Update sampler_explaination.md

sampler_explaination.md

@@ -2,9 +2,6 @@
 
 (made using Gemini and re-touched a little so it's readable)
 
-Diffusion models represent a powerful class of generative models that have achieved remarkable success in synthesizing high-quality data, particularly in image generation. The fundamental principle behind these models involves a two-stage process: a forward diffusion process where data is progressively noised over time, and a reverse diffusion process where a model learns to denoise the data back to its original form. The sampling process, which occurs during the reverse diffusion, is critical as it dictates how new data points are generated from a learned probability distribution.
-
-Within the ecosystem of generative AI tools, platforms like ComfyUI offer users a high degree of flexibility and control over their workflows, including the ability to implement and utilize custom sampling methods. These custom samplers allow for the exploration of novel techniques that can potentially enhance the quality, efficiency, or artistic style of the generated outputs. ComfyUI's node-based architecture facilitates the integration of such custom functionalities, enabling researchers and practitioners to go beyond the standard sampling algorithms provided by underlying libraries like k-diffusion.3 The provided Python code snippet presents an implementation of such a custom sampling method designed for use within the ComfyUI environment. Understanding the intricacies of this code is crucial for those seeking to leverage its unique features or to further innovate in the realm of diffusion model sampling.
 
 The function _matrix\_batch\_slerp_ implements batched spherical linear interpolation (SLERP). SLERP is a technique used to interpolate between two points on a unit sphere along the great circle that connects them, maintaining a constant angular velocity. This is particularly useful for interpolating rotations or, more generally, directions in high-dimensional spaces. The function is decorated with @torch.no\_grad(), indicating that the operations within it should not be tracked for gradient computation, as it is likely used during inference or sampling. The function takes three arguments: t, which likely represents the original batch of tensors; tn, which is likely the normalized version of t; and w, which probably contains the weights or interpolation factors for each tensor in the batch.  
 The first step inside matrix\_batch\_slerp is the calculation of dot products between all pairs of normalized tensors in tn: