Potential fix for code scanning alert no. 8: Workflow does not contain permissions

Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
Merge pull request #25 from ComfyAssets/alert-autofix-1
2025-08-02 08:38:37 -07:00 · 2025-08-02 08:22:06 -07:00 · 2025-08-02 08:14:03 -07:00 · 2025-08-02 08:12:04 -07:00 · 2025-08-02 08:00:10 -07:00 · 2025-08-02 07:54:21 -07:00
67 changed files with 5641 additions and 325 deletions
@@ -25,6 +25,10 @@ per-file-ignores =
    __init__.py:F401,F403
    # Allow assertions in tests
    tests/*:S101
+    # Allow higher complexity for Gemini prompt module
+    kikotools/tools/gemini_prompt/logic.py:C901
+    kikotools/tools/gemini_prompt/models.py:C901
+    kikotools/tools/gemini_prompt/node.py:C901

 # Statistics
 count = True
@@ -0,0 +1,10 @@
+version: 2
+updates:
+  - package-ecosystem: "pip"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"
@@ -1,4 +1,6 @@
 name: Code Quality
+permissions:
+  contents: read

 on:
  push:
@@ -14,12 +16,12 @@ jobs:
    - uses: actions/checkout@v4

    - name: Set up Python 3.10
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
      with:
        python-version: '3.10'

    - name: Cache pip dependencies
-      uses: actions/cache@v3
+      uses: actions/cache@v4
      with:
        path: ~/.cache/pip
        key: ${{ runner.os }}-pip-quality-${{ hashFiles('**/requirements-dev.txt') }}
@@ -134,7 +136,7 @@ jobs:
    - uses: actions/checkout@v4

    - name: Set up Python 3.10
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
      with:
        python-version: '3.10'

@@ -165,7 +167,7 @@ jobs:
    - uses: actions/checkout@v4

    - name: Set up Python 3.10
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
      with:
        python-version: '3.10'

@@ -1,5 +1,8 @@
 name: Release

+permissions:
+  contents: read
+
 on:
  push:
    tags:
@@ -8,12 +11,14 @@ on:
 jobs:
  create-release:
    runs-on: ubuntu-latest
+    permissions:
+      contents: write

    steps:
    - uses: actions/checkout@v4

    - name: Set up Python 3.10
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
      with:
        python-version: '3.10'

@@ -109,7 +114,7 @@ jobs:
        EOF

    - name: Create GitHub Release
-      uses: softprops/action-gh-release@v1
+      uses: softprops/action-gh-release@v2
      with:
        tag_name: ${{ steps.get_version.outputs.version }}
        name: ComfyUI-KikoTools ${{ steps.get_version.outputs.version }}
@@ -1,5 +1,8 @@
 name: Tests

+permissions:
+  contents: read
+
 on:
  push:
    branches: [main, develop]
@@ -17,12 +20,12 @@ jobs:
      - uses: actions/checkout@v4

      - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
        with:
          python-version: ${{ matrix.python-version }}

      - name: Cache pip dependencies
-        uses: actions/cache@v3
+        uses: actions/cache@v4
        with:
          path: ~/.cache/pip
          key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements-dev.txt') }}
@@ -398,7 +401,7 @@ jobs:
      - uses: actions/checkout@v4

      - name: Set up Python 3.10
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
        with:
          python-version: "3.10"

@@ -159,3 +159,6 @@ test_images/
 test_outputs/
 experiments/
 .claude/
+
+# Gemini model cache
+.gemini_models_cache.json
@@ -8,14 +8,14 @@ repos:
    hooks:
      - id: black
        language_version: python3.10
-        args: ['--line-length=127']  # Match CI configuration
+        args: ['--line-length=88']  # Match CI configuration

  # Python linting with flake8
  - repo: https://github.com/pycqa/flake8
    rev: 7.3.0
    hooks:
      - id: flake8
-        args: ['--max-line-length=127', '--max-complexity=10']
+        args: ['--max-line-length=88', '--max-complexity=10']
        exclude: '^tests/'

  # Python type checking with mypy
@@ -0,0 +1,128 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, religion, or sexual identity
+and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the
+  overall community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or
+  advances of any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official e-mail address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement at
+.
+All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series
+of actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or
+permanent ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior,  harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within
+the community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.0, available at
+https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
+
+Community Impact Guidelines were inspired by [Mozilla's code of conduct
+enforcement ladder](https://github.com/mozilla/diversity).
+
+[homepage]: https://www.contributor-covenant.org
+
+For answers to common questions about this code of conduct, see the FAQ at
+https://www.contributor-covenant.org/faq. Translations are available at
+https://www.contributor-covenant.org/translations.
@@ -14,6 +14,19 @@ ComfyUI-KikoTools provides carefully crafted, production-ready nodes grouped und

 ### ✨ Current Tools

+| Tool | Description | Category |
+|------|-------------|----------|
+| [📐 Resolution Calculator](#-resolution-calculator) | Calculate upscaled dimensions with model optimization | Image Processing |
+| [📏 Width Height Selector](#-width-height-selector) | Preset-based dimension selection with visual swap | Dimension Control |
+| [🎲 Seed History](#-seed-history) | Advanced seed tracking with interactive history | Generation Control |
+| [⚙️ Sampler Combo](#️-sampler-combo) | Unified sampling configuration interface | Sampling |
+| [📦 Empty Latent Batch](#-empty-latent-batch) | Create empty latent batches with preset support | Latent Generation |
+| [💾 Kiko Save Image](#-kiko-save-image) | Enhanced image saving with popup viewer | File Management |
+| [📋 Display Text](#-display-text) | Smart text display with prompt detection | Text Display |
+| [🤖 Gemini Prompt Engineer](#-gemini-prompt-engineer) | AI-powered image analysis and prompt generation | AI Integration |
+| [🔍 Display Any](#-display-any) | Universal debugging tool for any data type | Debugging |
+| [🖼️ Image to Multiple Of](#️-image-to-multiple-of) | Adjust dimensions to multiples for compatibility | Image Processing |
+
 #### 📐 Resolution Calculator
 Calculate upscaled dimensions from image or latent inputs with precision.

@@ -29,6 +42,8 @@ Calculate upscaled dimensions from image or latent inputs with precision.
 - Ensure ComfyUI tensor compatibility
 - Optimize batch processing workflows

+![Resolution Calculator Example](examples/workflows/resolution_calculator_example.png)
+
 #### 📏 Width Height Selector
 Advanced preset-based dimension selection with visual swap button.

@@ -60,6 +75,8 @@ Advanced seed tracking with interactive history management and UI.
 - Maintain reproducibility across sessions
 - Compare results from different seeds efficiently

+![Seed History functionality is shown in various workflow examples]
+
 #### ⚙️ Sampler Combo
 Unified sampling configuration interface combining sampler, scheduler, steps, and CFG.

@@ -92,6 +109,8 @@ Advanced empty latent creation with preset support and batch processing capabili
 - Optimize memory usage with batch size planning
 - Quick preset-based latent generation for different aspect ratios

+![Empty Latent Batch Example](examples/workflows/empty_latent_batch_example.png)
+
 #### 💾 Kiko Save Image
 Enhanced image saving with format selection, quality control, and floating popup viewer.

@@ -104,6 +123,28 @@ Enhanced image saving with format selection, quality control, and floating popup
 - **Smart UI**: Auto-hide/show, minimize/maximize, roll-up functionality
 - **Popup Toggle**: Enable/disable popup viewer per save operation

+![Kiko Save Image Example](examples/workflows/kiko_save_image_example.png)
+
+#### 📋 Display Text
+Advanced text display node with intelligent formatting and enhanced user interaction.
+
+- **Smart Prompt Detection**: Automatically detects positive/negative prompt pairs and displays in split view
+- **Text Wrapping**: Proper word wrapping that reflows when node is resized
+- **Scrollable Content**: Mouse wheel scrolling for long texts with visual scroll indicators
+- **Copy Functionality**: Always-visible copy button with visual feedback
+- **Split View Mode**: Automatic detection and formatting of SDXL-style prompts
+- **Responsive Design**: Content adapts to node resizing with proper text reflow
+- **Clean Formatting**: Strips prompt labels when copying for direct use
+
+**Use Cases:**
+- Display generated prompts with proper formatting
+- Compare positive and negative prompts side-by-side
+- Copy prompts without manual label removal
+- View long text content with proper wrapping
+- Debug prompt generation workflows
+
+![Display Text Example](examples/workflows/display_text_example.png)
+
 #### 🤖 Gemini Prompt Engineer
 AI-powered image analysis using Google's Gemini to generate optimized prompts for various models.

@@ -114,6 +155,9 @@ AI-powered image analysis using Google's Gemini to generate optimized prompts fo
 - **Flexible API Key Management**: Environment variable, config file, or direct input
 - **Visual Status Feedback**: Real-time processing indicators and error states
 - **Help Integration**: Built-in setup guide and documentation
+- **Dynamic Model Refresh**: Fetch latest Gemini models with refresh button
+- **Model Caching**: Persistent model list storage for offline access
+- **Enhanced SDXL Prompts**: Improved formatting with layered structure and quality boosters

 **Use Cases:**
 - Reverse-engineer prompts from reference images
@@ -121,6 +165,45 @@ AI-powered image analysis using Google's Gemini to generate optimized prompts fo
 - Generate consistent style descriptions across workflows
 - Create detailed scene breakdowns for complex compositions
 - Analyze and replicate lighting/mood from existing artwork
+- Access latest Gemini models including 2.0 and 2.5 versions
+
+![Gemini Prompt Example](examples/workflows/gemini_prompt_example.png)
+
+#### 🔍 Display Any
+Universal debugging node that displays any type of input value or tensor information.
+
+- **Universal Input Acceptance**: Works with any data type (tensors, strings, numbers, lists, dicts)
+- **Two Display Modes**: Raw value showing string representation, or tensor shape extraction
+- **Nested Structure Support**: Finds tensors within complex nested data structures
+- **Debugging Focus**: Essential tool for understanding data flow and tensor dimensions
+- **Clean Output**: Formatted display directly in ComfyUI interface
+
+**Use Cases:**
+- Debug tensor dimensions at any point in workflow
+- Inspect latent space data structures
+- View metadata and configuration objects
+- Track shape changes through processing nodes
+- Understand complex data types in ComfyUI
+
+![Display Any Example](examples/workflows/display_any_example.png)
+
+#### 🖼️ Image to Multiple Of
+Adjusts image dimensions to be multiples of a specified value for model compatibility.
+
+- **Dimension Adjustment**: Ensures image dimensions are multiples of specified value (e.g., 64, 128)
+- **Two Processing Methods**: Center crop for minimal loss, or rescale to fit
+- **Model Compatibility**: Essential for models requiring specific dimension constraints
+- **Flexible Multiple Values**: Support from 1 to 256 with 16-step increments
+- **Preserves Quality**: Smart processing maintains image quality
+
+**Use Cases:**
+- Prepare images for VAE encoding (multiple of 8 requirement)
+- Ensure compatibility with specific model architectures
+- Standardize dimensions across image batches
+- Fix dimension errors in complex workflows
+- Optimize for tiled processing requirements
+
+![Image to Multiple Of Example](examples/workflows/image_to_multiple_of_example.png)

 ### 💾 Kiko Save Image Features

@@ -245,18 +328,55 @@ Generate Image → Kiko Save Image → Floating Popup Viewer
 **Features:** Click images to open in new tabs, download individual files, batch selection
 **Advantages:** Immediate preview without file explorer, multi-format comparison, advanced quality controls

+### Display Text Example
+
+```
+Gemini Prompt → Display Text → Copy to Clipboard
+📋 SDXL prompt ↘ auto-split  ↘ [📋 Positive] [📋 Negative]
+                view          → formatted display
+```
+
+**Input:** Text with "Positive prompt:" and "Negative prompt:" sections
+**Output:** Split view with individual copy buttons
+**Features:** Text wrapping, scrolling, responsive resizing
+**Smart Detection:** Automatically formats SDXL-style prompts
+
 ### Gemini Prompt Engineer Example
 ```
-Load Image → Gemini Prompt → Text Generation Model
-🖼️ reference ↘ type: FLUX   ↘ "majestic landscape..."
-               [API key]      → FLUX model
+Load Image → Gemini Prompt → Display Text → Text Generation Model
+🖼️ reference ↘ type: SDXL   ↘ split view  ↘ "detailed portrait..."
+               [Refresh Models]             → SDXL model
 ```

 **Input:** Reference image for style analysis
-**Prompt Type:** FLUX (detailed artistic prompts)
-**Output:** Optimized prompt with style, lighting, composition details
+**Prompt Type:** SDXL (positive/negative pairs with layered structure)
+**Model Selection:** Dynamic list with latest Gemini models (2.0, 2.5)
+**Output:** Optimized prompts following community best practices
 **API:** Requires Gemini API key (free tier available)
-**Use Case:** Recreate similar style/mood from reference images
+**Refresh:** Click button to fetch latest available models
+
+### Display Any Example
+```
+Any Node → Display Any → Debug Output
+🔍 tensor  ↘ mode: shape ↘ "[[1, 3, 512, 512]]"
+```
+
+**Input:** Any data type (image, latent, config, etc.)
+**Mode:** "raw value" or "tensor shape"
+**Output:** Formatted display of value or tensor dimensions
+**Use Case:** Debug workflows, inspect data structures
+
+### Image to Multiple Of Example
+```
+Load Image → Image to Multiple Of → VAE Encode → KSampler
+🖼️ 513×769  ↘ multiple: 64    ↘ 512×768     → latent
+              method: crop
+```
+
+**Input:** Image with arbitrary dimensions
+**Multiple Of:** 64 (common for VAE compatibility)
+**Method:** "center crop" or "rescale"
+**Output:** Adjusted image with compatible dimensions

 ### Common Workflows

@@ -300,6 +420,10 @@ Load Image → Gemini Prompt → Text Generation Model
 | **Sampler Combo** | Unified sampling configuration with smart recommendations | ✅ Complete | [Docs](examples/documentation/sampler_combo.md) |
 | **Empty Latent Batch** | Create empty latent batches with preset support | ✅ Complete | [Docs](examples/documentation/empty_latent_batch.md) |
 | **Kiko Save Image** | Enhanced image saving with popup viewer and multi-format support | ✅ Complete | [Docs](examples/documentation/kiko_save_image.md) |
+| **Display Text** | Advanced text display with smart prompt detection and split view | ✅ Complete | [Docs](examples/documentation/display_text.md) |
+| **Gemini Prompt Engineer** | AI-powered image analysis with dynamic model refresh | ✅ Complete | [Docs](examples/documentation/gemini_prompt.md) |
+| **Display Any** | Universal debugging tool for any data type or tensor shapes | ✅ Complete | [Docs](examples/documentation/display_any.md) |
+| **Image to Multiple Of** | Adjust image dimensions to multiples for model compatibility | ✅ Complete | [Docs](examples/documentation/image_to_multiple_of.md) |
 | **Batch Image Processor** | Process multiple images with consistent settings | 🚧 Planned | Coming Soon |
 | **Advanced Prompt Utilities** | Enhanced prompt manipulation and generation | 🚧 Planned | Coming Soon |

@@ -593,14 +717,15 @@ MIT License - see [LICENSE](LICENSE) file for details.

