Add information about the optional items in the ReadME.

Author: kizamimi

.gitignore

@@ -10,6 +10,7 @@ result_lcm.png
 model.ckpt
 *.png
 !assets/img2img_example.png
+!assets/cfg_conparision.png
 !images/inputs/input.png
 
 # Byte-compiled / optimized / DLL files

README-ja.md

@@ -307,6 +307,71 @@ if __name__ == "__main__":
     run()
 ```
 
+## オプション
+
+## Stochastic Similarity Filter
+
+![demo](assets\demo_06.gif)
+
+Stochastic Similarity Filterは動画入力時、前フレームからあまり変化しないときの変換処理を減らすことで、上のGIFの赤枠の様にGPUの負荷を軽減する。使用方法は以下のとおりである。
+
+```
+stream = StreamDiffusion(
+        pipe,
+        [32, 45],
+        torch_dtype=torch.float16,
+    )
+stream.enable_similar_image_filter(similar_image_filter_threshold,similar_image_filter_max_skip_frame)
+```
+
+関数で設定できる引数として以下がある。
+### similar_image_filter_threshold
+
+- 処理を休止する前フレームと現フレームの類似度の閾値
+
+### similar_image_filter_max_skip_frame
+
+- 休止中に変換を再開する最大の間隔
+
+## Residual CFG (RCFG)
+
+![rcfg](assets\cfg_conparision.png)
+
+RCFGはCFG使用しない場合と比較し、競争力のある計算量で近似的にCFGを実現させる方法である。StreamDiffusionの引数cfg_typeから指定可能である。
+
+RCFGは二種類あり、negative promptの指定項目なしのRCFG Self-Negativeとnegative promptが指定可能なOnetime-Negativeが利用可能である。計算量はCFGなしの計算量をN、通常のCFGありの計算量を２Nとしたとき、RCFG Self-NegativeはN回で、Onetime-NegativeはN+1回で計算できる。
+
+The usage is as follows:
+
+```
+# CFG なし
+cfg_type = "none"
+
+# 通常のCFG
+cfg_type = "full"
+
+# RCFG Self-Negative
+cfg_type = "self"
+
+# RCFG Onetime-Negative
+cfg_type = "initialize"
+
+stream = StreamDiffusion(
+        pipe,
+        [32, 45],
+        torch_dtype=torch.float16,
+        cfg_type = cfg_type
+    )
+
+stream.prepare(
+        prompt = "1girl, purple hair",
+        guidance_scale = guidance_scale,
+        delta = delta,
+    )
+```
+
+deltaはRCFGの効きをマイルドにする効果を持つ
+
 # 開発チーム
 
 [Aki](https://github.com/cumulo-autumn/),

README.md

@@ -303,6 +303,70 @@ if __name__ == "__main__":
     run()
 ```
 
+## Optionals
+
+## Stochastic Similarity Filter
+
+![demo](assets\demo_06.gif)
+
+Stochastic Similarity Filter reduces processing during video input by minimizing conversion operations when there is little change from the previous frame, thereby alleviating GPU processing load, as shown by the red frame in the above GIF. The usage is as follows:
+
+```
+stream = StreamDiffusion(
+        pipe,
+        [32, 45],
+        torch_dtype=torch.float16,
+    )
+stream.enable_similar_image_filter(similar_image_filter_threshold,similar_image_filter_max_skip_frame)
+```
+
+There are the following parameters that can be set as arguments in the function:
+
+### similar_image_filter_threshold
+
+- The threshold for similarity between the previous frame and the current frame before the processing is paused.
+
+### similar_image_filter_max_skip_frame
+
+- The maximum interval during the pause before resuming the conversion.
+
+## Residual CFG (RCFG)
+
+![rcfg](assets\cfg_conparision.png)
+
+RCFG is a method for approximately realizing CFG with competitive computational complexity compared to cases where CFG is not used. It can be specified through the cfg_type argument in the StreamDiffusion. There are two types of RCFG: one with no specified items for negative prompts RCFG Self-Negative and one where negative prompts can be specified RCFG Onetime-Negative. In terms of computational complexity, denoting the complexity without CFG as N and the complexity with a regular CFG as 2N, RCFG Self-Negative can be computed in N steps, while RCFG Onetime-Negative can be computed in N+1 steps.
+
+The usage is as follows:
+
+```
+# w/0 CFG
+cfg_type = "none"
+
+# CFG
+cfg_type = "full"
+
+# RCFG Self-Negative
+cfg_type = "self"
+
+# RCFG Onetime-Negative
+cfg_type = "initialize"
+
+stream = StreamDiffusion(
+        pipe,
+        [32, 45],
+        torch_dtype=torch.float16,
+        cfg_type = cfg_type
+    )
+
+stream.prepare(
+        prompt = "1girl, purple hair",
+        guidance_scale = guidance_scale,
+        delta = delta,
+    )
+```
+
+The delta has a moderating effect on the effectiveness of RCFG.
+
 # Development Team
 
 [Aki](https://github.com/cumulo-autumn/),