diff --git a/README.md b/README.md
index 50be0d6..576a56b 100644
--- a/README.md
+++ b/README.md
@@ -59,29 +59,6 @@ Use this when you already have an external loop/for/while node pack and you want
 5. `GetPathByIndex.filepath` → your loader node (Load Image / Load Video / etc.)
 6. Do your processing + save/export inside your external loop pack
 
-### Node reference
-
-#### `LoadFilePathsFromFolder`
-- **Parameters**
-  - `folder_path`: folder to scan
-  - `extension`: pattern like `"*.png"`, `"*.jpg"`, `"*.txt"`
-- **Outputs**
-  - `filepaths`: newline-separated full paths
-  - `filenames`: newline-separated base names (no extension)
-  - `count`: number of matched files
-
-#### `GetPathByIndex`
-
-- **Inputs**
-  - `filepaths`: from `LoadFilePathsFromFolder`
-  - `filenames`: from `LoadFilePathsFromFolder`
-- **Parameter**
-  - `index`: 0-based index
-- **Outputs**
-  - `filepath`: selected full path
-  - `filename`: selected base name
-
-
 <a id="option-b-internal-loop"></a>
 ## Option B — Internal loop (this repo’s loop node, list batching)
 
@@ -93,15 +70,6 @@ Use this when you want the simplest setup: `FilePathsForLoop` returns lists, and
 - (Optional) `FilePathsEnsureExecution`: “anchors” a route so it definitely runs (useful for save/write/export routes) (UI: `File Paths Loop Ensure Execution`)
 - `FilePathsLoopClose`: loop terminator / completion signal (UI: `File Paths Loop End`)
 
-### Memory note
-
-`FilePathsForLoop` uses **ComfyUI list batching** (it sets `OUTPUT_IS_LIST`). This is not a “while/for loop” that runs one full item end-to-end.
-
-- **What you may observe**: ComfyUI often runs **node-by-node for the batch**. So a route like `Load X From Path` → `Process` → `Save` can look like “all loads”, then “all processing”, then “all saves” (not Load→Process→Save per file).
-- **Why memory can grow**: batching can keep more intermediate results “alive” until later nodes run; heavy nodes (models / large frames / big tensors) can push VRAM/RAM peak usage.
-- **Practical tip**: if you notice memory climbing, add “Clean VRAM” / “Clean RAM” (or equivalent) at safe points after heavy steps.
-- **If you need strict sequential iteration** (finish item 0 completely before item 1): use an external loop/for/while node pack and Option A.
-
 ### Example workflow (internal loop: once per file)
 
 ![Option B — Internal Loop Node Method](screenshots/Option%20B%20(Interal%20Loop%20Node%20Method).jpg)
@@ -113,46 +81,14 @@ Use this when you want the simplest setup: `FilePathsForLoop` returns lists, and
 5. `current_index` → `FilePathsLoopClose.current_index`
 6. (Optional) `FilePathsEnsureExecution.passthrough` → `FilePathsLoopClose.passthrough` (this “anchors” the route so it executes)
 
-### Node reference (internal loop nodes)
+### Memory note
 
-#### `FilePathsForLoop`
+`FilePathsForLoop` uses **ComfyUI list batching** (it sets `OUTPUT_IS_LIST`). This is not a “while/for loop” that runs one full item end-to-end.
 
-- **Parameters**
-  - `folder_path`
-  - `extension`
-- **Outputs** (**all are lists**)
-  - `current_filepath`
-  - `current_filename`
-  - `current_index` (0-based)
-  - `total_file_count`
-
-**Key detail:** this node sets `OUTPUT_IS_LIST`. Downstream nodes receive **one item per execution** (not the whole list).
-
-#### `FilePathsEnsureExecution`
-
-- **What it does**: “collects” outputs so a route becomes **required** (and actually runs).
-
-ComfyUI schedules execution based on **dependencies**: if nothing downstream “needs” a route’s results, ComfyUI may skip that route (or only run part of it).
-
-`FilePathsEnsureExecution` is a simple way to **guarantee a route runs**: plug the outputs you care about into `passthrough_1`…`passthrough_5`, then plug `passthrough` into `FilePathsLoopClose.passthrough` so the graph *depends on* that route.
-
-Practical rule of thumb: you usually only need to connect the **terminal node/output** of the route you want to guarantee (the last node in that route). If the end node must run, everything upstream of it becomes required too.
-
-Example route: `Load Image From Path` → processing → `Save Image` → connect the **`Save Image` output** to `FilePathsEnsureExecution.passthrough_*` to “anchor” the whole chain.
-- **Inputs**
-  - `passthrough_1` … `passthrough_5`: any type (`*`)
-- **Outputs**
-  - `passthrough`: first non-None input
-
-Tip: if you need more than 5 inputs, chain multiple `FilePathsEnsureExecution` nodes.
-
-#### `FilePathsLoopClose`
-
-- **Inputs**
-  - `current_index`: from `FilePathsForLoop` (required)
-  - `passthrough`: optional (often from `FilePathsEnsureExecution.passthrough`)
-- **Outputs**
-  - `processed_count`
+- **What you may observe**: ComfyUI often runs **node-by-node for the batch**. So a route like `Load X From Path` → `Process` → `Save` can look like “all loads”, then “all processing”, then “all saves” (not Load→Process→Save per file).
+- **Why memory can grow**: batching can keep more intermediate results “alive” until later nodes run; heavy nodes (models / large frames / big tensors) can push VRAM/RAM peak usage.
+- **Practical tip**: if you notice memory climbing, add “Clean VRAM” / “Clean RAM” (or equivalent) at safe points after heavy steps.
+- **If you need strict sequential iteration** (finish item 0 completely before item 1): use an external loop/for/while node pack and Option A.
 
 ## License