 ## 📈 Stats

- **Nodes**: 6 (Resolution Calculator, Width Height Selector, Seed History, Sampler Combo, Empty Latent Batch, Kiko Save Image)
+- **Nodes**: 10 (Resolution Calculator, Width Height Selector, Seed History, Sampler Combo, Empty Latent Batch, Kiko Save Image, Display Text, Gemini Prompt Engineer, Display Any, Image to Multiple Of)
 - **Format Support**: 3 (PNG, JPEG, WebP with advanced controls)
 - **Presets**: 26 curated resolution presets
- **Interactive Features**: 4 (Width/Height Swap Button, Seed History UI, Empty Latent Batch Swap Button, Kiko Save Image Popup Viewer)
+- **Interactive Features**: 6 (Width/Height Swap Button, Seed History UI, Empty Latent Batch Swap Button, Kiko Save Image Popup Viewer, Display Text Split View, Gemini Model Refresh)
+- **AI Integration**: Gemini API with 40+ model support
 - **Test Coverage**: 100% (200+ comprehensive tests)
 - **Python Version**: 3.8+
 - **ComfyUI Compatibility**: Latest
- **Dependencies**: Minimal (PyTorch, NumPy, Pillow)
+- **Dependencies**: Minimal (PyTorch, NumPy, Pillow, google-generativeai for Gemini)

 ---

@@ -0,0 +1,66 @@
+# Security Policy
+
+## Supported Versions
+
+ComfyUI-KikoTools is actively maintained. We provide security updates for the following versions:
+
+| Version | Supported          |
+| ------- | ------------------ |
+| 1.x.x   | :white_check_mark: |
+| < 1.0   | :x:                |
+
+## Reporting a Vulnerability
+
+We take the security of ComfyUI-KikoTools seriously. If you believe you have found a security vulnerability, please report it to us as described below.
+
+### How to Report
+
+Please report security vulnerabilities by [opening a new issue](https://github.com/ComfyAssets/ComfyUI-KikoTools/issues/new) with the following:
+
+- Use the title prefix `[SECURITY]`
+- Provide a clear description of the vulnerability
+- Include steps to reproduce the issue
+- Specify the version(s) affected
+- If possible, suggest a fix or mitigation
+
+### What to Expect
+
+- **Response Time**: We aim to acknowledge receipt within 48 hours
+- **Investigation**: We will investigate and validate the reported vulnerability
+- **Updates**: We will keep you informed about the progress
+- **Resolution**: Once verified, we will work on a fix and release it as soon as possible
+- **Credit**: We will acknowledge your contribution in the release notes (unless you prefer to remain anonymous)
+
+### Scope
+
+Security vulnerabilities in scope include:
+
+- Code execution vulnerabilities in node implementations
+- Path traversal or file system access issues
+- API key or credential exposure
+- Dependency vulnerabilities that affect the project
+- Any issue that could compromise user data or system security
+
+### Out of Scope
+
+The following are generally not considered security vulnerabilities:
+
+- Issues in ComfyUI core (report these to the ComfyUI project)
+- Performance issues
+- Bugs that don't have security implications
+- Feature requests
+
+## Security Best Practices
+
+When using ComfyUI-KikoTools:
+
+- Keep your installation up to date
+- Store API keys (like Gemini API keys) securely using environment variables
+- Review generated files before sharing them
+- Be cautious with custom prompts that might expose sensitive information
+
+## Contact
+
+For urgent security matters, you can also reach out to the maintainers directly through GitHub.
+
+Thank you for helping keep ComfyUI-KikoTools secure!
@@ -226,9 +226,11 @@ class HFHubLoraLoader:

