From 1f3bfe02eff226404b2c1a34efa33a434a239a1d Mon Sep 17 00:00:00 2001 From: solidlime Date: Wed, 7 Jan 2026 20:09:11 +0900 Subject: [PATCH] Initial implementation of Random Image Picker node - Single image and folder random selection modes - Subfolder scanning support - Resolution output (width/height) - Seed control for reproducible random selection - Support for PNG, JPEG, WebP, BMP, GIF formats --- .gitignore | 0 .serena/.gitignore | 1 + .serena/memories/code_style_conventions.md | 35 +++++ .serena/memories/codebase_structure.md | 32 ++++ .serena/memories/project_purpose.md | 22 +++ .serena/memories/suggested_commands.md | 28 ++++ .serena/memories/task_completion_checklist.md | 34 +++++ .serena/memories/tech_stack.md | 23 +++ .serena/project.yml | 84 +++++++++++ README.md | 99 ++++++++++++ __init__.py | 8 + random_image_picker.py | 141 ++++++++++++++++++ 12 files changed, 507 insertions(+) create mode 100644 .gitignore create mode 100644 .serena/.gitignore create mode 100644 .serena/memories/code_style_conventions.md create mode 100644 .serena/memories/codebase_structure.md create mode 100644 .serena/memories/project_purpose.md create mode 100644 .serena/memories/suggested_commands.md create mode 100644 .serena/memories/task_completion_checklist.md create mode 100644 .serena/memories/tech_stack.md create mode 100644 .serena/project.yml create mode 100644 README.md create mode 100644 __init__.py create mode 100644 random_image_picker.py diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..e69de29 diff --git a/.serena/.gitignore b/.serena/.gitignore new file mode 100644 index 0000000..14d86ad --- /dev/null +++ b/.serena/.gitignore @@ -0,0 +1 @@ +/cache diff --git a/.serena/memories/code_style_conventions.md b/.serena/memories/code_style_conventions.md new file mode 100644 index 0000000..27f9fb7 --- /dev/null +++ b/.serena/memories/code_style_conventions.md @@ -0,0 +1,35 @@ +# Code Style and Conventions + +## Naming Conventions +- **Classes**: PascalCase (例: `RandomImagePicker`) +- **Functions/Methods**: snake_case (例: `load_image`, `get_image_files`) +- **Constants**: UPPER_SNAKE_CASE (例: `NODE_CLASS_MAPPINGS`) +- **Private methods**: アンダースコアなし（staticmethodを活用） + +## Type Hints +- **使用**: 全ての関数/メソッドパラメータと戻り値に型ヒントを使用 +- **例**: `def load_image_file(image_path: str) -> Tuple[torch.Tensor, int, int]:` + +## Docstrings +- **スタイル**: Google style docstrings +- **必須箇所**: + - すべてのクラス + - すべてのpublicメソッド/関数 + - staticmethod +- **内容**: + - 簡潔な説明 + - Args: 引数の説明 + - Returns: 戻り値の説明 + +## Import Order +1. 標準ライブラリ +2. サードパーティライブラリ +3. ComfyUI関連 +4. ローカルモジュール + +## ComfyUI Specific +- **INPUT_TYPES**: classmethodで定義、辞書形式で入力パラメータを定義 +- **RETURN_TYPES**: タプル形式で出力型を定義 +- **RETURN_NAMES**: タプル形式で出力名を定義 +- **FUNCTION**: 実行される関数名を文字列で指定 +- **CATEGORY**: ノードのカテゴリを文字列で指定 diff --git a/.serena/memories/codebase_structure.md b/.serena/memories/codebase_structure.md new file mode 100644 index 0000000..6d00fcb --- /dev/null +++ b/.serena/memories/codebase_structure.md @@ -0,0 +1,32 @@ +# Codebase Structure + +## Directory Layout +``` +Comfyui-Random_Image_Picker/ +├── .github/ +│ └── copilot-instructions.md # AI assistant instructions +├── .serena/ # Serena project config +├── __init__.py # Package entry point +└── random_image_picker.py # Main node implementation +``` + +## File Descriptions + +### `__init__.py` +- パッケージのエントリーポイント +- `NODE_CLASS_MAPPINGS`と`NODE_DISPLAY_NAME_MAPPINGS`をインポートしてエクスポート +- ComfyUIがカスタムノードを認識するために必要 + +### `random_image_picker.py` +- メインの実装ファイル +- `RandomImagePicker`クラス: ノードの本体 + - `INPUT_TYPES()`: 入力パラメータの定義 + - `get_image_files()`: 画像ファイルのリスト取得 + - `load_image_file()`: 画像ファイルの読み込みとテンソル変換 + - `load_image()`: メイン処理（モードに応じた画像読み込み） +- ノード登録用の定数 + +## Future Extensions +- 追加の画像処理機能 +- フィルタリングオプション +- プレビュー機能 diff --git a/.serena/memories/project_purpose.md b/.serena/memories/project_purpose.md