Merge branch 'maisi_readme' of https://github.com/Can-Zhao/tutorials into maisi_readme

Author: Can-Zhao

generation/maisi/README.md

@@ -76,11 +76,11 @@ We retrained several state-of-the-art diffusion model-based methods using our da
 
 **Table 3:** Inference Time Cost and GPU Memory Usage. `DM Time` refers to the time required for diffusion model inference. `VAE Time` refers to the time required for VAE decoder inference. The total inference time is the sum of `DM Time` and `VAE Time`. The experiment was conducted on an A100 80G GPU.
 
-During inference, the peak GPU memory usage occurs during the VAE's decoding of latent features.  
-To reduce GPU memory usage, we can either increase `autoencoder_tp_num_splits` or reduce `autoencoder_sliding_window_infer_size`.  
+During inference, the peak GPU memory usage occurs during the VAE's decoding of latent features.
+To reduce GPU memory usage, we can either increase `autoencoder_tp_num_splits` or reduce `autoencoder_sliding_window_infer_size`.
 Increasing `autoencoder_tp_num_splits` has a smaller impact on the generated image quality, while reducing `autoencoder_sliding_window_infer_size` may introduce stitching artifacts and has a larger impact on the generated image quality.
 
-When `autoencoder_sliding_window_infer_size` is equal to or larger than the latent feature size, the sliding window will not be used, and the time and memory costs remain the same. 
+When `autoencoder_sliding_window_infer_size` is equal to or larger than the latent feature size, the sliding window will not be used, and the time and memory costs remain the same.
 
 
 ### Training GPU Memory Usage