        lora_path = hf_hub_download(
            repo_id=repo_id.strip(),
-            subfolder=None
-            if subfolder is None or subfolder.strip() == ""
-            else subfolder.strip(),
+            subfolder=(
+                None
+                if subfolder is None or subfolder.strip() == ""
+                else subfolder.strip()
+            ),
            filename=filename.strip(),
            cache_dir=find_or_create_cache(),
        )
@@ -281,9 +283,11 @@ class HFHubEmbeddingLoader:
    ):
        hf_hub_download(
            repo_id=repo_id.strip(),
-            subfolder=None
-            if subfolder is None or subfolder.strip() == ""
-            else subfolder.strip(),
+            subfolder=(
+                None
+                if subfolder is None or subfolder.strip() == ""
+                else subfolder.strip()
+            ),
            filename=filename.strip(),
            local_dir=get_folder_paths("embeddings")[0],
        )
@@ -0,0 +1,120 @@
+# Display Any
+
+The Display Any node is a debugging and inspection tool that can display any type of input value in ComfyUI. It's particularly useful for understanding data structures and tensor shapes during workflow development.
+
+## Features
+
+- **Universal Input**: Accepts any type of input data (tensors, strings, numbers, lists, dictionaries, etc.)
+- **Two Display Modes**:
+  - **Raw Value**: Shows the string representation of the input
+  - **Tensor Shape**: Extracts and displays the shapes of any tensors found in the input
+- **Nested Structure Support**: Can find tensors within nested dictionaries and lists
+- **UI Output**: Displays results directly in the ComfyUI interface
+
+## Inputs
+
+- **input** (*): Any value you want to display or inspect
+- **mode** (DROPDOWN): Display mode selection
+  - `raw value`: Shows the complete string representation of the input
+  - `tensor shape`: Extracts and shows shapes of any tensors in the input
+
+## Outputs
+
+- **display_text** (STRING): The formatted display text
+
+## Usage Examples
+
+### 1. Display Simple Values
+
+Connect any output to see its raw value:
+```
+String Input: "Hello, ComfyUI!"
+Mode: raw value
+Output: "Hello, ComfyUI!"
+```
+
+### 2. Inspect Tensor Shapes
+
+Great for debugging image processing pipelines:
+```
+Image Tensor: [1, 3, 512, 512]
+Mode: tensor shape
+Output: "[[1, 3, 512, 512]]"
+```
+
+### 3. Debug Complex Data Structures
+
+View nested data structures with multiple tensors:
+```python
+Input: {
+    "images": tensor([1, 3, 256, 256]),
+    "masks": [tensor([256, 256]), tensor([256, 256, 1])],
+    "config": {"steps": 20}
+}
+Mode: tensor shape
+Output: "[[1, 3, 256, 256], [256, 256], [256, 256, 1]]"
+```
+
+### 4. Workflow Debugging
+
+Use Display Any nodes at various points in your workflow to understand data flow:
+- After loading images to verify dimensions
+- Before/after processing nodes to track shape changes
+- To inspect conditioning or latent data structures
+- To view metadata or configuration dictionaries
+
+## Use Cases
+
+### Image Pipeline Debugging
+Place Display Any nodes after image loading and processing nodes to track dimension changes:
+```
+Load Image → Display Any (tensor shape) → Resize → Display Any (tensor shape)
+```
+
+### Latent Space Inspection
+Understand latent dimensions in your workflows:
+```
+VAE Encode → Display Any (tensor shape) → KSampler → Display Any (raw value)
+```
+
+### Configuration Verification
+Display complex configuration objects to ensure correct settings:
+```
+Config Node → Display Any (raw value) → Processing Node
+```
+
+## Tips
+
+1. **Multiple Display Nodes**: You can use multiple Display Any nodes in a single workflow to track data at different stages
+
+2. **Tensor Shape Mode**: Particularly useful when working with:
+   - Image batches to verify batch size
+   - Latent tensors to understand dimensions
+   - Mask arrays to check compatibility
+
+3. **Raw Value Mode**: Best for:
+   - String prompts and text
+   - Configuration dictionaries
+   - Debugging node outputs
+   - Understanding data structure
+
+4. **No Tensors Found**: If you see "No tensors found in input" in tensor shape mode, the input doesn't contain any tensor-like objects (numpy arrays, torch tensors, etc.)
+
+## Technical Notes
+
+- The node uses `str()` for raw value display, providing Python's string representation
+- Tensor shape detection works with any object that has a `shape` attribute
+- Nested structure traversal supports dictionaries, lists, and tuples
+- The output is both displayed in the UI and available as a string output for further processing
+
+## Example Workflow Integration
+
+```
+[Load Image] → [Image Processing] → [Display Any (tensor shape)]
+                                           ↓
+                                    "[[1, 3, 512, 512]]"
+                                           ↓
+[Text Multiline] ← [Concatenate] ← "Image dimensions: "
+```
+
+This creates a text output showing the current image dimensions that can be used elsewhere in your workflow.
@@ -0,0 +1,147 @@
+# Display Text
+
+The Display Text node provides advanced text display capabilities with smart formatting, interactive features, and responsive design for ComfyUI workflows.
+
+## Features
+
+- **Smart Prompt Detection**: Automatically detects and formats SDXL-style positive/negative prompt pairs
+- **Text Wrapping**: Proper word wrapping that reflows when node is resized
+- **Scrollable Content**: Mouse wheel scrolling for long texts with visual indicators
+- **Copy Functionality**: Always-visible copy button with visual feedback
+- **Split View Mode**: Side-by-side display for prompt pairs
+- **Responsive Design**: Content adapts to node resizing
+
+## Inputs
+
+- **text** (STRING): The text to display
+  - Can be a single text block
+  - Can contain "Positive prompt:" and "Negative prompt:" sections for automatic split view
+
+## Outputs
+
+- **text** (STRING): Pass-through of the input text
+
+## Display Modes
+
+### Single Text Mode
+
+When the input is regular text without prompt markers, it displays as a single scrollable text area with:
+- Word wrapping at word boundaries
+- Vertical scrolling for long content
+- Single copy button for the entire text
+
+### Split View Mode
+
+Automatically activated when text contains both "Positive prompt:" and "Negative prompt:" sections:
+- Side-by-side display with 50/50 split
+- Independent scrolling for each section
+- Separate copy buttons for each prompt
+- Labels are stripped when copying (clean prompts)
+
+## Usage Examples
+
+### 1. Display Generated Prompts
+
+```
+Gemini Prompt → Display Text → Copy to workflow
+```
+The node automatically detects SDXL format and shows positive/negative prompts side-by-side.
+
+### 2. Debug Text Processing
+
+```
+Text Processing → Display Text → Further Processing
+```
+View intermediate text processing results with proper formatting.
+
+### 3. Show Long Descriptions
+
+```
+Load Text → Display Text → Review
+```
+Display long text content with scrolling and word wrapping.
+
+## Interactive Features
+
+### Copy Button
+- Always visible in the top-right corner
+- Shows "✓ Copied!" feedback on click
+- In split view: separate buttons for each section
+- Strips prompt labels for clean copying
+
+### Scrolling
+- Mouse wheel scrolling when hovering over text
+- Visual indicators appear when content is scrollable
+- Smooth scrolling with proper boundaries
+- Independent scrolling in split view mode
+
+### Resizing
+- Text reflows when node width changes
+- Maintains readability at different sizes
+- Split view maintains 50/50 proportions
+- Minimum height ensures usability
+
+## Smart Prompt Detection
+
+The node intelligently detects prompt formats:
+
+1. **SDXL Format**: 
+   - Looks for "Positive prompt:" and "Negative prompt:" markers
+   - Case-insensitive detection
+   - Handles various formatting styles
+
+2. **Label Stripping**:
+   - When copying from split view, labels are removed
+   - "Positive prompt: beautiful sunset" → "beautiful sunset"
+   - Clean prompts ready for direct use
+
+## Styling
+
+- **Font**: Monospace for consistent alignment
+- **Colors**: 
+  - Text: Light gray (#ddd) on dark background
+  - Background: Semi-transparent dark (#1a1a1a)
+  - Borders: Subtle gray (#333)
+- **Spacing**: Comfortable padding and line height
+- **Visual Feedback**: Hover effects on interactive elements
+
+## Use Cases
+
+### Prompt Engineering Workflows
+- Display AI-generated prompts with proper formatting
+- Compare positive and negative prompts side-by-side
+- Copy refined prompts without manual cleanup
+
+### Text Processing Pipelines
+- Debug text transformations at each step
+- View formatted outputs from text nodes
+- Monitor prompt construction workflows
+
+### Documentation and Notes
+- Display workflow instructions
+- Show generation parameters
+- Present formatted metadata
+
+## Technical Details
+
+- **Text Processing**: Preserves original text while adding display formatting
+- **Responsive Design**: CSS-based layout adapts to node dimensions
+- **Event Handling**: Proper event propagation for ComfyUI compatibility
+- **Memory Efficient**: Only renders visible text portions
+
+## Tips
+
+1. **For Long Prompts**: The scrolling feature handles texts of any length efficiently
+2. **Quick Copy**: Use the copy buttons to quickly grab prompts for other nodes
+3. **Resizing**: Drag node edges to find optimal display width for your content
+4. **Split View**: Works best with SDXL-format prompts but handles any dual-section text
+
+## Integration Example
+
+```
+[Gemini Prompt Engineer] → [Display Text] → [Copy Button Click]
+         ↓                        ↓                    ↓
+   SDXL Format            Split View Display    Clean Prompts
+```
+
+This creates a seamless workflow from prompt generation to usage, with the Display Text node providing the visual interface for review and interaction.
@@ -0,0 +1,209 @@
+# Gemini Prompt Engineer
+
+The Gemini Prompt Engineer node uses Google's Gemini AI to analyze images and generate optimized prompts for various AI image generation models.
+
+## Features
+
+- **Multi-Model Support**: Generate prompts optimized for FLUX, SDXL, Danbooru, and Video generation
+- **Custom Prompts**: Override templates with your own system prompts
+- **Visual Feedback**: UI shows processing status and error states
+- **Flexible API Key Management**: Multiple ways to provide API credentials
+- **Dynamic Model Selection**: Fetch and use latest Gemini models with refresh button
+- **Model Caching**: Persistent storage of available models for offline access
+- **Help Integration**: Built-in setup guide accessible via help button
+
+## Setup
+
+### 1. Get API Key
+
+Get your free Gemini API key from [Google AI Studio](https://makersuite.google.com/app/apikey)
+
+### 2. Install Dependencies
+
+```bash
+pip install google-generativeai
+```
+
+### 3. Configure API Key
+
+Choose one of these methods:
+
+1. **Environment Variable** (Recommended):
+   ```bash
+   export GEMINI_API_KEY="your-api-key-here"
+   ```
+
+2. **Config File**:
+   Create `gemini_config.json` in your ComfyUI root directory:
+   ```json
+   {
+     "api_key": "your-api-key-here"
+   }
+   ```
+
+3. **Node Input**:
+   Enter the API key directly in the node's `api_key` field
+
+## Inputs
+
+- **image** (IMAGE): The image to analyze
+- **prompt_type** (DROPDOWN): Type of prompt to generate
+  - `flux`: Detailed artistic prompts with quality markers
+  - `sdxl`: Positive/negative prompt pairs with weight emphasis
+  - `danbooru`: Anime-style booru tags with underscores
+  - `video`: Motion and temporal descriptions for video generation
+- **model** (DROPDOWN): Gemini model selection
+  - Dynamically populated list of available models
+  - Includes latest models like gemini-2.0-flash-exp
+  - Click refresh button to update model list
+- **api_key** (STRING, optional): Gemini API key if not set elsewhere
+- **custom_prompt** (STRING, optional): Override template with custom system prompt
+
+## Outputs
+
+- **prompt** (STRING): Generated prompt text
+- **negative_prompt** (STRING): Negative prompt (only populated for SDXL format)
+
+## Prompt Type Details
+
+### FLUX Format
+Generates detailed prompts optimized for FLUX models:
+- Starts with main subject and action
+- Includes style and medium descriptors
+- Adds lighting and atmosphere details
+- Uses quality markers like "4K", "highly detailed", "award-winning"
+
+Example output:
+```
+majestic mountain landscape at golden hour, oil painting style, dramatic lighting with sun rays piercing through clouds, wide angle composition, warm color palette with orange and purple hues, highly detailed, 4K resolution, trending on ArtStation, photorealistic rendering
+```
+
+### SDXL Format
+Generates positive and negative prompt pairs with enhanced structure:
+- Layered positive prompts: main subject → style → composition → technical
+- Comprehensive negative prompts to avoid common issues
+- Uses parentheses for emphasis: `(detailed eyes:1.2)`
+- Includes quality boosters and technical specifications
+
+Example output:
+```
+Positive prompt:
+beautiful woman with flowing red hair, elegant pose, (detailed eyes:1.2), serene expression
+oil painting style, renaissance art influence, classical portraiture
+golden hour lighting, warm color palette, soft shadows, dramatic chiaroscuro
+centered composition, rule of thirds, shallow depth of field, bokeh background
+masterpiece, best quality, highly detailed, 8k uhd, professional artwork
+
+Negative prompt:
+low quality, worst quality, blurry, out of focus, pixelated, low resolution
+bad anatomy, deformed features, extra limbs, missing limbs, disconnected limbs
+poorly drawn face, poorly drawn hands, amateur drawing, bad proportions
+oversaturated, overexposed, underexposed, bad lighting, harsh shadows
+jpeg artifacts, watermark, signature, text, cropped, duplicate
+```
+
+### Danbooru Format
+Generates booru-style tags for anime artwork:
+- Uses underscores for multi-word concepts
+- Includes character count descriptors (1girl, 2boys)
+- Orders tags from most to least important
+
+Example output:
+```
+1girl, solo, long_hair, blue_eyes, blonde_hair, school_uniform, serafuku, pleated_skirt, thighhighs, smile, looking_at_viewer, classroom, sitting, desk, window, sunlight, highres, masterpiece
+```
+
+### Video Format
+Generates prompts for video generation models:
+- Describes motion and camera movements
+- Includes temporal markers and transitions
+- Specifies technical details like fps and duration
+
+Example output:
+```
+Aerial shot slowly descending toward a misty forest at dawn, camera smoothly transitions to tracking shot following a deer through the trees, photorealistic style, soft golden hour lighting with fog, 10 second duration, 4K resolution 24fps, ending with close-up of deer looking at camera
+```
+
+## Custom System Prompts
+
+You can override any template by providing your own system prompt. This is useful for:
+- Specialized use cases
+- Different language outputs
+- Custom formatting requirements
+- Integration with specific workflows
+
+Example custom prompt:
+```
+You are an expert at analyzing images and creating simple, concise descriptions.
+Focus only on the main subject and primary colors.
+Keep your response under 50 words.
+```
+
+## Error Handling
+
+The node provides clear error messages for common issues:
+- Missing API key
+- API request failures
+- Invalid image inputs
+- Rate limiting
+
+Errors are displayed in the prompt output for easy debugging.
+
+## Model Selection
+
+### Dynamic Model List
+- Click the refresh button (🔄) next to the model dropdown to fetch latest models
+- Models are fetched from Google's API and include all available versions
+- Common models include:
+  - `gemini-2.0-flash-exp`: Latest experimental flash model
+  - `gemini-1.5-pro`: Advanced model with larger context
+  - `gemini-1.5-flash`: Fast and efficient for most tasks
+
+### Model Caching
+- Available models are cached locally for offline access
+- Cache persists across ComfyUI sessions
+- Refresh button updates the cache with latest models
+
+## UI Features
+
+### Help Button
+- Click the help button (?) for quick setup instructions
+- Shows API key setup methods
+- Links to Google AI Studio for key generation
+
+### Status Indicators
+- Processing spinner during API calls
+- Error messages displayed in red
+- Success feedback when prompt is generated
+
+## Tips
+
+1. **API Usage**: Gemini has generous free tier limits, but be mindful of rate limits
+2. **Image Quality**: Higher resolution images provide better analysis results
+3. **Prompt Refinement**: You can chain multiple Gemini nodes with different custom prompts
+4. **Caching**: Results are not cached, so identical images will make new API calls
+5. **Model Selection**: Use flash models for faster responses, pro models for complex analysis
+
+## Example Workflow
+
+1. Load an image using Load Image node
+2. Connect to Gemini Prompt Engineer
+3. Select appropriate prompt_type for your target model
+4. Connect prompt output to your generation model
+5. For SDXL, connect both prompt and negative_prompt outputs
+
+## Troubleshooting
+
+**"API key not found" error**:
+- Check environment variable is set correctly
+- Verify config file path and JSON format
+- Try entering key directly in node
+
+**"No response generated" error**:
+- Check internet connection
+- Verify API key is valid
+- Image might be too large (resize if needed)
+
+**Import error for google-generativeai**:
+- Run `pip install google-generativeai` in your ComfyUI environment
+- Restart ComfyUI after installation
@@ -0,0 +1,213 @@
+# Kiko Save Image
+
+Enhanced image saving node with multiple format support, quality controls, and an interactive floating popup viewer for ComfyUI.
+
+## Features
+
+- **Multiple Format Support**: Save as PNG, JPEG, or WebP with format-specific optimizations
+- **Advanced Quality Controls**: Fine-tune compression settings per format
+- **Floating Popup Viewer**: Interactive window showing saved images immediately
+- **Batch Operations**: Multi-select images for bulk actions
+- **File Size Display**: Real-time feedback on compression effectiveness
+- **Smart UI**: Auto-hide, draggable, resizable popup window
+
+## Inputs
+
+- **images** (IMAGE): Batch of images to save
+- **filename_prefix** (STRING): Prefix for saved filenames
+  - Default: "KikoSave"
+  - Supports subfolder paths (e.g., "outputs/renders/final")
+- **format** (DROPDOWN): Output format selection
+  - `PNG`: Lossless compression, best quality
+  - `JPEG`: Lossy compression, smaller files
+  - `WEBP`: Modern format, best compression ratio
+- **quality** (INT): JPEG/WebP quality level
+  - Range: 1-100 (default: 90)
+  - Higher values = better quality, larger files
+- **png_compress_level** (INT): PNG compression level
+  - Range: 0-9 (default: 4)
+  - Higher values = smaller files, slower saving
+- **webp_lossless** (BOOLEAN): Use lossless WebP compression
+  - Default: False (lossy)
+  - True: Lossless compression like PNG
+- **popup** (BOOLEAN): Enable popup viewer window
+  - Default: True
+  - Toggle per save operation
+
+## Outputs
+
+- **UI**: Enhanced preview data with interactive popup viewer
+
+## Popup Viewer Features
+
+### Window Controls
+- **Drag Handle**: Click and drag the header to move window
+- **Minimize Button**: Collapse to title bar only
+- **Maximize Button**: Expand to larger viewing size
+- **Roll-up Button**: Show/hide content area
+- **Close Button**: Hide the popup (can reopen with toggle)
+
+### Image Grid
+- **Thumbnails**: Click any image to open full-size in new tab
+- **File Info**: Shows filename and size for each image
+- **Quality Indicators**: 
+  - PNG: Compression level (0-9)
+  - JPEG/WebP: Quality percentage
+- **Batch Selection**: Checkboxes for multi-select operations
+
+### Bulk Actions
+- **Open All Selected**: Opens selected images in new tabs
+- **Download All Selected**: Downloads selected images as a batch
+- **Individual Downloads**: Download button per image
+
+### Smart Behavior
+- **Auto-positioning**: Appears in convenient screen location
+- **Persistence**: Stays open across multiple saves
+- **Auto-hide**: Can be minimized when not needed
+- **Responsive**: Adapts to different image counts
+
+## Format Details
+
+### PNG Format
+- **Pros**: Lossless quality, transparency support, wide compatibility
+- **Cons**: Larger file sizes
+- **Best for**: Final outputs, images with transparency, archival
+- **Compression**: 0 (none) to 9 (maximum)
+  - Level 4 (default) balances size and speed
+  - Level 9 for maximum compression (slow)
+
+### JPEG Format
+- **Pros**: Smaller files, fast loading, universal support
+- **Cons**: Lossy compression, no transparency
+- **Best for**: Web images, previews, photos
+- **Quality**: 1-100%
+  - 90% (default) excellent quality with good compression
+  - 95%+ for near-lossless quality
+  - 70-85% for web optimization
+
+### WebP Format
+- **Pros**: Best compression ratios, supports transparency, modern
+- **Cons**: Limited software support
+- **Best for**: Web deployment, storage optimization
+- **Modes**:
+  - Lossy (default): Excellent compression with quality control
+  - Lossless: PNG-like quality with better compression
+
+## Usage Examples
+
+### High-Quality Archive
+```
+Format: PNG
+Compression: 0-2
+Use Case: Final renders for portfolio or client delivery
+```
+
+### Web Optimization
+```
+Format: JPEG or WebP
+Quality: 80-85
+Use Case: Website images, social media posts
+```
+
+### Balanced Storage
+```
+Format: WebP
+Quality: 90
+Lossless: False
+Use Case: Large batches with storage constraints
+```
+
+### Transparency Preservation
+```
+Format: PNG or WebP (lossless)
+Use Case: Logos, UI elements, cutout images
+```
+
+## Workflow Integration
+
+### Basic Save
+```
+Generate → Kiko Save Image
+           format: PNG
+           popup: enabled
+```
+
+### Format Comparison
+```
+Generate → Kiko Save Image (PNG)    → Compare file sizes
+        ↘ Kiko Save Image (JPEG)   ↗
+        ↘ Kiko Save Image (WebP)   ↗
+```
+
+### Batch Processing
+```
+Batch Generate → Kiko Save Image → Popup Viewer
+                 ↓                  ↓
+                4 images        Select best results
+```
+
+## Tips and Best Practices
+
+1. **Format Selection**:
+   - Use PNG for maximum quality and transparency
+   - Use JPEG for photographs without transparency
+   - Use WebP for modern web deployment
+
+2. **Quality Settings**:
+   - Start with defaults (90 for JPEG/WebP, 4 for PNG)
+   - Adjust based on file size requirements
+   - Preview results in popup before finalizing
+
+3. **Popup Management**:
+   - Drag to second monitor for larger workspace
+   - Use roll-up to save screen space
+   - Disable popup for automated workflows
+
+4. **Batch Operations**:
+   - Use checkboxes to select multiple images
+   - Open all in tabs for side-by-side comparison
+   - Download all for quick collection
+
+5. **File Organization**:
+   - Use subfolders in filename_prefix
+   - Include descriptive prefixes
+   - Let ComfyUI handle timestamp suffixes
+
+## Advantages Over Standard Save Image
+
+- **Immediate Preview**: No need to navigate file system
+- **Format Flexibility**: Choose optimal format per use case
+- **Quality Control**: Fine-tune compression settings
+- **Batch Management**: Handle multiple images efficiently
+- **Modern UI**: Floating interface doesn't interrupt workflow
+- **File Size Awareness**: See compression effectiveness immediately
+- **Quick Access**: One-click opening and downloading
+
+## Technical Details
+
+- **Image Processing**: Uses Pillow for format conversion
+- **Metadata**: Preserves ComfyUI metadata in saved files
+- **File Naming**: Automatic timestamp and counter suffixes
+- **Memory Efficiency**: Processes images individually
+- **Thread Safety**: Proper handling of concurrent saves
+
+## Troubleshooting
+
+**Popup not appearing**:
+- Check that popup input is enabled
+- Look for minimized window
+- Try toggling the popup button in node
+
+**WebP not working**:
+- Ensure Pillow has WebP support
+- Update Pillow: `pip install --upgrade pillow`
+
+**Large file sizes**:
+- Increase compression (PNG) or reduce quality (JPEG/WebP)
+- Consider switching formats
+- Check image dimensions
+
+**Can't see all images**:
+- Scroll within the popup grid
+- Maximize the popup window
+- Images are shown newest first
@@ -0,0 +1,379 @@
+{
+  "id": "display-any-example",
+  "revision": 0,
+  "last_node_id": 11,
+  "last_link_id": 9,
+  "nodes": [
+    {
+      "id": 1,
+      "type": "DisplayAny",
+      "pos": [
+        400,
+        270
+      ],
+      "size": [
+        210,
+        60
+      ],
+      "flags": {},
+      "order": 3,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "input",
+          "type": "*",
+          "link": 1
+        }
+      ],
+      "outputs": [
+        {
+          "name": "display_text",
+          "type": "STRING",
+          "links": [
+            8
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "kikotools",
+        "ver": "271cd020c1b2f78e7ee40c1f08e70191fed00012",
+        "Node name for S&R": "DisplayAny"
+      },
+      "widgets_values": [
+        "tensor shape"
+      ]
+    },
+    {
+      "id": 2,
+      "type": "LoadImage",
+      "pos": [
+        50,
+        270
+      ],
+      "size": [
+        315,
+        314
+      ],
+      "flags": {},
+      "order": 2,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            1,
+            5
+          ]
+        },
+        {
+          "name": "MASK",
+          "type": "MASK",
+          "links": null
+        }
+      ],
+      "properties": {
+        "cnr_id": "comfy-core",
+        "ver": "0.3.47",
+        "Node name for S&R": "LoadImage"
+      },
+      "widgets_values": [
+        "example.png",
+        "image"
+      ]
+    },
+    {
+      "id": 4,
+      "type": "DisplayAny",
+      "pos": [
+        400,
+        520
+      ],
+      "size": [
+        210,
+        70
+      ],
+      "flags": {},
+      "order": 6,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "input",
+          "type": "*",
+          "link": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "display_text",
+          "type": "STRING",
+          "links": [
+            9
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "kikotools",
+        "ver": "271cd020c1b2f78e7ee40c1f08e70191fed00012",
+        "Node name for S&R": "DisplayAny"
+      },
+      "widgets_values": [
+        "raw value"
+      ]
+    },
+    {
+      "id": 7,
+      "type": "VAELoader",
+      "pos": [
+        -250,
+        410
+      ],
+      "size": [
+        270,
+        58
+      ],
+      "flags": {},
+      "order": 0,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "VAE",
+          "type": "VAE",
+          "links": [
+            6
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "comfy-core",
+        "ver": "0.3.47",
+        "Node name for S&R": "VAELoader"
+      },
+      "widgets_values": [
+        "ae.safetensors"
+      ]
+    },
+    {
+      "id": 8,
+      "type": "VAEEncode",
+      "pos": [
+        430,
+        390
+      ],
+      "size": [
+        140,
+        46
+      ],
+      "flags": {},
+      "order": 4,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "pixels",
+          "type": "IMAGE",
+          "link": 5
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 6
+        }
+      ],
+      "outputs": [
+        {
+          "name": "LATENT",
+          "type": "LATENT",
+          "links": [
+            7
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "comfy-core",
+        "ver": "0.3.47",
+        "Node name for S&R": "VAEEncode"
+      },
+      "widgets_values": []
+    },
+    {
+      "id": 9,
+      "type": "DisplayText",
+      "pos": [
+        640,
+        270
+      ],
+      "size": [
+        450,
+        278
+      ],
+      "flags": {},
+      "order": 5,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "text",
+          "type": "STRING",
+          "link": 8
+        }
+      ],
+      "outputs": [
+        {
+          "name": "text",
+          "type": "STRING",
+          "links": null
+        }
+      ],
+      "properties": {
+        "cnr_id": "kikotools",
+        "ver": "271cd020c1b2f78e7ee40c1f08e70191fed00012",
+        "Node name for S&R": "DisplayText"
+      },
+      "widgets_values": [
+        null
+      ]
+    },
+    {
+      "id": 10,
+      "type": "DisplayText",
+      "pos": [
+        640,
+        610
+      ],
+      "size": [
+        590,
+        278
+      ],
+      "flags": {},
+      "order": 7,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "text",
+          "type": "STRING",
+          "link": 9
+        }
+      ],
+      "outputs": [
+        {
+          "name": "text",
+          "type": "STRING",
+          "links": null
+        }
+      ],
+      "properties": {
+        "cnr_id": "kikotools",
+        "ver": "271cd020c1b2f78e7ee40c1f08e70191fed00012",
+        "Node name for S&R": "DisplayText"
+      },
+      "widgets_values": [
+        null
+      ]
+    },
+    {
+      "id": 11,
+      "type": "MarkdownNote",
+      "pos": [
+        -320,
+        530
+      ],
+      "size": [
+        350,
+        270
+      ],
+      "flags": {},
+      "order": 1,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [],
+      "properties": {},
+      "widgets_values": [
+        "Display Any Example\n\nUniversal debugging tool:\n- Accepts ANY input type\n- Two modes: raw value or tensor shape\n- Finds tensors in nested structures\n\nUse cases:\n- Debug tensor dimensions\n- Inspect latent data\n- View config objects\n- Track data flow\n\nConnect anything to see its contents!"
+      ],
+      "color": "#432",
+      "bgcolor": "#653"
+    }
+  ],
+  "links": [
+    [
+      1,
+      2,
+      0,
+      1,
+      0,
+      "IMAGE"
+    ],
+    [
+      5,
+      2,
+      0,
+      8,
+      0,
+      "IMAGE"
+    ],
+    [
+      6,
+      7,
+      0,
+      8,
+      1,
+      "VAE"
+    ],
+    [
+      7,
+      8,
+      0,
+      4,
+      0,
+      "*"
+    ],
+    [
+      8,
+      1,
+      0,
+      9,
+      0,
+      "STRING"
+    ],
+    [
+      9,
+      4,
+      0,
+      10,
+      0,
+      "STRING"
+    ]
+  ],
+  "groups": [
+    {
+      "id": 1,
+      "title": "Display Any",
+      "bounding": [
+        -400,
+        130,
+        1740,
+        850
+      ],
+      "color": "#ffffff",
+      "font_size": 24,
+      "flags": {}
+    }
+  ],
+  "config": {},
+  "extra": {
+    "ds": {
+      "scale": 0.6115909044841477,
+      "offset": [
+        689.1392030323894,
+        -27.435530779258137
+      ]
+    },
+    "frontendVersion": "1.23.4",
+    "VHS_latentpreview": true,
+    "VHS_latentpreviewrate": 0,
+    "VHS_MetadataImage": true,
+    "VHS_KeepIntermediate": true
+  },
+  "version": 0.4
+}
@@ -0,0 +1,144 @@
+{
+  "id": "display-text-example",
+  "revision": 0,
+  "last_node_id": 6,
+  "last_link_id": 2,
+  "nodes": [
+    {
+      "id": 1,
+      "type": "DisplayText",
+      "pos": [
+        -160,
+        70
+      ],
+      "size": [
+        500,
+        400
+      ],
+      "flags": {},
+      "order": 2,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "text",
+          "type": "STRING",
+          "link": 2
+        }
+      ],
+      "outputs": [
+        {
+          "name": "text",
+          "type": "STRING",
+          "links": null
+        }
+      ],
+      "properties": {
+        "cnr_id": "kikotools",
+        "ver": "271cd020c1b2f78e7ee40c1f08e70191fed00012",
+        "Node name for S&R": "DisplayText"
+      },
+      "widgets_values": [
+        null
+      ]
+    },
+    {
+      "id": 4,
+      "type": "easy positive",
+      "pos": [
+        -620,
+        70
+      ],
+      "size": [
+        400,
+        200
+      ],
+      "flags": {},
+      "order": 0,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "positive",
+          "type": "STRING",
+          "links": [
+            2
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "comfyui-easy-use",
+        "ver": "1.3.1",
+        "Node name for S&R": "easy positive"
+      },
+      "widgets_values": [
+        "Positive prompt:\nbeautiful landscape, mountains in background, sunset lighting, golden hour, professional photography, high resolution, detailed textures, vibrant colors, masterpiece\n\nNegative prompt:\nlow quality, blurry, pixelated, bad composition, oversaturated, underexposed, amateur"
+      ],
+      "color": "#232",
+      "bgcolor": "#353"
+    },
+    {
+      "id": 6,
+      "type": "MarkdownNote",
+      "pos": [
+        -620,
+        330
+      ],
+      "size": [
+        360,
+        250
+      ],
+      "flags": {},
+      "order": 1,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [],
+      "properties": {},
+      "widgets_values": [