new file mode 100644 index 0000000..b08b5bf --- /dev/null +++ b/.serena/memories/project_purpose.md @@ -0,0 +1,22 @@ +# Project Purpose + +**Project Name**: Comfyui-Random_Image_Picker + +## Overview +ComfyUIカスタムノード - ランダム画像選択機能 + +## Core Features +1. **単一画像ロード**: 指定された画像ファイルを読み込み +2. **フォルダランダムロード**: フォルダ内からランダムに画像を選択 +3. **モード切り替え**: ボタンで単一/フォルダモードを切り替え +4. **サブフォルダスキャン**: オプションでサブフォルダも検索対象に +5. **解像度情報出力**: 画像と共にwidth, heightを出力 + +## Output +- IMAGE: ComfyUI形式の画像テンソル +- width: 画像の幅（整数） +- height: 画像の高さ（整数） + +## Target System +- ComfyUI custom node +- Python-based implementation diff --git a/.serena/memories/suggested_commands.md b/.serena/memories/suggested_commands.md new file mode 100644 index 0000000..49348ab --- /dev/null +++ b/.serena/memories/suggested_commands.md @@ -0,0 +1,28 @@ +# Suggested Commands + +## Windows System Commands +- `ls` または `dir`: ディレクトリ内容の表示 +- `cd `: ディレクトリ移動 +- `Get-Content `: ファイル内容の表示 +- `Select-String -Path -Pattern `: ファイル内検索 + +## Git Commands +- `git status`: 変更状況の確認 +- `git add .`: 変更をステージング +- `git commit -m "message"`: コミット +- `git push`: リモートへプッシュ + +## Python Development +- `python -m py_compile `: Pythonファイルの構文チェック +- `python `: Pythonスクリプトの実行 + +## ComfyUI Testing +- ComfyUIを起動してカスタムノードをテスト +- カスタムノードは `custom_nodes/Comfyui-Random_Image_Picker/` に配置 + +## Code Quality (推奨) +- **Black**: `python -m black ` - コードフォーマット +- **Flake8**: `python -m flake8 ` - リンティング +- **MyPy**: `python -m mypy ` - 型チェック + +Note: これらのツールは必要に応じてインストール diff --git a/.serena/memories/task_completion_checklist.md b/.serena/memories/task_completion_checklist.md new file mode 100644 index 0000000..456f8d8 --- /dev/null +++ b/.serena/memories/task_completion_checklist.md @@ -0,0 +1,34 @@ +# Task Completion Checklist + +## タスク完了時の必須作業 + +### 1. コード品質チェック +- [ ] 構文エラーがないことを確認 +- [ ] 型ヒントが正しく付与されているか +- [ ] Docstringsが適切に書かれているか + +### 2. ComfyUI互換性 +- [ ] `INPUT_TYPES`が正しく定義されているか +- [ ] `RETURN_TYPES`と`RETURN_NAMES`が一致しているか +- [ ] ノードの登録（`NODE_CLASS_MAPPINGS`）が正しいか + +### 3. ドキュメント +- [ ] README.mdが最新の情報か +- [ ] 使用方法が明確に記載されているか +- [ ] 公開情報に個人情報が含まれていないか + +### 4. Git管理 +- [ ] 変更をコミット: `git add . && git commit -m "descriptive message"` +- [ ] 適切なタイミングでプッシュ: `git push` + +### 5. テスト +- [ ] ComfyUIでノードが正しく読み込まれるか +- [ ] 単一画像モードが動作するか +- [ ] フォルダモードが動作するか +- [ ] サブフォルダスキャンが動作するか +- [ ] 出力（IMAGE, width, height）が正しいか + +## 区切りのいいタイミング +- 機能追加完了時 +- バグ修正完了時 +- リファクタリング完了時 diff --git a/.serena/memories/tech_stack.md b/.serena/memories/tech_stack.md new file mode 100644 index 0000000..872d4de --- /dev/null +++ b/.serena/memories/tech_stack.md @@ -0,0 +1,23 @@ +# Tech Stack + +## Programming Language +- **Python 3.x** + +## Dependencies +- **ComfyUI**: カスタムノードのベースシステム +- **PyTorch**: 画像テンソル処理 +- **PIL (Pillow)**: 画像ファイル読み込み +- **NumPy**: 配列処理 +- **folder_paths**: ComfyUI標準パス管理 + +## Supported Image Formats +- PNG (.png) +- JPEG (.jpg, .jpeg) +- WebP (.webp) +- BMP (.bmp) +- GIF (.gif) + +## ComfyUI Node Structure +- `NODE_CLASS_MAPPINGS`: ノードクラスの登録辞書 +- `NODE_DISPLAY_NAME_MAPPINGS`: 表示名の登録辞書 +- `__init__.py`: エントリーポイント diff --git a/.serena/project.yml b/.serena/project.yml new file mode 100644 index 0000000..13a8395 --- /dev/null +++ b/.serena/project.yml @@ -0,0 +1,84 @@ +# list of languages for which language servers are started; choose from: +# al bash clojure cpp csharp csharp_omnisharp +# dart elixir elm erlang fortran go +# haskell java julia kotlin lua markdown +# nix perl php python python_jedi r +# rego ruby ruby_solargraph rust scala swift +# terraform typescript typescript_vts yaml zig +# Note: +# - For C, use cpp +# - For JavaScript, use typescript +# Special requirements: +# - csharp: Requires the presence of a .sln file in the project folder. +# When using multiple languages, the first language server that supports a given file will be used for that file. +# The first language is the default language and the respective language server will be used as a fallback. +# Note that when using the JetBrains backend, language servers are not used and this list is correspondingly ignored. +languages: +- python + +# the encoding used by text files in the project +# For a list of possible encodings, see https://docs.python.org/3.11/library/codecs.html#standard-encodings +encoding: "utf-8" + +# whether to use the project's gitignore file to ignore files +# Added on 2025-04-07 +ignore_all_files_in_gitignore: true + +# list of additional paths to ignore +# same syntax as gitignore, so you can use * and ** +# Was previously called `ignored_dirs`, please update your config if you are using that. +# Added (renamed) on 2025-04-07 +ignored_paths: [] + +# whether the project is in read-only mode +# If set to true, all editing tools will be disabled and attempts to use them will result in an error +# Added on 2025-04-18 +read_only: false + +# list of tool names to exclude. We recommend not excluding any tools, see the readme for more details. +# Below is the complete list of tools for convenience. +# To make sure you have the latest list of tools, and to view their descriptions, +# execute `uv run scripts/print_tool_overview.py`. +# +# * `activate_project`: Activates a project by name. +# * `check_onboarding_performed`: Checks whether project onboarding was already performed. +# * `create_text_file`: Creates/overwrites a file in the project directory. +# * `delete_lines`: Deletes a range of lines within a file. +# * `delete_memory`: Deletes a memory from Serena's project-specific memory store. +# * `execute_shell_command`: Executes a shell command. +# * `find_referencing_code_snippets`: Finds code snippets in which the symbol at the given location is referenced. +# * `find_referencing_symbols`: Finds symbols that reference the symbol at the given location (optionally filtered by type). +# * `find_symbol`: Performs a global (or local) search for symbols with/containing a given name/substring (optionally filtered by type). +# * `get_current_config`: Prints the current configuration of the agent, including the active and available projects, tools, contexts, and modes. +# * `get_symbols_overview`: Gets an overview of the top-level symbols defined in a given file. +# * `initial_instructions`: Gets the initial instructions for the current project. +# Should only be used in settings where the system prompt cannot be set, +# e.g. in clients you have no control over, like Claude Desktop. +# * `insert_after_symbol`: Inserts content after the end of the definition of a given symbol. +# * `insert_at_line`: Inserts content at a given line in a file. +# * `insert_before_symbol`: Inserts content before the beginning of the definition of a given symbol. +# * `list_dir`: Lists files and directories in the given directory (optionally with recursion). +# * `list_memories`: Lists memories in Serena's project-specific memory store. +# * `onboarding`: Performs onboarding (identifying the project structure and essential tasks, e.g. for testing or building). +# * `prepare_for_new_conversation`: Provides instructions for preparing for a new conversation (in order to continue with the necessary context). +# * `read_file`: Reads a file within the project directory. +# * `read_memory`: Reads the memory with the given name from Serena's project-specific memory store. +# * `remove_project`: Removes a project from the Serena configuration. +# * `replace_lines`: Replaces a range of lines within a file with new content. +# * `replace_symbol_body`: Replaces the full definition of a symbol. +# * `restart_language_server`: Restarts the language server, may be necessary when edits not through Serena happen. +# * `search_for_pattern`: Performs a search for a pattern in the project. +# * `summarize_changes`: Provides