handles both standard 4D [B, C, H, W] and modern 5D [B, C, T, H, W] tensor layouts.