+        "Display Text Example\n\nSmart text display with:\n- Auto-detection of SDXL prompt format\n- Split view for positive/negative prompts\n- Text wrapping and scrolling\n- Copy buttons (strips labels)\n- Responsive resizing\n\nTry editing the text to see:\n1. Single text mode (no prompt markers)\n2. Split view mode (with Positive/Negative prompts)\n\nPerfect for displaying Gemini-generated prompts!"
+      ],
+      "color": "#432",
+      "bgcolor": "#653"
+    }
+  ],
+  "links": [
+    [
+      2,
+      4,
+      0,
+      1,
+      0,
+      "STRING"
+    ]
+  ],
+  "groups": [
+    {
+      "id": 1,
+      "title": "Display Text",
+      "bounding": [
+        -750,
+        -60,
+        1240,
+        700
+      ],
+      "color": "#ffffff",
+      "font_size": 24,
+      "flags": {}
+    }
+  ],
+  "config": {},
+  "extra": {
+    "ds": {
+      "scale": 0.90909090909091,
+      "offset": [
+        720,
+        30
+      ]
+    },
+    "frontendVersion": "1.23.4",
+    "VHS_latentpreview": true,
+    "VHS_latentpreviewrate": 0,
+    "VHS_MetadataImage": true,
+    "VHS_KeepIntermediate": true
+  },
+  "version": 0.4
+}
@@ -0,0 +1,301 @@
+{
+  "id": "empty-latent-batch-example",
+  "revision": 0,
+  "last_node_id": 9,
+  "last_link_id": 8,
+  "nodes": [
+    {
+      "id": 1,
+      "type": "EmptyLatentBatch",
+      "pos": [
+        350,
+        350
+      ],
+      "size": [
+        370,
+        210
+      ],
+      "flags": {},
+      "order": 0,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "latent",
+          "type": "LATENT",
+          "slot_index": 0,
+          "links": []
+        },
+        {
+          "name": "width",
+          "type": "INT",
+          "slot_index": 1,
+          "links": [
+            4
+          ]
+        },
+        {
+          "name": "height",
+          "type": "INT",
+          "slot_index": 2,
+          "links": [
+            5
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "kikotools",
+        "ver": "271cd020c1b2f78e7ee40c1f08e70191fed00012",
+        "Node name for S&R": "EmptyLatentBatch"
+      },
+      "widgets_values": [
+        "896×1152 - 7:9 (1.0MP) - SDXL",
+        896,
+        1152,
+        4
+      ]
+    },
+    {
+      "id": 2,
+      "type": "Note",
+      "pos": [
+        -50,
+        320
+      ],
+      "size": [
+        350,
+        250
+      ],
+      "flags": {},
+      "order": 1,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [],
+      "properties": {
+        "text": "Empty Latent Batch Example\n\nThis node creates empty latent tensors with:\n- 26 preset resolutions for SDXL/FLUX/Ultra-wide\n- Batch size support (1-64)\n- Interactive swap button\n- Memory usage estimation\n\nConnect to:\n- KSampler for image generation\n- Other latent processing nodes\n\nOutputs sanitized dimensions divisible by 8."
+      },
+      "widgets_values": [
+        "Empty Latent Batch Example\n\nThis node creates empty latent tensors with:\n- 26 preset resolutions for SDXL/FLUX/Ultra-wide\n- Batch size support (1-64)\n- Interactive swap button\n- Memory usage estimation\n\nConnect to:\n- KSampler for image generation\n- Other latent processing nodes\n\nOutputs sanitized dimensions divisible by 8."
+      ],
+      "color": "#432",
+      "bgcolor": "#653"
+    },
+    {
+      "id": 5,
+      "type": "DisplayAny",
+      "pos": [
+        760,
+        280
+      ],
+      "size": [
+        210,
+        60
+      ],
+      "flags": {},
+      "order": 2,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "input",
+          "type": "*",
+          "link": 4
+        }
+      ],
+      "outputs": [
+        {
+          "name": "display_text",
+          "type": "STRING",
+          "links": [
+            7
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "kikotools",
+        "ver": "271cd020c1b2f78e7ee40c1f08e70191fed00012",
+        "Node name for S&R": "DisplayAny"
+      },
+      "widgets_values": [
+        "raw value"
+      ]
+    },
+    {
+      "id": 6,
+      "type": "DisplayAny",
+      "pos": [
+        770,
+        500
+      ],
+      "size": [
+        210,
+        60
+      ],
+      "flags": {},
+      "order": 3,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "input",
+          "type": "*",
+          "link": 5
+        }
+      ],
+      "outputs": [
+        {
+          "name": "display_text",
+          "type": "STRING",
+          "links": [
+            8
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "kikotools",
+        "ver": "271cd020c1b2f78e7ee40c1f08e70191fed00012",
+        "Node name for S&R": "DisplayAny"
+      },
+      "widgets_values": [
+        "raw value"
+      ]
+    },
+    {
+      "id": 8,
+      "type": "DisplayText",
+      "pos": [
+        1000,
+        280
+      ],
+      "size": [
+        210,
+        138
+      ],
+      "flags": {},
+      "order": 4,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "text",
+          "type": "STRING",
+          "link": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "text",
+          "type": "STRING",
+          "links": null
+        }
+      ],
+      "properties": {
+        "cnr_id": "kikotools",
+        "ver": "271cd020c1b2f78e7ee40c1f08e70191fed00012",
+        "Node name for S&R": "DisplayText"
+      },
+      "widgets_values": [
+        null
+      ]
+    },
+    {
+      "id": 9,
+      "type": "DisplayText",
+      "pos": [
+        1010,
+        500
+      ],
+      "size": [
+        210,
+        138
+      ],
+      "flags": {},
+      "order": 5,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "text",
+          "type": "STRING",
+          "link": 8
+        }
+      ],
+      "outputs": [
+        {
+          "name": "text",
+          "type": "STRING",
+          "links": null
+        }
+      ],
+      "properties": {
+        "cnr_id": "kikotools",
+        "ver": "271cd020c1b2f78e7ee40c1f08e70191fed00012",
+        "Node name for S&R": "DisplayText"
+      },
+      "widgets_values": [
+        null
+      ]
+    }
+  ],
+  "links": [
+    [
+      4,
+      1,
+      1,
+      5,
+      0,
+      "*"
+    ],
+    [
+      5,
+      1,
+      2,
+      6,
+      0,
+      "*"
+    ],
+    [
+      7,
+      5,
+      0,
+      8,
+      0,
+      "STRING"
+    ],
+    [
+      8,
+      6,
+      0,
+      9,
+      0,
+      "STRING"
+    ]
+  ],
+  "groups": [
+    {
+      "id": 1,
+      "title": "Empty Latent",
+      "bounding": [
+        -110,
+        120,
+        1440,
+        620
+      ],
+      "color": "#ffffff",
+      "font_size": 24,
+      "flags": {}
+    }
+  ],
+  "config": {},
+  "extra": {
+    "ds": {
+      "scale": 0.8264462809917358,
+      "offset": [
+        156.41790912499965,
+        -2.272547312500285
+      ]
+    },
+    "frontendVersion": "1.23.4",
+    "VHS_latentpreview": true,
+    "VHS_latentpreviewrate": 0,
+    "VHS_MetadataImage": true,
+    "VHS_KeepIntermediate": true
+  },
+  "version": 0.4
+}
@@ -0,0 +1,207 @@
+{
+  "id": "gemini-prompt-example",
+  "revision": 0,
+  "last_node_id": 6,
+  "last_link_id": 4,
+  "nodes": [
+    {
+      "id": 2,
+      "type": "LoadImage",
+      "pos": [
+        300,
+        30
+      ],
+      "size": [
+        315,
+        314
+      ],
+      "flags": {},
+      "order": 1,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            3
+          ]
+        },
+        {
+          "name": "MASK",
+          "type": "MASK",
+          "links": null
+        }
+      ],
+      "properties": {
+        "cnr_id": "comfy-core",
+        "ver": "0.3.47",
+        "Node name for S&R": "LoadImage"
+      },
+      "widgets_values": [
+        "example.png",
+        "image"
+      ]
+    },
+    {
+      "id": 3,
+      "type": "DisplayText",
+      "pos": [
+        1070,
+        30
+      ],
+      "size": [
+        500,
+        400
+      ],
+      "flags": {},
+      "order": 3,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "text",
+          "type": "STRING",
+          "link": 4
+        }
+      ],
+      "outputs": [
+        {
+          "name": "text",
+          "type": "STRING",
+          "links": null
+        }
+      ],
+      "properties": {
+        "cnr_id": "kikotools",
+        "ver": "271cd020c1b2f78e7ee40c1f08e70191fed00012",
+        "Node name for S&R": "DisplayText"
+      },
+      "widgets_values": [
+        null
+      ]
+    },
+    {
+      "id": 5,
+      "type": "GeminiPrompt",
+      "pos": [
+        640,
+        30
+      ],
+      "size": [
+        400,
+        276
+      ],
+      "flags": {},
+      "order": 2,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 3
+        }
+      ],
+      "outputs": [
+        {
+          "name": "prompt",
+          "type": "STRING",
+          "links": [
+            4
+          ]
+        },
+        {
+          "name": "negative_prompt",
+          "type": "STRING",
+          "links": null
+        }
+      ],
+      "properties": {
+        "cnr_id": "kikotools",
+        "ver": "271cd020c1b2f78e7ee40c1f08e70191fed00012",
+        "Node name for S&R": "GeminiPrompt"
+      },
+      "widgets_values": [
+        "sdxl",
+        "gemini-2.0-flash",
+        "1234-1234-1234-1234",
+        "",
+        true,
+        null,
+        null,
+        null
+      ]
+    },
+    {
+      "id": 6,
+      "type": "MarkdownNote",
+      "pos": [
+        300,
+        410
+      ],
+      "size": [
+        400,
+        240
+      ],
+      "flags": {},
+      "order": 0,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [],
+      "properties": {},
+      "widgets_values": [
+        "Gemini Prompt Engineer Example\n\nAI-powered image analysis:\n- Analyzes image content and style\n- Generates optimized prompts for FLUX/SDXL/Danbooru/Video\n- Dynamic model selection with refresh button\n- Custom system prompt override\n\nSetup:\n1. Get free API key from Google AI Studio\n2. Set GEMINI_API_KEY env var or use config file\n3. Click refresh button to get latest models\n\nDisplayText automatically shows split view for SDXL prompts!"
+      ],
+      "color": "#432",
+      "bgcolor": "#653"
+    }
+  ],
+  "links": [
+    [
+      3,
+      2,
+      0,
+      5,
+      0,
+      "IMAGE"
+    ],
+    [
+      4,
+      5,
+      0,
+      3,
+      0,
+      "STRING"
+    ]
+  ],
+  "groups": [
+    {
+      "id": 1,
+      "title": "Gemini Prompt Engineer",
+      "bounding": [
+        210,
+        -110,
+        1460,
+        850
+      ],
+      "color": "#ffffff",
+      "font_size": 24,
+      "flags": {}
+    }
+  ],
+  "config": {},
+  "extra": {
+    "ds": {
+      "scale": 0.7513148009015777,
+      "offset": [
+        97.5582232217803,
+        133.12148846503663
+      ]
+    },
+    "frontendVersion": "1.23.4",
+    "VHS_latentpreview": true,
+    "VHS_latentpreviewrate": 0,
+    "VHS_MetadataImage": true,
+    "VHS_KeepIntermediate": true
+  },
+  "version": 0.4
+}
@@ -1,123 +1,552 @@
 {
-  "last_node_id": 4,
-  "last_link_id": 3,
+  "id": "3cd0ac86-8d11-41e5-9d8b-6621bc810ee6",
+  "revision": 0,
+  "last_node_id": 21,
+  "last_link_id": 21,
  "nodes": [
    {
      "id": 1,
      "type": "LoadImage",
-      "pos": [100, 200],
-      "size": [315, 314],
+      "pos": [
+        -80,
+        850
+      ],
+      "size": [
+        315,
+        314.0000305175781
+      ],
      "flags": {},
-      "order": 0,
+      "order": 1,
      "mode": 0,
+      "inputs": [],
      "outputs": [
        {
+          "label": "IMAGE",
          "name": "IMAGE",
          "type": "IMAGE",
-          "links": [1],
-          "shape": 3,
-          "label": "IMAGE"
+          "links": [
+            13
+          ]
        },
        {
          "name": "MASK",
          "type": "MASK",
-          "links": null,
-          "shape": 3
+          "links": null
        }
      ],
      "properties": {
+        "cnr_id": "comfy-core",
+        "ver": "0.3.47",
        "Node name for S&R": "LoadImage"
      },
-      "widgets_values": ["example.png", "image"]
+      "widgets_values": [
+        "example.png",
+        "image"
+      ]
    },
    {
-      "id": 2,
-      "type": "ImageToMultipleOf",
-      "pos": [500, 200],
-      "size": [315, 106],
+      "id": 8,
+      "type": "GetNode",
+      "pos": [
+        540,
+        840
+      ],
+      "size": [
+        210,
+        34
+      ],
+      "flags": {
+        "collapsed": true
+      },
+      "order": 0,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "UPSCALE_MODEL",
+          "type": "UPSCALE_MODEL",
+          "links": []
+        }
+      ],
+      "title": "Get_upscale_skin_model",
+      "properties": {
+        "widget_ue_connectable": {}
+      },
+      "widgets_values": [
+        "upscale_skin_model"
+      ]
+    },
+    {
+      "id": 9,
+      "type": "ImageUpscaleWithModel",
+      "pos": [
+        530,
+        810
+      ],
+      "size": [
+        221.98202514648438,
+        60
+      ],
      "flags": {},
-      "order": 1,
+      "order": 5,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "upscale_model",
+          "type": "UPSCALE_MODEL",
+          "link": 16
+        },
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 5
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            10,
+            21
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "comfy-core",
+        "ver": "0.3.28",
+        "Node name for S&R": "ImageUpscaleWithModel",
+        "widget_ue_connectable": {}
+      },
+      "widgets_values": []
+    },
+    {
+      "id": 10,
+      "type": "ImageToMultipleOf",
+      "pos": [
+        1000,
+        810
+      ],
+      "size": [
+        230,
+        82
+      ],
+      "flags": {},
+      "order": 9,
      "mode": 0,
      "inputs": [
        {
          "name": "image",
          "type": "IMAGE",
-          "link": 1
+          "link": 6
        }
      ],
      "outputs": [
        {
          "name": "image",
          "type": "IMAGE",
-          "links": [2, 3],
-          "shape": 3,
-          "label": "image"
+          "links": [
+            18
+          ]
        }
      ],
      "properties": {
-        "Node name for S&R": "ImageToMultipleOf"
+        "cnr_id": "comfyui-glifnodes",
+        "ver": "1.0.0",
+        "Node name for S&R": "ImageToMultipleOf",
+        "widget_ue_connectable": {}
      },
-      "widgets_values": [64, "center crop"]
+      "widgets_values": [
+        65,
+        "center crop"
+      ]
    },
    {
-      "id": 3,
-      "type": "PreviewImage",
-      "pos": [900, 100],
-      "size": [210, 246],
+      "id": 13,
+      "type": "ImageScaleBy",
+      "pos": [
+        760,
+        810
+      ],
+      "size": [
+        220,
+        82
+      ],
+      "flags": {},
+      "order": 7,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 10
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            6,
+            19
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "comfy-core",
+        "ver": "0.3.28",
+        "Node name for S&R": "ImageScaleBy",
+        "widget_ue_connectable": {}
+      },
+      "widgets_values": [
+        "lanczos",
+        0.5000000000000001
+      ]
+    },
+    {
+      "id": 14,
+      "type": "ImageUpscaleWithModel",
+      "pos": [
+        280,
+        830
+      ],
+      "size": [
+        221.98202514648438,
+        60
+      ],
+      "flags": {},
+      "order": 4,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "upscale_model",
+          "type": "UPSCALE_MODEL",
+          "link": 15
+        },
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 13
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            5,
+            20
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "comfy-core",
+        "ver": "0.3.28",
+        "Node name for S&R": "ImageUpscaleWithModel",
+        "widget_ue_connectable": {}
+      },
+      "widgets_values": []
+    },
+    {
+      "id": 15,
+      "type": "UpscaleModelLoader",
+      "pos": [
+        -90,
+        720
+      ],
+      "size": [
+        320,
+        60
+      ],
      "flags": {},
      "order": 2,
      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "UPSCALE_MODEL",
+          "type": "UPSCALE_MODEL",
+          "links": [
+            15
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "comfy-core",
+        "ver": "0.3.28",
+        "Node name for S&R": "UpscaleModelLoader",
+        "widget_ue_connectable": {}
+      },
+      "widgets_values": [
+        "4x-ClearRealityV1.pth"
+      ],
+      "color": "#232",
+      "bgcolor": "#353"
+    },
+    {
+      "id": 16,
+      "type": "UpscaleModelLoader",
+      "pos": [
+        140,
+        610
+      ],
+      "size": [
+        320,
+        60
+      ],
+      "flags": {},
+      "order": 3,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "UPSCALE_MODEL",
+          "type": "UPSCALE_MODEL",
+          "links": [
+            16
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "comfy-core",
+        "ver": "0.3.28",
+        "Node name for S&R": "UpscaleModelLoader",
+        "widget_ue_connectable": {}
+      },
+      "widgets_values": [
+        "1xSkinContrast-High-SuperUltraCompact.pth"
+      ],
+      "color": "#232",
+      "bgcolor": "#353"
+    },
+    {
+      "id": 18,
+      "type": "PreviewImage",
+      "pos": [
+        1260,
+        810
+      ],
+      "size": [
+        270,
+        280
+      ],
+      "flags": {},
+      "order": 11,
+      "mode": 0,
      "inputs": [
        {
          "name": "images",
          "type": "IMAGE",
-          "link": 2
+          "link": 18
        }
      ],
+      "outputs": [],
      "properties": {
+        "cnr_id": "comfy-core",
+        "ver": "0.3.47",
        "Node name for S&R": "PreviewImage"
-      }
+      },
+      "widgets_values": []
    },
    {
-      "id": 4,
-      "type": "VAEEncode",
-      "pos": [900, 400],
-      "size": [210, 46],
+      "id": 19,
+      "type": "PreviewImage",
+      "pos": [
+        1010,
+        940
+      ],
+      "size": [
+        210,
+        258
+      ],
      "flags": {},
-      "order": 3,
+      "order": 10,
      "mode": 0,
      "inputs": [
        {
-          "name": "pixels",
+          "name": "images",
          "type": "IMAGE",
-          "link": 3
-        },
-        {
-          "name": "vae",
-          "type": "VAE",
-          "link": null
-        }
-      ],
-      "outputs": [
-        {
-          "name": "LATENT",
-          "type": "LATENT",
-          "links": null,
-          "shape": 3
+          "link": 19
        }
      ],
+      "outputs": [],
      "properties": {
-        "Node name for S&R": "VAEEncode"
-      }
+        "cnr_id": "comfy-core",
+        "ver": "0.3.47",
+        "Node name for S&R": "PreviewImage"
+      },
+      "widgets_values": []
+    },
+    {
+      "id": 20,
+      "type": "PreviewImage",
+      "pos": [
+        520,
+        940
+      ],
+      "size": [
+        210,
+        258
+      ],
+      "flags": {},
+      "order": 6,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 20
+        }
+      ],
+      "outputs": [],
+      "properties": {
+        "cnr_id": "comfy-core",
+        "ver": "0.3.47",
+        "Node name for S&R": "PreviewImage"
+      },
+      "widgets_values": []
+    },
+    {
+      "id": 21,
+      "type": "PreviewImage",
+      "pos": [
+        750,
+        940
+      ],
+      "size": [
+        210,
+        258
+      ],
+      "flags": {},
+      "order": 8,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 21
+        }
+      ],
+      "outputs": [],
+      "properties": {
+        "cnr_id": "comfy-core",
+        "ver": "0.3.47",
+        "Node name for S&R": "PreviewImage"
+      },
+      "widgets_values": []
    }
  ],
  "links": [
-    [1, 1, 0, 2, 0, "IMAGE"],
-    [2, 2, 0, 3, 0, "IMAGE"],
-    [3, 2, 0, 4, 0, "IMAGE"]
+    [
+      5,
+      14,
+      0,
+      9,
+      1,
+      "IMAGE"
+    ],
+    [
+      6,
+      13,
+      0,
+      10,
+      0,
+      "IMAGE"
+    ],
+    [
+      10,
+      9,
+      0,
+      13,
+      0,
+      "IMAGE"
+    ],
+    [
+      13,
+      1,
+      0,
+      14,
+      1,
+      "IMAGE"
+    ],
+    [
+      15,
+      15,
+      0,
+      14,
+      0,
+      "UPSCALE_MODEL"
+    ],
+    [
+      16,
+      16,
+      0,
+      9,
+      0,
+      "UPSCALE_MODEL"
+    ],
+    [
+      18,
+      10,
+      0,
+      18,
+      0,
+      "IMAGE"
+    ],
+    [
+      19,
+      13,
+      0,
+      19,
+      0,
+      "IMAGE"
+    ],
+    [
+      20,
+      14,
+      0,
+      20,
+      0,
+      "IMAGE"
+    ],
+    [
+      21,
+      9,
+      0,
+      21,
+      0,
+      "IMAGE"
+    ]
+  ],
+  "groups": [
+    {
+      "id": 1,
+      "title": "Image to Multiple of",
+      "bounding": [
+        -180,
+        420,
+        1800,
+        830
+      ],
+      "color": "#ffffff",
+      "font_size": 24,
+      "flags": {}
+    }
  ],
-  "groups": [],
  "config": {},
-  "extra": {},
+  "extra": {
+    "ds": {
+      "scale": 0.6655312045216585,
+      "offset": [
+        292.51725658775155,
+        -375.0766486499791
+      ]
+    },
+    "frontendVersion": "1.23.4",
+    "VHS_latentpreview": true,
+    "VHS_latentpreviewrate": 0,
+    "VHS_MetadataImage": true,
+    "VHS_KeepIntermediate": true
+  },
  "version": 0.4
 }
@@ -0,0 +1,147 @@
+{
+  "id": "kiko-save-image-example",
+  "revision": 0,
+  "last_node_id": 4,
+  "last_link_id": 1,
+  "nodes": [
+    {
+      "id": 1,
+      "type": "KikoSaveImage",
+      "pos": [
+        390,
+        80
+      ],
+      "size": [
+        400,
+        390
+      ],
+      "flags": {},
+      "order": 2,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 1
+        }
+      ],
+      "outputs": [],
+      "properties": {
+        "cnr_id": "kikotools",
+        "ver": "271cd020c1b2f78e7ee40c1f08e70191fed00012",
+        "Node name for S&R": "KikoSaveImage"
+      },
+      "widgets_values": [
+        "KikoSave",
+        "PNG",
+        90,
+        4,
+        false,
+        true
+      ]
+    },
+    {
+      "id": 2,
+      "type": "LoadImage",
+      "pos": [
+        -10,
+        80
+      ],
+      "size": [
+        315,
+        314
+      ],
+      "flags": {},
+      "order": 1,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            1
+          ]
+        },
+        {
+          "name": "MASK",
+          "type": "MASK",
+          "links": null
+        }
+      ],
+      "properties": {
+        "cnr_id": "comfy-core",
+        "ver": "0.3.47",
+        "Node name for S&R": "LoadImage"
+      },
+      "widgets_values": [
+        "example.png",
+        "image"
+      ]
+    },
+    {
+      "id": 4,
+      "type": "MarkdownNote",
+      "pos": [
+        -10,
+        460
+      ],
+      "size": [
+        370,
+        270
+      ],
+      "flags": {},
+      "order": 0,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [],
+      "properties": {},
+      "widgets_values": [
+        "Kiko Save Image Example\n\nEnhanced image saving with:\n- Format selection: PNG, JPEG, WebP\n- Quality controls per format\n- Floating popup viewer (draggable)\n- Batch operations support\n- File size display\n\nPopup Features:\n- Click images to open in new tab\n- Download individual or selected images\n- Minimize/maximize/roll-up controls\n- Persistent across saves\n\nTry different formats to compare file sizes!"
+      ],
+      "color": "#432",
+      "bgcolor": "#653"
+    }
+  ],
+  "links": [
+    [
+      1,
+      2,
+      0,
+      1,
+      0,
+      "IMAGE"
+    ]
+  ],
+  "groups": [
+    {
+      "id": 1,
+      "title": "Kiko save Image",
+      "bounding": [
+        -110,
+        -60,
+        1020,
+        870
+      ],
+      "color": "#ffffff",
+      "font_size": 24,
+      "flags": {}
+    }
+  ],
+  "config": {},
+  "extra": {
+    "ds": {
+      "scale": 0.7513148009015777,
+      "offset": [
+        648.1018911400128,
+        110.02838653698085
+      ]
+    },
+    "frontendVersion": "1.23.4",
+    "VHS_latentpreview": true,
+    "VHS_latentpreviewrate": 0,
+    "VHS_MetadataImage": true,
+    "VHS_KeepIntermediate": true
+  },
+  "version": 0.4
+}
@@ -1,15 +1,15 @@
 {
  "id": "41469b2d-d616-479d-879a-95cdc6074a37",
  "revision": 0,
-  "last_node_id": 6,
-  "last_link_id": 5,
+  "last_node_id": 11,
+  "last_link_id": 9,
  "nodes": [
    {
      "id": 1,
      "type": "ResolutionCalculator",
      "pos": [
-        60,
-        430
+        -30,
+        210
      ],
      "size": [
        315,
@@ -38,8 +38,7 @@
          "type": "INT",
          "slot_index": 0,
          "links": [
-            1,
-            3
+            6
          ]
        },
        {
@@ -47,15 +46,15 @@
          "type": "INT",
          "slot_index": 1,
          "links": [
-            2,
-            4
+            7
          ]
        }
      ],
      "properties": {
-        "aux_id": "ComfyAssets/ComfyUI-KikoTools",
+        "cnr_id": "kikotools",
        "ver": "965ad60c74d7f25b1acce890d9c06518e46e6d0b",
        "Node name for S&R": "ResolutionCalculator",
+        "aux_id": "ComfyAssets/ComfyUI-KikoTools",
        "widget_ue_connectable": {}
      },
      "widgets_values": [
@@ -66,8 +65,8 @@
      "id": 6,
      "type": "LoadImage",
      "pos": [
-        -250,
-        430
+        -340,
+        210
      ],
      "size": [
        274.080078125,
@@ -94,8 +93,8 @@
      "properties": {
        "cnr_id": "comfy-core",
        "ver": "0.3.40",
-        "widget_ue_connectable": {},
-        "Node name for S&R": "LoadImage"
+        "Node name for S&R": "LoadImage",
+        "widget_ue_connectable": {}
      },
      "widgets_values": [
        "image-2025-06-13-105737.jpg",
@@ -103,80 +102,14 @@
      ]
    },
    {
-      "id": 4,
-      "type": "Display Int (rgthree)",
+      "id": 7,
+      "type": "MarkdownNote",
      "pos": [
-        420,
-        360
+        -350,
+        610
      ],
      "size": [
-        210,
-        88
-      ],
-      "flags": {},
-      "order": 3,
-      "mode": 0,
-      "inputs": [
-        {
-          "dir": 3,
-          "name": "input",
-          "type": "INT",
-          "link": 3
-        }
-      ],
-      "outputs": [],
-      "properties": {
-        "cnr_id": "rgthree-comfy",
-        "ver": "1.0.2506081210",
-        "Node name for S&R": "Display Int (rgthree)",
-        "widget_ue_connectable": {}
-      },
-      "widgets_values": [
-        ""
-      ]
-    },
-    {
-      "id": 5,
-      "type": "Display Int (rgthree)",
-      "pos": [
-        430,
-        530
-      ],
-      "size": [
-        210,
-        88
-      ],
-      "flags": {},
-      "order": 4,
-      "mode": 0,
-      "inputs": [
-        {
-          "dir": 3,
-          "name": "input",
-          "type": "INT",
-          "link": 4
-        }
-      ],
-      "outputs": [],
-      "properties": {
-        "cnr_id": "rgthree-comfy",
-        "ver": "1.0.2506081210",
-        "widget_ue_connectable": {},
-        "Node name for S&R": "Display Int (rgthree)"
-      },
-      "widgets_values": [
-        ""
-      ]
-    },
-    {
-      "id": 2,
-      "type": "Note",
-      "pos": [
-        -150,
-        170
-      ],
-      "size": [
-        400,
+        410,
        200
      ],
      "flags": {},
@@ -184,50 +117,167 @@
      "mode": 0,
      "inputs": [],
      "outputs": [],
-      "properties": {
-        "text": "Resolution Calculator Example\n\nThis node calculates upscaled dimensions from:\n- IMAGE tensors (connect from image loaders)\n- LATENT tensors (connect from VAE encode/generation)\n\nUse cases:\n- Calculate target dimensions for upscalers\n- Plan memory usage for large generations\n- Ensure dimensions are divisible by 8\n\nScale factors optimized for SDXL and FLUX models.",
-        "widget_ue_connectable": {}
-      },
+      "properties": {},
      "widgets_values": [
        "Resolution Calculator Example\n\nThis node calculates upscaled dimensions from:\n- IMAGE tensors (connect from image loaders)\n- LATENT tensors (connect from VAE encode/generation)\n\nUse cases:\n- Calculate target dimensions for upscalers\n- Plan memory usage for large generations\n- Ensure dimensions are divisible by 8\n\nScale factors optimized for SDXL and FLUX models."
      ],
      "color": "#432",
      "bgcolor": "#653"
+    },
+    {
+      "id": 8,
+      "type": "DisplayAny",
+      "pos": [
+        330,
+        160
+      ],
+      "size": [
+        270,
+        58
+      ],
+      "flags": {},
+      "order": 3,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "input",
+          "type": "*",
+          "link": 6
+        }
+      ],
+      "outputs": [
+        {
+          "name": "display_text",
+          "type": "STRING",
+          "links": [
+            8
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "kikotools",
+        "ver": "271cd020c1b2f78e7ee40c1f08e70191fed00012",
+        "Node name for S&R": "DisplayAny"
+      },
+      "widgets_values": [
+        "raw value"
+      ]
+    },
+    {
+      "id": 9,
+      "type": "DisplayAny",
+      "pos": [
+        330,
+        310
+      ],
+      "size": [
+        270,
+        58
+      ],
+      "flags": {},
+      "order": 4,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "input",
+          "type": "*",
+          "link": 7
+        }
+      ],
+      "outputs": [
+        {
+          "name": "display_text",
+          "type": "STRING",
+          "links": [
+            9
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "kikotools",
+        "ver": "271cd020c1b2f78e7ee40c1f08e70191fed00012",
+        "Node name for S&R": "DisplayAny"
+      },
+      "widgets_values": [
+        "raw value"
+      ]
+    },
+    {
+      "id": 10,
+      "type": "DisplayText",
+      "pos": [
+        670,
+        160
+      ],
+      "size": [
+        210,
+        138
+      ],
+      "flags": {},
+      "order": 5,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "text",
+          "type": "STRING",
+          "link": 8
+        }
+      ],
+      "outputs": [
+        {
+          "name": "text",
+          "type": "STRING",
+          "links": null
+        }
+      ],
+      "properties": {
+        "cnr_id": "kikotools",
+        "ver": "271cd020c1b2f78e7ee40c1f08e70191fed00012",
+        "Node name for S&R": "DisplayText"
+      },
+      "widgets_values": [
+        null
+      ]
+    },
+    {
+      "id": 11,
+      "type": "DisplayText",
+      "pos": [
+        660,
+        400
+      ],
+      "size": [
+        210,
+        138
+      ],
+      "flags": {},
+      "order": 6,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "text",
+          "type": "STRING",
+          "link": 9
+        }
+      ],
+      "outputs": [
+        {
+          "name": "text",
+          "type": "STRING",
+          "links": null
+        }
+      ],
+      "properties": {
+        "cnr_id": "kikotools",
+        "ver": "271cd020c1b2f78e7ee40c1f08e70191fed00012",
+        "Node name for S&R": "DisplayText"
+      },
+      "widgets_values": [
+        null
+      ]
    }
  ],
  "links": [
-    [
-      1,
-      1,
-      0,
-      3,
-      0,
-      "INT"
-    ],
-    [
-      2,
-      1,
-      1,
-      3,
-      1,
-      "INT"
-    ],
-    [
-      3,
-      1,
-      0,
-      4,
-      0,
-      "INT"
-    ],
-    [
-      4,
-      1,
-      1,
-      5,
-      0,
-      "INT"
-    ],
    [
      5,
      6,
@@ -235,25 +285,71 @@
      1,
      0,
      "IMAGE"
+    ],
+    [
+      6,
+      1,
+      0,
+      8,
+      0,
+      "*"
+    ],
+    [
+      7,
+      1,
+      1,
+      9,
+      0,
+      "*"
+    ],
+    [
+      8,
+      8,
+      0,
+      10,
+      0,
+      "STRING"
+    ],
+    [
+      9,
+      9,
+      0,
+      11,
+      0,
+      "STRING"
    ]
  ],
-  "groups": [],
+  "groups": [
+    {
+      "id": 1,
+      "title": "Resolution Calculator",
+      "bounding": [
+        -480,
+        20,
+        1480,
+        880
+      ],
+      "color": "#ffffff",
+      "font_size": 24,
+      "flags": {}
+    }
+  ],
  "config": {},
  "extra": {
    "ue_links": [],
    "ds": {
-      "scale": 0.7972024500000015,
+      "scale": 0.45000000000000145,
      "offset": [
-        709.6391289161842,
-        -90.0127389290854
+        1248.1498802376432,
+        256.0155843113725
      ]
    },
    "links_added_by_ue": [],
-    "frontendVersion": "1.21.7",
+    "frontendVersion": "1.23.4",
    "VHS_latentpreview": true,
    "VHS_latentpreviewrate": 0,
    "VHS_MetadataImage": true,
    "VHS_KeepIntermediate": true
  },
  "version": 0.4
-}
+}
@@ -10,6 +10,9 @@ from .tools.sampler_combo import SamplerComboNode, SamplerComboCompactNode
 from .tools.empty_latent_batch import EmptyLatentBatchNode
 from .tools.kiko_save_image import KikoSaveImageNode
 from .tools.image_to_multiple_of import ImageToMultipleOfNode
+from .tools.gemini_prompt import GeminiPromptNode
+from .tools.display_any import DisplayAnyNode
+from .tools.display_text import DisplayTextNode

 # ComfyUI node registration mappings
 NODE_CLASS_MAPPINGS = {
@@ -21,6 +24,9 @@ NODE_CLASS_MAPPINGS = {
    "EmptyLatentBatch": EmptyLatentBatchNode,
    "KikoSaveImage": KikoSaveImageNode,
    "ImageToMultipleOf": ImageToMultipleOfNode,
+    "GeminiPrompt": GeminiPromptNode,
+    "DisplayAny": DisplayAnyNode,
+    "DisplayText": DisplayTextNode,
 }

 NODE_DISPLAY_NAME_MAPPINGS = {
@@ -32,6 +38,9 @@ NODE_DISPLAY_NAME_MAPPINGS = {
    "EmptyLatentBatch": "Empty Latent Batch",
    "KikoSaveImage": "Kiko Save Image",
    "ImageToMultipleOf": "Image to Multiple of",
+    "GeminiPrompt": "Gemini Prompt Engineer",
+    "DisplayAny": "Display Any",
+    "DisplayText": "Display Text",
 }

 __all__ = ["NODE_CLASS_MAPPINGS", "NODE_DISPLAY_NAME_MAPPINGS"]
@@ -35,7 +35,9 @@ class ComfyAssetsBaseNode:
        """
        pass

-    def handle_error(self, error_msg: str, exception: Optional[Exception] = None) -> None:
+    def handle_error(
+        self, error_msg: str, exception: Optional[Exception] = None
+    ) -> None:
        """
        Standardized error handling with logging