instructions for summarizing the changes made to the codebase. +# * `switch_modes`: Activates modes by providing a list of their names +# * `think_about_collected_information`: Thinking tool for pondering the completeness of collected information. +# * `think_about_task_adherence`: Thinking tool for determining whether the agent is still on track with the current task. +# * `think_about_whether_you_are_done`: Thinking tool for determining whether the task is truly completed. +# * `write_memory`: Writes a named memory (for future reference) to Serena's project-specific memory store. +excluded_tools: [] + +# initial prompt for the project. It will always be given to the LLM upon activating the project +# (contrary to the memories, which are loaded on demand). +initial_prompt: "" + +project_name: "Comfyui-Random_Image_Picker" +included_optional_tools: [] diff --git a/README.md b/README.md new file mode 100644 index 0000000..a6daf6a --- /dev/null +++ b/README.md @@ -0,0 +1,99 @@ +# Random Image Picker - ComfyUI Custom Node + +A ComfyUI custom node that provides flexible image loading with support for both single file and random folder selection. + +## Features + +- **Single Image Mode**: Load a specific image file +- **Folder Mode**: Randomly select an image from a folder +- **Subfolder Support**: Option to include subfolders in the search +- **Resolution Output**: Automatically outputs image width and height +- **Reproducible Random**: Seed control for consistent random selection + +## Installation + +1. Clone or download this repository to your ComfyUI custom nodes directory: + ```bash + cd ComfyUI/custom_nodes + git clone Comfyui-Random_Image_Picker + ``` + +2. Restart ComfyUI + +## Usage + +### Node Inputs + +- **path** (STRING): + - In Single mode: Full path to an image file + - In Folder mode: Full path to a folder containing images + +- **folder_mode** (BOOLEAN): + - `OFF` (Single): Load the specified image file + - `ON` (Folder): Randomly select an image from the folder + +- **include_subfolders** (BOOLEAN): + - `OFF`: Only scan the specified folder + - `ON`: Include all subfolders in the search + +- **seed** (INT): + - Random seed for reproducible image selection in Folder mode + - Range: 0 to 18446744073709551615 + +### Node Outputs + +- **IMAGE**: The loaded image in ComfyUI tensor format +- **width** (INT): Image width in pixels +- **height** (INT): Image height in pixels + +### Supported Image Formats + +- PNG (.png) +- JPEG (.jpg, .jpeg) +- WebP (.webp) +- BMP (.bmp) +- GIF (.gif) + +## Examples + +### Single Image Mode +``` +path: D:/images/photo.png +folder_mode: OFF +include_subfolders: OFF +seed: 0 +``` +Loads the specific image at `D:/images/photo.png` + +### Random Folder Mode +``` +path: D:/images/ +folder_mode: ON +include_subfolders: OFF +seed: 42 +``` +Randomly selects one image from `D:/images/` (excluding subfolders) + +### Random with Subfolders +``` +path: D:/images/ +folder_mode: ON +include_subfolders: ON +seed: 42 +``` +Randomly selects one image from `D:/images/` and all its subfolders + +## Technical Details + +- Images are converted to RGB format +- Output tensor format: `[batch, height, width, channels]` +- Pixel values normalized to 0.0-1.0 range +- Uses PyTorch tensors for ComfyUI compatibility + +## License + +MIT License + +## Author + +Created for ComfyUI diff --git a/__init__.py b/__init__.py new file mode 100644 index 0000000..07b6b85 --- /dev/null +++ b/__init__.py @@ -0,0 +1,8 @@ +""" +Random Image Picker Node for ComfyUI +Loads single images or random images from folders +""" + +from .random_image_picker import NODE_CLASS_MAPPINGS, NODE_DISPLAY_NAME_MAPPINGS + +__all__ = ['NODE_CLASS_MAPPINGS', 'NODE_DISPLAY_NAME_MAPPINGS'] diff --git a/random_image_picker.py b/random_image_picker.py new file mode 100644 index 0000000..accd7cd --- /dev/null +++ b/random_image_picker.py @@ -0,0 +1,141 @@ +""" +Random Image Picker Node Implementation +""" + +import os +import random +from pathlib import Path +from typing import Tuple, List +import folder_paths +from PIL import Image +import numpy as np +import torch + + +class RandomImagePicker: + """ + ComfyUI node that loads either a single image or a random image from a folder. + Supports subfolder scanning and outputs image with resolution information. + """ + + @classmethod + def INPUT_TYPES(cls): + return { + "required": { + "path": ("STRING", {"default": "", "multiline": False}), + "folder_mode": ("BOOLEAN", {"default": False, "label_on": "Folder", "label_off": "Single"}), + "include_subfolders": ("BOOLEAN", {"default": False, "label_on": "ON", "label_off": "OFF"}), + "seed": ("INT", {"default": 0, "min": 0, "max": 0xffffffffffffffff}), + }, + } + + RETURN_TYPES = ("IMAGE", "INT", "INT") + RETURN_NAMES = ("IMAGE", "width", "height") + FUNCTION = "load_image" + CATEGORY = "image" + + @staticmethod + def get_image_files(directory: str, include_subfolders: bool = False) -> List[str]: + """ + Get all image files from a directory. + + Args: + directory: Directory path to scan + include_subfolders: Whether to include subfolders in the scan + + Returns: + List of image file paths + """ + supported_formats = {'.png', '.jpg', '.jpeg', '.webp', '.bmp', '.gif'} + image_files = [] + + if include_subfolders: + for root, _, files in os.walk(directory): + for file in files: + if Path(file).suffix.lower() in supported_formats: + image_files.append(os.path.join(root, file)) + else: + for file in os.listdir(directory): + file_path = os.path.join(directory, file) + if os.path.isfile(file_path) and Path(file).suffix.lower() in supported_formats: + image_files.append(file_path) + + return image_files + + @staticmethod + def load_image_file(image_path: str) -> Tuple[torch.Tensor, int, int]: + """ + Load an image file and convert to ComfyUI format. + + Args: + image_path: Path to the image file + + Returns: + Tuple of (image_tensor, width, height) + """ + img = Image.open(image_path) + + # Convert to RGB if needed + if img.mode != 'RGB': + img = img.convert('RGB') + + # Get dimensions + width, height = img.size + + # Convert to numpy array + img_array = np.array(img).astype(np.float32) / 255.0 + + # Convert to torch tensor and add batch dimension + # ComfyUI expects [batch, height, width, channels] + img_tensor = torch.from_numpy(img_array)[None,] + + return img_tensor, width, height + + def load_image(self, path: str, folder_mode: bool, include_subfolders: bool, seed: int): + """ + Load image based on mode settings. + + Args: + path: File or folder path + folder_mode: True for folder mode, False for single file mode + include_subfolders: Whether to scan subfolders + seed: Random seed for folder mode + + Returns: + Tuple of (image_tensor, width, height) + """ + if not path or not os.path.exists(path): + raise ValueError(f"Path does not exist: {path}") + + if folder_mode: + # Folder mode: pick random image + if not os.path.isdir(path): + raise ValueError(f"Folder mode enabled but path is not a directory: {path}") + + image_files = self.get_image_files(path, include_subfolders) + + if not image_files: + raise ValueError(f"No image files found in directory: {path}") + + # Use seed for reproducible random selection + random.seed(seed) + selected_image = random.choice(image_files) + + print(f"[Random Image Picker] Selected: {selected_image}") + return self.load_image_file(selected_image) + else: + # Single file mode + if not os.path.isfile(path): + raise ValueError(f"Single file mode enabled but path is not a file: {path}") + + return self.load_image_file(path) + + +# Node registration +NODE_CLASS_MAPPINGS = { + "RandomImagePicker": RandomImagePicker +} + +NODE_DISPLAY_NAME_MAPPINGS = { + "RandomImagePicker": "Random Image Picker" +}