Update README.md

README.md

@@ -6,4 +6,32 @@ datasets:
 - bitmind/AFHQ
 - ILSVRC/imagenet-1k
 pipeline_tag: unconditional-image-generation
----
+---
+---
+license: apache-2.0
+language:
+- en
+datasets:
+- bitmind/AFHQ
+- ILSVRC/imagenet-1k
+pipeline_tag: unconditional-image-generation
+---
+
+# Transformer AutoRegressive Flow Model
+The TarFlow is proposed by [Zhai et al., 2024], which introduces stacks of autoregressive Transformer blocks (similar to MAF) into the building of affine coupling layers to do Non-Volume Preserving, combined with guidance and denoising }, finally achieves state-of-the-art results across multiple benchmarks.
+
+Let $z$ denotes the noise direction and $x$ denotes the image direction, both with size $(B,T,C)$, where B,T,C represent batch size, patchified sequence length, and feature dimension, respectively. For TarFlow model, an autoregressive block can be written as:
+
+\begin{equation}
+\begin{aligned}
+\text{Forward:\quad}z_t &= \exp(-s(x_{<t}))(x_t-u(x_{<t})),\\
+\text{Inverse:\quad}x_t &= \exp(s(x_{<t})) z_t +u(x_{<t}).
+\end{aligned}
+\end{equation}
+
+
+It's sampling process is extremely slow, and we want to accelerate it in []. In experiments, we found that the 
+
+
+
+[1] Zhai S, Zhang R, Nakkiran P, et al. Normalizing flows are capable generative models[J]. arXiv preprint arXiv:2412.06329, 2024.