@@ -0,0 +1,5 @@
+"""DisplayAny tool for ComfyUI."""
+
+from .node import DisplayAnyNode
+
+__all__ = ["DisplayAnyNode"]
@@ -0,0 +1,64 @@
+"""Logic for DisplayAny node - displays any input value or tensor shape."""
+
+from typing import Any, List, Union
+
+
+def get_tensor_shapes(input_value: Any) -> List[List[int]]:
+    """Extract tensor shapes from nested structures.
+
+    Args:
+        input_value: Any input value that may contain tensors
+
+    Returns:
+        List of tensor shapes found in the input
+    """
+    shapes = []
+
+    def extract_shapes(value: Any) -> None:
+        """Recursively extract shapes from nested structures."""
+        if isinstance(value, dict):
+            for v in value.values():
+                extract_shapes(v)
+        elif isinstance(value, (list, tuple)):
+            for item in value:
+                extract_shapes(item)
+        elif hasattr(value, "shape"):
+            # Handle tensors (numpy arrays, torch tensors, etc.)
+            shapes.append(list(value.shape))
+
+    extract_shapes(input_value)
+    return shapes
+
+
+def format_display_value(input_value: Any, mode: str = "raw value") -> str:
+    """Format input value for display based on selected mode.
+
+    Args:
+        input_value: Any input value to display
+        mode: Display mode - "raw value" or "tensor shape"
+
+    Returns:
+        Formatted string representation of the input
+    """
+    if mode == "tensor shape":
+        shapes = get_tensor_shapes(input_value)
+        if shapes:
+            return str(shapes)
+        else:
+            return "No tensors found in input"
+
+    # Default to raw value display
+    return str(input_value)
+
+
+def validate_display_mode(mode: str) -> bool:
+    """Validate if the display mode is supported.
+
+    Args:
+        mode: Display mode to validate
+
+    Returns:
+        True if mode is valid, False otherwise
+    """
+    valid_modes = ["raw value", "tensor shape"]
+    return mode in valid_modes
@@ -0,0 +1,66 @@
+"""DisplayAny node for ComfyUI - displays any input value or tensor information."""
+
+from typing import Any, Dict, Tuple
+
+from ...base import ComfyAssetsBaseNode
+from .logic import format_display_value, validate_display_mode
+
+
+# Define AnyType for wildcard input matching
+class AnyType(str):
+    """A special type that matches any input type in ComfyUI."""
+
+    def __ne__(self, other):
+        return False
+
+
+class DisplayAnyNode(ComfyAssetsBaseNode):
+    """Display any input value or tensor shape information.
+
+    This node can display any type of input in two modes:
+    - Raw value: Shows the string representation of the input
+    - Tensor shape: Extracts and displays shapes of any tensors in the input
+    """
+
+    @classmethod
+    def INPUT_TYPES(cls) -> Dict[str, Any]:
+        """Define input types for the node."""
+        return {
+            "required": {
+                "input": (AnyType("*"), {}),  # Accept any type of input
+                "mode": (["raw value", "tensor shape"],),
+            },
+        }
+
+    @classmethod
+    def VALIDATE_INPUTS(cls, **kwargs) -> bool:
+        """Validate inputs - always returns True as we accept any input."""
+        return True
+
+    RETURN_TYPES = ("STRING",)
+    RETURN_NAMES = ("display_text",)
+    FUNCTION = "display"
+    OUTPUT_NODE = True  # This node displays output in the UI
+
+    def display(self, input: Any, mode: str = "raw value") -> Dict[str, Any]:
+        """Display the input value according to the selected mode.
+
+        Args:
+            input: Any input value to display
+            mode: Display mode - "raw value" or "tensor shape"
+
+        Returns:
+            Dictionary with UI display and result
+        """
+        # Validate mode
+        if not validate_display_mode(mode):
+            mode = "raw value"  # Default to raw value if invalid
+
+        # Format the display text
+        display_text = format_display_value(input, mode)
+
+        # Return both UI display and result
+        return {
+            "ui": {"text": display_text},
+            "result": (display_text,),
+        }
@@ -0,0 +1,5 @@
+"""Display Text tool for ComfyUI."""
+
+from .node import DisplayTextNode, NODE_DISPLAY_NAME
+
+__all__ = ["DisplayTextNode", "NODE_DISPLAY_NAME"]
@@ -0,0 +1,48 @@
+"""Display Text node implementation."""
+
+from ...base import ComfyAssetsBaseNode
+
+
+class DisplayTextNode(ComfyAssetsBaseNode):
+    """Displays text in the ComfyUI interface with copy-to-clipboard functionality."""
+
+    @classmethod
+    def INPUT_TYPES(cls):
+        """Define input types for the node."""
+        return {
+            "required": {
+                "text": ("STRING", {"forceInput": True}),
+            },
+        }
+
+    RETURN_TYPES = ("STRING",)
+    RETURN_NAMES = ("text",)
+    OUTPUT_NODE = True
+    FUNCTION = "display_text"
+    CATEGORY = "ComfyAssets"
+
+    DESCRIPTION = """
+Displays text in the UI with a copy-to-clipboard feature.
+
+Features:
+- Shows text content in a readable format
+- Copy button appears on hover
+- Passes text through for chaining
+"""
+
+    def display_text(self, text):
+        """Display the text and pass it through.
+
+        Args:
+            text: Input text to display
+
+        Returns:
+            Tuple containing the text
+        """
+        # The actual display happens in the frontend
+        # We just pass the text through
+        return {"ui": {"text": [text]}, "result": (text,)}
+
+
+# Node display name
+NODE_DISPLAY_NAME = "Display Text"
@@ -4,7 +4,9 @@ import torch
 from typing import Dict, Tuple


-def create_empty_latent_batch(width: int, height: int, batch_size: int = 1) -> Dict[str, torch.Tensor]:
+def create_empty_latent_batch(
+    width: int, height: int, batch_size: int = 1
+) -> Dict[str, torch.Tensor]:
    """
    Create empty latent tensor with batch support.

@@ -28,7 +30,9 @@ def create_empty_latent_batch(width: int, height: int, batch_size: int = 1) -> D

    # Ensure dimensions are divisible by 8 (VAE requirement)
    if width % 8 != 0 or height % 8 != 0:
-        raise ValueError(f"Width and height must be divisible by 8, got {width}x{height}")
+        raise ValueError(
+            f"Width and height must be divisible by 8, got {width}x{height}"
+        )

    # Convert pixel dimensions to latent space (divide by 8)
    latent_width = width // 8
@@ -36,7 +36,8 @@ class EmptyLatentBatchNode(ComfyAssetsBaseNode):
                metadata = PRESET_METADATA.get(preset_name)
                if metadata:
                    formatted_option = (
-                        f"{preset_name} - {metadata.aspect_ratio} " f"({metadata.megapixels:.1f}MP) - {metadata.model_group}"
+                        f"{preset_name} - {metadata.aspect_ratio} "
+                        f"({metadata.megapixels:.1f}MP) - {metadata.model_group}"
                    )
                    preset_options.append(formatted_option)
                else:
@@ -85,7 +86,8 @@ class EmptyLatentBatchNode(ComfyAssetsBaseNode):
                        "min": 1,
                        "max": 64,
                        "step": 1,
-                        "tooltip": "Number of empty latents to create in the batch. " "Useful for batch processing workflows.",
+                        "tooltip": "Number of empty latents to create in the batch. "
+                        "Useful for batch processing workflows.",
                    },
                ),
            }
@@ -116,7 +118,9 @@ class EmptyLatentBatchNode(ComfyAssetsBaseNode):
            original_preset = self._extract_preset_name(preset)

            # Get base dimensions from preset or custom input
-            base_width, base_height = get_preset_dimensions(original_preset, width, height)
+            base_width, base_height = get_preset_dimensions(
+                original_preset, width, height
+            )

            # Sanitize dimensions to ensure they meet requirements
            final_width, final_height = sanitize_dimensions(base_width, base_height)
@@ -130,17 +134,23 @@ class EmptyLatentBatchNode(ComfyAssetsBaseNode):

            # Validate final dimensions
            if not validate_dimensions(final_width, final_height):
-                self.handle_error(f"Invalid dimensions after sanitization: {final_width}×{final_height}")
+                self.handle_error(
+                    f"Invalid dimensions after sanitization: {final_width}×{final_height}"
+                )

            # Validate batch size
            if batch_size <= 0:
                self.handle_error(f"Batch size must be positive, got {batch_size}")

            if batch_size > 64:
-                self.log_info(f"Large batch size ({batch_size}) may use significant memory")
+                self.log_info(
+                    f"Large batch size ({batch_size}) may use significant memory"
+                )

            # Create the empty latent batch
-            latent_dict = create_empty_latent_batch(final_width, final_height, batch_size)
+            latent_dict = create_empty_latent_batch(
+                final_width, final_height, batch_size
+            )

            # Log the operation
            latent_height = final_height // 8
@@ -188,7 +198,9 @@ class EmptyLatentBatchNode(ComfyAssetsBaseNode):
        # Default to "custom" if we can't parse it
        return "custom"

-    def validate_inputs(self, preset: str, width: int, height: int, batch_size: int) -> bool:
+    def validate_inputs(
+        self, preset: str, width: int, height: int, batch_size: int
+    ) -> bool:
        """
        Validate node inputs.

@@ -279,7 +291,12 @@ class EmptyLatentBatchNode(ComfyAssetsBaseNode):

    def __repr__(self) -> str:
        """Detailed string representation of the node."""
-        return f"EmptyLatentBatchNode(" f"category='{self.CATEGORY}', " f"function='{self.FUNCTION}'" f")"
+        return (
+            f"EmptyLatentBatchNode("
+            f"category='{self.CATEGORY}', "
+            f"function='{self.FUNCTION}'"
+            f")"
+        )


 # Node class mappings for ComfyUI registration
@@ -0,0 +1,89 @@
+{
+  "models": [
+    "gemini-2.5-pro",
+    "gemini-2.5-flash",
+    "gemini-2.5-flash-lite",
+    "gemini-2.5-pro-preview-03-25",
+    "gemini-2.5-flash-preview-05-20",
+    "gemini-2.5-pro-preview-05-06",
+    "gemini-2.5-pro-preview-06-05",
+    "gemini-2.5-flash-lite-preview-06-17",
+    "gemini-2.0-flash",
+    "gemini-2.0-flash-001",
+    "gemini-2.0-flash-lite-001",
+    "gemini-2.0-flash-lite",
+    "gemini-2.5-flash-preview-tts",
+    "gemini-2.5-pro-preview-tts",
+    "gemini-2.0-flash-preview-image-generation",
+    "gemini-2.0-flash-exp",
+    "gemini-2.0-flash-exp-image-generation",
+    "gemini-2.0-flash-lite-preview-02-05",
+    "gemini-2.0-flash-lite-preview",
+    "gemini-2.0-pro-exp",
+    "gemini-2.0-pro-exp-02-05",
+    "learnlm-2.0-flash-experimental",
+    "gemini-1.5-pro-latest",
+    "gemini-1.5-pro-002",
+    "gemini-1.5-pro",
+    "gemini-1.5-flash-latest",
+    "gemini-1.5-flash",
+    "gemini-1.5-flash-002",
+    "gemini-1.5-flash-8b",
+    "gemini-1.5-flash-8b-001",
+    "gemini-1.5-flash-8b-latest",
+    "gemini-2.0-flash-thinking-exp-01-21",
+    "gemini-2.0-flash-thinking-exp",
+    "gemini-2.0-flash-thinking-exp-1219",
+    "gemma-3-1b-it",
+    "gemma-3-4b-it",
+    "gemma-3-12b-it",
+    "gemma-3-27b-it",
+    "gemma-3n-e4b-it",
+    "gemma-3n-e2b-it",
+    "gemini-exp-1206"
+  ],
+  "descriptions": {
+    "gemini-1.5-pro-latest": "Gemini 1.5 Pro Latest",
+    "gemini-1.5-pro-002": "Gemini 1.5 Pro 002",
+    "gemini-1.5-pro": "Gemini 1.5 Pro",
+    "gemini-1.5-flash-latest": "Gemini 1.5 Flash Latest",
+    "gemini-1.5-flash": "Gemini 1.5 Flash",
+    "gemini-1.5-flash-002": "Gemini 1.5 Flash 002",
+    "gemini-1.5-flash-8b": "Gemini 1.5 Flash-8B",
+    "gemini-1.5-flash-8b-001": "Gemini 1.5 Flash-8B 001",
+    "gemini-1.5-flash-8b-latest": "Gemini 1.5 Flash-8B Latest",
+    "gemini-2.5-pro-preview-03-25": "Gemini 2.5 Pro Preview 03-25",
+    "gemini-2.5-flash-preview-05-20": "Gemini 2.5 Flash Preview 05-20",
+    "gemini-2.5-flash": "Gemini 2.5 Flash",
+    "gemini-2.5-flash-lite-preview-06-17": "Gemini 2.5 Flash-Lite Preview 06-17",
+    "gemini-2.5-pro-preview-05-06": "Gemini 2.5 Pro Preview 05-06",
+    "gemini-2.5-pro-preview-06-05": "Gemini 2.5 Pro Preview",
+    "gemini-2.5-pro": "Gemini 2.5 Pro",
+    "gemini-2.0-flash-exp": "Gemini 2.0 Flash Experimental",
+    "gemini-2.0-flash": "Gemini 2.0 Flash",
+    "gemini-2.0-flash-001": "Gemini 2.0 Flash 001",
+    "gemini-2.0-flash-exp-image-generation": "Gemini 2.0 Flash (Image Generation) Experimental",
+    "gemini-2.0-flash-lite-001": "Gemini 2.0 Flash-Lite 001",
+    "gemini-2.0-flash-lite": "Gemini 2.0 Flash-Lite",
+    "gemini-2.0-flash-preview-image-generation": "Gemini 2.0 Flash Preview Image Generation",
+    "gemini-2.0-flash-lite-preview-02-05": "Gemini 2.0 Flash-Lite Preview 02-05",
+    "gemini-2.0-flash-lite-preview": "Gemini 2.0 Flash-Lite Preview",
+    "gemini-2.0-pro-exp": "Gemini 2.0 Pro Experimental",
+    "gemini-2.0-pro-exp-02-05": "Gemini 2.0 Pro Experimental 02-05",
+    "gemini-exp-1206": "Gemini Experimental 1206",
+    "gemini-2.0-flash-thinking-exp-01-21": "Gemini 2.5 Flash Preview 05-20",
+    "gemini-2.0-flash-thinking-exp": "Gemini 2.5 Flash Preview 05-20",
+    "gemini-2.0-flash-thinking-exp-1219": "Gemini 2.5 Flash Preview 05-20",
+    "gemini-2.5-flash-preview-tts": "Gemini 2.5 Flash Preview TTS",
+    "gemini-2.5-pro-preview-tts": "Gemini 2.5 Pro Preview TTS",
+    "learnlm-2.0-flash-experimental": "LearnLM 2.0 Flash Experimental",
+    "gemma-3-1b-it": "Gemma 3 1B",
+    "gemma-3-4b-it": "Gemma 3 4B",
+    "gemma-3-12b-it": "Gemma 3 12B",
+    "gemma-3-27b-it": "Gemma 3 27B",
+    "gemma-3n-e4b-it": "Gemma 3n E4B",
+    "gemma-3n-e2b-it": "Gemma 3n E2B",
+    "gemini-2.5-flash-lite": "Gemini 2.5 Flash-Lite"
+  },
+  "timestamp": 1754142231.0568295
+}
@@ -0,0 +1,5 @@
+"""Gemini Prompt Engineer node for ComfyUI."""
+
+from .node import GeminiPromptNode
+
+__all__ = ["GeminiPromptNode"]
@@ -0,0 +1,163 @@
+"""Logic for Gemini API integration and prompt generation."""
+
+import base64
+import io
+import json
+import os
+from typing import Optional, Tuple
+
+import numpy as np
+from PIL import Image
+
+from .prompts import PROMPT_TEMPLATES
+
+
+def tensor_to_pil(tensor: np.ndarray) -> Image.Image:
+    """Convert ComfyUI tensor to PIL Image.
+
+    Args:
+        tensor: Input tensor in ComfyUI format (B, H, W, C)
+
+    Returns:
+        PIL Image object
+    """
+    # ComfyUI tensors are in [0, 1] range
+    if tensor.ndim == 4:
+        # Take first image from batch
+        tensor = tensor[0]
+
+    # Convert to uint8
+    image_array = (tensor * 255).astype(np.uint8)
+
+    # Convert to PIL
+    return Image.fromarray(image_array, mode="RGB")
+
+
+def image_to_base64(image: Image.Image, format: str = "PNG") -> str:
+    """Convert PIL Image to base64 string.
+
+    Args:
+        image: PIL Image object
+        format: Image format (PNG or JPEG)
+
+    Returns:
+        Base64 encoded string
+    """
+    buffer = io.BytesIO()
+    image.save(buffer, format=format)
+    buffer.seek(0)
+    return base64.b64encode(buffer.read()).decode("utf-8")
+
+
+def get_api_key() -> Optional[str]:
+    """Get Gemini API key from environment or config.
+
+    Returns:
+        API key string or None if not found
+    """
+    # Check environment variable first
+    api_key = os.environ.get("GEMINI_API_KEY")
+
+    if not api_key:
+        # Check for config file in ComfyUI directory
+        try:
+            config_path = os.path.join(
+                os.path.dirname(__file__), "..", "..", "..", "gemini_config.json"
+            )
+            if os.path.exists(config_path):
+                with open(config_path, "r") as f:
+                    config = json.load(f)
+                    api_key = config.get("api_key")
+        except Exception:
+            pass
+
+    return api_key
+
+
+def analyze_image_with_gemini(
+    image: np.ndarray,
+    prompt_type: str,
+    api_key: Optional[str] = None,
+    custom_prompt: Optional[str] = None,
+    model_name: str = "gemini-1.5-flash",
+) -> Tuple[str, Optional[str]]:
+    """Analyze image using Gemini API and generate appropriate prompt.
+
+    Args:
+        image: Input image tensor
+        prompt_type: Type of prompt to generate (flux, sdxl, danbooru, video)
+        api_key: Gemini API key (optional, will try to get from env/config)
+        custom_prompt: Custom system prompt to use instead of templates
+        model_name: Gemini model to use (default: gemini-1.5-flash)
+
+    Returns:
+        Tuple of (generated_prompt, error_message)
+    """
+    # Get API key
+    if not api_key:
+        api_key = get_api_key()
+
+    if not api_key:
+        return (
+            "",
+            "Gemini API key not found. Please set GEMINI_API_KEY environment variable or provide it in the node.",
+        )
+
+    # Convert tensor to PIL image
+    try:
+        pil_image = tensor_to_pil(image)
+    except Exception as e:
+        return "", f"Failed to convert image: {str(e)}"
+
+    # Get system prompt
+    if custom_prompt:
+        system_prompt = custom_prompt
+    else:
+        system_prompt = PROMPT_TEMPLATES.get(prompt_type, PROMPT_TEMPLATES["flux"])
+
+    # Here we would normally make the API call to Gemini
+    # For now, we'll import the google-generativeai library
+    try:
+        import google.generativeai as genai
+    except ImportError:
+        return (
+            "",
+            "google-generativeai library not installed. Please run: pip install google-generativeai",
+        )
+
+    try:
+        # Configure Gemini
+        genai.configure(api_key=api_key)
+
+        # Create model
+        model = genai.GenerativeModel(model_name)
+
+        # Generate content
+        response = model.generate_content(
+            [
+                system_prompt,
+                pil_image,
+                "Analyze this image and generate an appropriate prompt according to the instructions.",
+            ]
+        )
+
+        # Extract text from response
+        if response.text:
+            return response.text.strip(), None
+        else:
+            return "", "No response generated from Gemini"
+
+    except Exception as e:
+        return "", f"Gemini API error: {str(e)}"
+
+
+def validate_prompt_type(prompt_type: str) -> bool:
+    """Validate if prompt type is supported.
+
+    Args:
+        prompt_type: Type of prompt to validate
+
+    Returns:
+        True if valid, False otherwise
+    """
+    return prompt_type in PROMPT_TEMPLATES
@@ -0,0 +1,191 @@
+"""Dynamic model fetching and caching for Gemini API."""
+
+import json
+import os
+import time
+from typing import List, Dict, Optional, Tuple
+import logging
+
+logger = logging.getLogger(__name__)
+
+# Cache settings
+CACHE_DURATION = 3600 * 24  # 24 hours in seconds
+CACHE_FILE = os.path.join(os.path.dirname(__file__), ".gemini_models_cache.json")
+
+
+def get_available_models(
+    api_key: Optional[str] = None, silent: bool = False
+) -> Tuple[List[str], Dict[str, str]]:
+    """Fetch available Gemini models that support generateContent.
+
+    Args:
+        api_key: Optional API key. If not provided, will try to get from environment.
+        silent: If True, suppress error logging (useful for initial load).
+
+    Returns:
+        Tuple of (model_names_list, model_descriptions_dict)
+    """
+    # Check cache first
+    cached_data = _load_cache()
+    if cached_data:
+        return cached_data["models"], cached_data["descriptions"]
+
+    # Try to fetch from API
+    try:
+        models, descriptions = _fetch_models_from_api(api_key, silent=silent)
+        if models:
+            _save_cache(models, descriptions)
+            return models, descriptions
+    except Exception as e:
+        if not silent:
+            logger.warning(f"Failed to fetch models from API: {e}")
+
+    # Fall back to defaults
+    from .prompts import DEFAULT_GEMINI_MODELS
+
+    return DEFAULT_GEMINI_MODELS, {}
+
+
+def _fetch_models_from_api(
+    api_key: Optional[str] = None, silent: bool = False
+) -> Tuple[List[str], Dict[str, str]]:
+    """Fetch models from Gemini API.
+
+    Args:
+        api_key: Optional API key.
+        silent: If True, suppress error logging.
+
+    Returns:
+        Tuple of (model_names_list, model_descriptions_dict)
+    """
+    try:
+        import google.generativeai as genai
+    except ImportError:
+        if not silent:
+            logger.error("google-generativeai not installed")
+        return [], {}
+
+    # Get API key
+    if not api_key:
+        from .logic import get_api_key
+
+        api_key = get_api_key()
+
+    if not api_key:
+        if not silent:
+            logger.debug("No API key available for fetching models")
+        return [], {}
+
+    try:
+        genai.configure(api_key=api_key)
+
+        models = []
+        descriptions = {}
+
+        # Fetch all models
+        for model in genai.list_models():
+            # Only include models that support generateContent
+            if "generateContent" in model.supported_generation_methods:
+                # Remove "models/" prefix from name
+                model_name = model.name.replace("models/", "")
+                models.append(model_name)
+                descriptions[model_name] = model.display_name
+
+        # Sort models by priority (newer versions first)
+        models = _sort_models(models)
+
+        return models, descriptions
+
+    except Exception as e:
+        if not silent:
+            logger.error(f"Error fetching models from API: {e}")
+        return [], {}
+
+
+def _sort_models(models: List[str]) -> List[str]:
+    """Sort models by version and capability.
+
+    Prioritizes:
+    1. Newer versions (2.5 > 2.0 > 1.5)
+    2. Non-experimental models
+    3. Flash models for general use
+    """
+
+    def sort_key(model: str):
+        # Priority scoring
+        score = 0
+
+        # Version priority
+        if "2.5" in model:
+            score += 1000
+        elif "2.0" in model:
+            score += 800
+        elif "1.5" in model:
+            score += 600
+
+        # Model type priority
+        if "pro" in model and "preview" not in model and "exp" not in model:
+            score += 100
+        elif "flash" in model and "preview" not in model and "exp" not in model:
+            score += 90
+
+        # Penalize experimental/preview models
+        if "exp" in model or "experimental" in model:
+            score -= 50
+        if "preview" in model:
+            score -= 30
+
+        # Penalize specific variants
+        if "thinking" in model:
+            score -= 100
+        if "tts" in model:
+            score -= 100
+        if "lite" in model:
+            score -= 20
+
+        return -score  # Negative for descending sort
+
+    return sorted(models, key=sort_key)
+
+
+def _load_cache() -> Optional[Dict]:
+    """Load cached model data if available and not expired."""
+    if not os.path.exists(CACHE_FILE):
+        return None
+
+    try:
+        with open(CACHE_FILE, "r") as f:
+            data = json.load(f)
+
+        # Check if cache is expired
+        if time.time() - data.get("timestamp", 0) > CACHE_DURATION:
+            return None
+
+        return data
+    except Exception as e:
+        logger.warning(f"Failed to load cache: {e}")
+        return None
+
+
+def _save_cache(models: List[str], descriptions: Dict[str, str]) -> None:
+    """Save model data to cache."""
+    try:
+        data = {
+            "models": models,
+            "descriptions": descriptions,
+            "timestamp": time.time(),
+        }
+
+        with open(CACHE_FILE, "w") as f:
+            json.dump(data, f, indent=2)
+    except Exception as e:
+        logger.warning(f"Failed to save cache: {e}")
+
+
+def clear_cache() -> None:
+    """Clear the model cache."""
+    if os.path.exists(CACHE_FILE):
+        try:
+            os.remove(CACHE_FILE)
+        except Exception as e:
+            logger.warning(f"Failed to clear cache: {e}")
@@ -0,0 +1,169 @@
+"""Gemini Prompt Engineer node implementation."""
+
+import torch
+
+from ...base import ComfyAssetsBaseNode
+
+from .logic import analyze_image_with_gemini, validate_prompt_type
+from .prompts import PROMPT_OPTIONS, DEFAULT_GEMINI_MODELS
+from .models import get_available_models
+
+
+class GeminiPromptNode(ComfyAssetsBaseNode):
+    """Analyzes images using Gemini AI to generate optimized prompts for various AI models."""
+
+    @classmethod
+    def INPUT_TYPES(cls):
+        """Define input types for the node."""
+        # Get available models dynamically (silent mode for initial load)
+        models, _ = get_available_models(silent=True)
+
+        # Use default if no models available
+        if not models:
+            models = DEFAULT_GEMINI_MODELS
+
+        # Find best default model
+        default_model = models[0] if models else "gemini-2.5-flash"
+
+        return {
+            "required": {
+                "image": ("IMAGE",),
+                "prompt_type": (PROMPT_OPTIONS, {"default": "flux"}),
+                "model": (models, {"default": default_model}),
+            },
+            "optional": {
+                "api_key": ("STRING", {"default": "", "multiline": False}),
+                "custom_prompt": (
+                    "STRING",
+                    {
+                        "default": "",
+                        "multiline": True,
+                        "placeholder": "Optional: Enter custom system prompt instead of using templates",
+                    },
+                ),
+                "refresh_models": (
+                    "BOOLEAN",
+                    {"default": False, "label_on": "Refresh", "label_off": "Skip"},
+                ),
+            },
+        }
+
+    RETURN_TYPES = ("STRING", "STRING")
+    RETURN_NAMES = ("prompt", "negative_prompt")
+    FUNCTION = "generate_prompt"
+    CATEGORY = "ComfyAssets"
+
+    DESCRIPTION = """
+Analyzes images using Google's Gemini AI to generate optimized prompts.
+
+Supports multiple prompt formats:
+- FLUX: Detailed artistic prompts with quality markers
+- SDXL: Positive/negative prompt pairs with weight emphasis
+- Danbooru: Anime-style booru tags with underscores
+- Video: Motion and temporal descriptions for video generation
+
+Requires Gemini API key (set GEMINI_API_KEY env var or provide in node).
+Install: pip install google-generativeai
+"""
+
+    def generate_prompt(
+        self,
+        image,
+        prompt_type,
+        model,
+        api_key="",
+        custom_prompt="",
+        refresh_models=False,
+    ):
+        """Generate prompt from image using Gemini.
+
+        Args:
+            image: Input image tensor
+            prompt_type: Type of prompt to generate
+            model: Gemini model to use
+            api_key: Optional API key
+            custom_prompt: Optional custom system prompt
+            refresh_models: Whether to refresh the model list
+
+        Returns:
+            Tuple of (prompt, negative_prompt)
+        """
+        # Refresh models if requested
+        if refresh_models and api_key:
+            try:
+                from .models import clear_cache
+
+                # Clear cache to force refresh on next node creation
+                clear_cache()
+                print(
+                    "Model cache cleared. Please recreate the node to see updated models."
+                )
+            except Exception as e:
+                print(f"Failed to clear model cache: {e}")
+
+        # Validate prompt type
+        if not validate_prompt_type(prompt_type):
+            raise ValueError(f"Invalid prompt type: {prompt_type}")
+
+        # Convert torch tensor to numpy if needed
+        if isinstance(image, torch.Tensor):
+            image_np = image.cpu().numpy()
+        else:
+            image_np = image
+
+        # If API key is provided, try to refresh model list in background
+        if api_key:
+            try:
+                from .models import get_available_models
+
+                # Try to get fresh models with the provided API key
+                fresh_models, _ = get_available_models(api_key=api_key, silent=True)
+                if fresh_models and fresh_models != DEFAULT_GEMINI_MODELS:
+                    # Models were successfully fetched with this API key
+                    pass
+            except Exception:
+                pass
+
+        # Analyze image with Gemini
+        prompt, error = analyze_image_with_gemini(
+            image_np,
+            prompt_type,
+            api_key=api_key or None,
+            custom_prompt=custom_prompt or None,
+            model_name=model,
+        )
+
+        if error:
+            # Return error as prompt for visibility
+            return (f"Error: {error}", "")
+
+        # Handle different prompt types
+        if prompt_type == "sdxl":
+            # SDXL returns positive and negative prompts
+            lines = prompt.split("\n")
+            positive_prompt = ""
+            negative_prompt = ""
+
+            for line in lines:
+                if line.lower().startswith("positive:"):
+                    positive_prompt = (
+                        line.replace("Positive:", "").replace("positive:", "").strip()
+                    )
+                elif line.lower().startswith("negative:"):
+                    negative_prompt = (
+                        line.replace("Negative:", "").replace("negative:", "").strip()
+                    )
+
+            # If format not found, assume entire response is positive prompt
+            if not positive_prompt:
+                positive_prompt = prompt
+
+            return (positive_prompt, negative_prompt)
+
+        else:
+            # Other formats don't use negative prompts
+            return (prompt, "")
+
+
+# Node display name
+NODE_DISPLAY_NAME = "Gemini Prompt Engineer"
@@ -0,0 +1,128 @@
+"""System prompts for different AI model types."""
+
+FLUX_PROMPT = """You are an expert FLUX prompt engineer. Analyze the provided image and generate ONLY a FLUX prompt - no explanations, analysis, or additional text.
+
+FLUX uses natural language descriptions, not comma-separated tags. Write a detailed, flowing description that reads like you're explaining the image to someone.
+
+Include these elements in your description:
+- Main subject with specific details (appearance, clothing, expression, pose)
+- Environment and background details
+- Lighting conditions and atmosphere
+- Artistic style or photographic approach
+- Color palette and mood
+- Technical details if relevant (camera angle, focal length, etc.)
+- Textures and materials
+
+Write in a natural, descriptive style. Use complete sentences that flow together. Be specific and detailed but maintain readability.
+
+IMPORTANT: Return ONLY the prompt text. No analysis, headers, or additional commentary. Just the natural language description that can be directly used in FLUX.
+
+Example of correct output:
+A close-up portrait of a middle-aged woman with curly red hair and green eyes, wearing a blue silk blouse. She has a warm smile and freckles across her cheeks. The lighting is soft and natural, coming from a window to her left, creating gentle shadows that accentuate her features. The background is softly blurred, showing hints of a cozy bookshelf. The overall mood is warm and inviting, captured in a photorealistic style with shallow depth of field."""
+
+SDXL_PROMPT = """You are an expert prompt engineer specializing in SDXL (Stable Diffusion XL). Your task is to generate high-quality positive and negative prompts that conform to SDXL prompt formatting standards.
+
+Your expertise includes:
+- Leveraging community-tested techniques (ComfyUI, A1111, InvokeAI)
+- Applying photographic theory for realism, composition, lighting
+- Following Civitai trend standards and style best practices
+- Mastering Pony Diffusion XL formatting for stylized and anime content
+
+Structure prompts in this layered, modular format:
+[Main Subject], [Pose & Camera], [Lighting & Environment], [Style & Details], [Boost Terms], [Style References]
+
+For SDXL specifically:
+- Use quality boosters: 8k, RAW photo, masterpiece, ultra detailed, cinematic lighting
+- Prioritize realism and artistry
+- Excellent for portraits, landscapes, or cinematic scenes
+
+Instructions:
+
+Only reply with two fields:
+Positive prompt: (Your positive prompt here)
+Negative prompt: (Your negative prompt here)
+
+Do not include any commentary or explanation.
+
+Use concise, highly descriptive language that maximizes visual richness.
+
+Follow SDXL prompt conventions: prioritize subject clarity, camera perspective, lighting, mood, style tags, and composition.
+
+Keep total token length efficient (ideally under 250 tokens).
+
+Avoid redundancy and generic filler words.
+
+Focus on crafting super high-quality prompts for stunning visual output.
+
+Example Input:
+A futuristic cyberpunk samurai standing on a neon-lit rooftop in the rain.
+
+Example Output:
+Positive prompt: cyberpunk samurai, neon-lit rooftop, dramatic rain, glowing katana, futuristic cityscape, night scene, cinematic lighting, intense expression, sleek cyber armor, atmospheric depth, ultra-detailed, masterpiece, 8k, sharp focus, trending on artstation
+Negative prompt: blurry, low quality, poorly drawn, extra limbs, bad anatomy, deformed hands, text, watermark, jpeg artifacts, duplicate, cropped, out of frame
+"""
+
+DANBOORU_PROMPT = """You are a Danbooru tagging expert specializing in anime-style image tagging. Analyze the image and generate ONLY Danbooru-style tags - no explanations or analysis.
+
+CRITICAL: Use strict Danbooru conventions:
+- Use underscores for multi-word tags (e.g., long_hair, school_uniform)
+- All tags must be lowercase
+- Character count comes first (1girl, 2boys, multiple_girls)
+- For anime models trained on Danbooru data, proper tagging is essential
+
+Tag order and categories:
+1. Character count (1girl, solo, 2boys, etc.)
+2. Character features (hair_color, eye_color, hair_length)
+3. Expression/pose (smile, looking_at_viewer, sitting)
+4. Clothing (specific items with underscores)
+5. Background/setting (simple_background, outdoors, classroom)
+6. View/composition (upper_body, full_body, from_side)
+7. Quality tags (masterpiece, best_quality, highres)
+
+Common quality prefix for anime models:
+"masterpiece, best_quality, very_aesthetic"
+
+IMPORTANT: Return ONLY the comma-separated tags. Use underscores, not spaces. All lowercase.
+
+Example of correct output:
+1girl, solo, long_hair, blue_eyes, blonde_hair, school_uniform, serafuku, pleated_skirt, smile, looking_at_viewer, classroom, sitting, desk, window, sunlight, upper_body, masterpiece, best_quality"""
+
+VIDEO_PROMPT = """You are a WAN 2.2 video generation prompt specialist. Analyze the content and generate ONLY a video generation prompt optimized for WAN 2.2 - no explanations or analysis.
+
+WAN 2.2 excels with rich, descriptive prompts that focus on:
+- Visual composition and scene elements
+- Specific movements and actions
+- Lighting and aesthetic details
+- Cinematographic elements
+
+Write a single detailed paragraph describing the video scene. Focus on:
+- Main subjects and their actions
+- Visual style and atmosphere
+- Movement dynamics (use words like "intensely", "smoothly", "rapidly")
+- Environmental details and lighting
+- Specific visual elements and their interactions
+
+Keep the prompt descriptive but concise. WAN 2.2 works best with natural language that paints a clear picture of the desired video.
+
+IMPORTANT: Return ONLY the video prompt as a single descriptive paragraph. No analysis, headers, or additional text.
+
+Example of correct output:
+Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage, their movements fluid and dynamic as they exchange rapid punches under dramatic theater lighting that casts long shadows across the ring, with the crowd visible as blurred silhouettes in the darkened background."""
+
+PROMPT_TEMPLATES = {
+    "flux": FLUX_PROMPT,
+    "sdxl": SDXL_PROMPT,
+    "danbooru": DANBOORU_PROMPT,
+    "video": VIDEO_PROMPT,
+}
+
+PROMPT_OPTIONS = ["flux", "sdxl", "danbooru", "video"]
+
+# Default models list (fallback if API is unavailable)
+DEFAULT_GEMINI_MODELS = [
+    "gemini-2.5-flash",
+    "gemini-2.5-pro",
+    "gemini-2.0-flash",
+    "gemini-1.5-flash",
+    "gemini-1.5-pro",
+]
@@ -48,7 +48,9 @@ def get_save_image_path(
    prefix_name = os.path.basename(filename_prefix)

    # Sanitize only the filename part (not the directory path)
-    safe_prefix = prefix_name.replace(":", "_")  # Only sanitize problematic chars for filenames
+    safe_prefix = prefix_name.replace(
+        ":", "_"
+    )  # Only sanitize problematic chars for filenames
    safe_prefix = "".join(c for c in safe_prefix if c.isalnum() or c in "._-")

    # Create unique filename with timestamp to avoid conflicts
@@ -114,7 +116,9 @@ def convert_tensor_to_pil(image_tensor: torch.Tensor) -> Image.Image:
    return img


-def create_png_metadata(prompt: Optional[Dict] = None, extra_pnginfo: Optional[Dict] = None) -> Optional[PngInfo]:
+def create_png_metadata(
+    prompt: Optional[Dict] = None, extra_pnginfo: Optional[Dict] = None
+) -> Optional[PngInfo]:
    """
    Create PNG metadata with workflow information

@@ -242,7 +246,10 @@ def process_image_batch(
    format_extensions = {"PNG": ".png", "JPEG": ".jpg", "WEBP": ".webp"}

    if format_type not in format_extensions:
-        raise ValueError(f"Unsupported format: {format_type}. " f"Supported: {list(format_extensions.keys())}")
+        raise ValueError(
+            f"Unsupported format: {format_type}. "
+            f"Supported: {list(format_extensions.keys())}"
+        )

    format_ext = format_extensions[format_type]

@@ -308,7 +315,9 @@ def process_image_batch(
    return results, enhanced_data


-def validate_save_inputs(images: torch.Tensor, format_type: str, quality: int, png_compress_level: int) -> None:
+def validate_save_inputs(
+    images: torch.Tensor, format_type: str, quality: int, png_compress_level: int
+) -> None:
    """
    Validate inputs for image saving

@@ -326,19 +335,31 @@ def validate_save_inputs(images: torch.Tensor, format_type: str, quality: int, p
        raise ValueError(f"images must be a torch.Tensor, got {type(images).__name__}")

    if len(images.shape) != 4:
-        raise ValueError(f"images tensor must have 4 dimensions [batch, height, width, channels], " f"got {len(images.shape)}")
+        raise ValueError(
+            f"images tensor must have 4 dimensions [batch, height, width, channels], "
+            f"got {len(images.shape)}"
+        )

    # Validate format
    supported_formats = ["PNG", "JPEG", "WEBP"]
    if format_type not in supported_formats:
-        raise ValueError(f"format must be one of {supported_formats}, got {format_type}")
+        raise ValueError(
+            f"format must be one of {supported_formats}, got {format_type}"
+        )

    # Validate quality (for JPEG/WebP)
    if format_type in ["JPEG", "WEBP"]:
        if not isinstance(quality, int) or not (1 <= quality <= 100):
-            raise ValueError(f"quality must be an integer between 1 and 100, got {quality}")
+            raise ValueError(
+                f"quality must be an integer between 1 and 100, got {quality}"
+            )

    # Validate PNG compression level
    if format_type == "PNG":
-        if not isinstance(png_compress_level, int) or not (0 <= png_compress_level <= 9):
-            raise ValueError(f"png_compress_level must be an integer between 0 and 9, " f"got {png_compress_level}")
+        if not isinstance(png_compress_level, int) or not (
+            0 <= png_compress_level <= 9
+        ):
+            raise ValueError(
+                f"png_compress_level must be an integer between 0 and 9, "
+                f"got {png_compress_level}"
+            )
@@ -79,7 +79,8 @@ class KikoSaveImageNode(ComfyAssetsBaseNode):
                    "BOOLEAN",
                    {
                        "default": False,
-                        "tooltip": "Use lossless WebP compression " "(ignores quality setting)",
+                        "tooltip": "Use lossless WebP compression "
+                        "(ignores quality setting)",
                    },
                ),
                "popup": (
@@ -162,7 +163,10 @@ class KikoSaveImageNode(ComfyAssetsBaseNode):

            # Log results
            total_size = sum(data["file_size"] for data in enhanced_data)
-            self.log_info(f"Successfully saved {len(results)} images " f"(total size: {total_size / 1024:.1f} KB)")
+            self.log_info(
+                f"Successfully saved {len(results)} images "
+                f"(total size: {total_size / 1024:.1f} KB)"
+            )

            # Return UI data for ComfyUI preview (clean) + enhanced data for our JS
            return {
@@ -204,7 +208,9 @@ class KikoSaveImageNode(ComfyAssetsBaseNode):

        # Additional node-specific validation
        if not isinstance(webp_lossless, bool):
-            raise ValueError(f"webp_lossless must be a boolean, got {type(webp_lossless).__name__}")
+            raise ValueError(
+                f"webp_lossless must be a boolean, got {type(webp_lossless).__name__}"
+            )

        if not isinstance(popup, bool):
            raise ValueError(f"popup must be a boolean, got {type(popup).__name__}")
@@ -28,7 +28,9 @@ def extract_dimensions(
    if image is not None:
        # IMAGE tensor format: [batch, height, width, channels]
        if len(image.shape) != 4:
-            raise ValueError(f"Expected IMAGE tensor with 4 dimensions, got {len(image.shape)}")
+            raise ValueError(
+                f"Expected IMAGE tensor with 4 dimensions, got {len(image.shape)}"
+            )

        _, height, width, _ = image.shape
        return int(width), int(height)
@@ -40,7 +42,10 @@ def extract_dimensions(

        samples = latent["samples"]
        if len(samples.shape) != 4:
-            raise ValueError(f"Expected LATENT samples tensor with 4 dimensions, " f"got {len(samples.shape)}")
+            raise ValueError(
+                f"Expected LATENT samples tensor with 4 dimensions, "
+                f"got {len(samples.shape)}"
+            )

        _, _, latent_height, latent_width = samples.shape

@@ -74,7 +79,9 @@ def ensure_divisible_by_8(width: int, height: int) -> Tuple[int, int]:
    return int(new_width), int(new_height)


-def calculate_scaled_dimensions(width: int, height: int, scale_factor: float) -> Tuple[int, int]:
+def calculate_scaled_dimensions(
+    width: int, height: int, scale_factor: float
+) -> Tuple[int, int]:
    """
    Calculate new dimensions with scale factor and ensure divisible by 8

@@ -97,7 +104,9 @@ def calculate_scaled_dimensions(width: int, height: int, scale_factor: float) ->
    return ensure_divisible_by_8(new_width, new_height)


-def validate_scale_factor(scale_factor: float, min_scale: float = 0.1, max_scale: float = 8.0) -> None:
+def validate_scale_factor(
+    scale_factor: float, min_scale: float = 0.1, max_scale: float = 8.0
+) -> None:
    """
    Validate scale factor is within reasonable bounds

@@ -110,13 +119,19 @@ def validate_scale_factor(scale_factor: float, min_scale: float = 0.1, max_scale
        ValueError: If scale factor is out of bounds
    """
    if not isinstance(scale_factor, (int, float)):
-        raise ValueError(f"Scale factor must be a number, got {type(scale_factor).__name__}")
+        raise ValueError(
+            f"Scale factor must be a number, got {type(scale_factor).__name__}"
+        )

    if scale_factor < min_scale:
-        raise ValueError(f"Scale factor {scale_factor} is too small (minimum: {min_scale})")
+        raise ValueError(
+            f"Scale factor {scale_factor} is too small (minimum: {min_scale})"
+        )

    if scale_factor > max_scale:
-        raise ValueError(f"Scale factor {scale_factor} is too large (maximum: {max_scale})")
+        raise ValueError(
+            f"Scale factor {scale_factor} is too large (maximum: {max_scale})"
+        )


 def calculate_resolution_from_input(
@@ -146,6 +161,8 @@ def calculate_resolution_from_input(
    original_width, original_height = extract_dimensions(image=image, latent=latent)

    # Calculate scaled dimensions
-    new_width, new_height = calculate_scaled_dimensions(original_width, original_height, scale_factor)
+    new_width, new_height = calculate_scaled_dimensions(
+        original_width, original_height, scale_factor
+    )

    return new_width, new_height
@@ -42,7 +42,8 @@ class ResolutionCalculatorNode(ComfyAssetsBaseNode):
                        "max": 8.0,
                        "step": 0.1,
                        "display": "slider",
-                        "tooltip": "Factor to scale the resolution by " "(e.g., 2.0 for 2x, 0.5 for half scale)",
+                        "tooltip": "Factor to scale the resolution by "
+                        "(e.g., 2.0 for 2x, 0.5 for half scale)",
                    },
                ),
            },
@@ -87,11 +88,20 @@ class ResolutionCalculatorNode(ComfyAssetsBaseNode):
            self.validate_inputs(scale_factor=scale_factor, image=image, latent=latent)

            # Log the operation
-            input_type = "IMAGE" if image is not None else "LATENT" if latent is not None else "NONE"
-            self.log_info(f"Calculating resolution with scale_factor={scale_factor}, " f"input_type={input_type}")
+            input_type = (
+                "IMAGE"
+                if image is not None
+                else "LATENT" if latent is not None else "NONE"
+            )
+            self.log_info(
+                f"Calculating resolution with scale_factor={scale_factor}, "
+                f"input_type={input_type}"
+            )

            # Calculate the resolution
-            width, height = calculate_resolution_from_input(scale_factor=scale_factor, image=image, latent=latent)
+            width, height = calculate_resolution_from_input(
+                scale_factor=scale_factor, image=image, latent=latent
+            )

            # Log the result
            self.log_info(f"Calculated resolution: {width}x{height}")
@@ -126,7 +136,9 @@ class ResolutionCalculatorNode(ComfyAssetsBaseNode):

        # Validate scale factor type
        if not isinstance(scale_factor, (int, float)):
-            raise ValueError(f"scale_factor must be a number, got {type(scale_factor).__name__}")
+            raise ValueError(
+                f"scale_factor must be a number, got {type(scale_factor).__name__}"
+            )

        # Validate tensors using helper methods
        if image is not None:
@@ -138,11 +150,14 @@ class ResolutionCalculatorNode(ComfyAssetsBaseNode):
    def _validate_image_tensor(self, image: torch.Tensor) -> None:
        """Validate image tensor format"""
        if not isinstance(image, torch.Tensor):
-            raise ValueError(f"image must be a torch.Tensor, got {type(image).__name__}")
+            raise ValueError(
+                f"image must be a torch.Tensor, got {type(image).__name__}"
+            )

        if len(image.shape) != 4:
            raise ValueError(
-                f"image tensor must have 4 dimensions " f"[batch, height, width, channels], got {len(image.shape)}"
+                f"image tensor must have 4 dimensions "
+                f"[batch, height, width, channels], got {len(image.shape)}"
            )

    def _validate_latent_dict(self, latent: Dict[str, torch.Tensor]) -> None:
@@ -155,11 +170,15 @@ class ResolutionCalculatorNode(ComfyAssetsBaseNode):

        samples = latent["samples"]
        if not isinstance(samples, torch.Tensor):
-            raise ValueError(f"latent['samples'] must be a torch.Tensor, " f"got {type(samples).__name__}")
+            raise ValueError(
+                f"latent['samples'] must be a torch.Tensor, "
+                f"got {type(samples).__name__}"
+            )

        if len(samples.shape) != 4:
            raise ValueError(
-                f"latent samples tensor must have 4 dimensions " f"[batch, channels, height, width], got {len(samples.shape)}"
+                f"latent samples tensor must have 4 dimensions "
+                f"[batch, channels, height, width], got {len(samples.shape)}"
            )


@@ -65,7 +65,9 @@ class SamplerComboCompactNode(ComfyAssetsBaseNode):
    FUNCTION = "get_combo"
    CATEGORY = "ComfyAssets"

-    def get_combo(self, sampler: str, sched: str, steps: int, cfg: float) -> Tuple[object, str, int, float]:
+    def get_combo(
+        self, sampler: str, sched: str, steps: int, cfg: float
+    ) -> Tuple[object, str, int, float]:
        """
        Get compact sampler combo configuration.

@@ -40,7 +40,9 @@ except ImportError:
    ]


-def validate_sampler_settings(sampler_name: str, scheduler: str, steps: int, cfg: float) -> bool:
+def validate_sampler_settings(
+    sampler_name: str, scheduler: str, steps: int, cfg: float
+) -> bool:
    """
    Validate sampler configuration settings.

@@ -81,7 +83,9 @@ def validate_sampler_settings(sampler_name: str, scheduler: str, steps: int, cfg
        return False


-def get_sampler_combo(sampler_name: str, scheduler: str, steps: int, cfg: float) -> Tuple[str, str, int, float]:
+def get_sampler_combo(
+    sampler_name: str, scheduler: str, steps: int, cfg: float
+) -> Tuple[str, str, int, float]:
    """
    Process and return sampler combo settings.

@@ -70,7 +70,9 @@ class SamplerComboNode(ComfyAssetsBaseNode):
    FUNCTION = "get_sampler_combo"
    CATEGORY = "ComfyAssets"

-    def get_sampler_combo(self, sampler_name: str, scheduler: str, steps: int, cfg: float) -> Tuple[object, str, int, float]:
+    def get_sampler_combo(
+        self, sampler_name: str, scheduler: str, steps: int, cfg: float
+    ) -> Tuple[object, str, int, float]:
        """
        Get sampler combo configuration.

@@ -117,7 +119,10 @@ class SamplerComboNode(ComfyAssetsBaseNode):
                # Return sampler name for testing
                sampler = result[0]

-            self.log_info(f"Configured sampler combo: {result[0]}, {result[1]}, " f"{result[2]} steps, CFG {result[3]}")
+            self.log_info(
+                f"Configured sampler combo: {result[0]}, {result[1]}, "
+                f"{result[2]} steps, CFG {result[3]}"
+            )

            return (sampler, result[1], result[2], result[3])

@@ -139,7 +144,9 @@ class SamplerComboNode(ComfyAssetsBaseNode):
                sampler = "euler"
            return (sampler, "normal", 20, 7.0)

-    def validate_inputs(self, sampler_name: str, scheduler: str, steps: int, cfg: float) -> None:
+    def validate_inputs(
+        self, sampler_name: str, scheduler: str, steps: int, cfg: float
+    ) -> None:
        """
        Validate sampler combo inputs.

@@ -154,7 +161,8 @@ class SamplerComboNode(ComfyAssetsBaseNode):
        """
        if not validate_sampler_settings(sampler_name, scheduler, steps, cfg):
            self.handle_error(
-                f"Invalid sampler settings: sampler={sampler_name}, " f"scheduler={scheduler}, steps={steps}, cfg={cfg}"
+                f"Invalid sampler settings: sampler={sampler_name}, "
+                f"scheduler={scheduler}, steps={steps}, cfg={cfg}"
            )

    def get_scheduler_suggestions(self, sampler_name: str) -> list:
@@ -205,7 +213,9 @@ class SamplerComboNode(ComfyAssetsBaseNode):
            "recommendation": f"Recommended range: {min_cfg}-{max_cfg} CFG",
        }

-    def get_combo_analysis(self, sampler_name: str, scheduler: str, steps: int, cfg: float) -> dict:
+    def get_combo_analysis(
+        self, sampler_name: str, scheduler: str, steps: int, cfg: float
+    ) -> dict:
        """
        Analyze the sampler combo configuration and provide recommendations.

@@ -264,7 +274,10 @@ class SamplerComboNode(ComfyAssetsBaseNode):

    def __str__(self) -> str:
        """String representation of the node."""
-        return f"SamplerComboNode(samplers={len(SAMPLERS)}, " f"schedulers={len(SCHEDULERS)})"
+        return (
+            f"SamplerComboNode(samplers={len(SAMPLERS)}, "
+            f"schedulers={len(SCHEDULERS)})"
+        )

    def __repr__(self) -> str:
        """Detailed string representation of the node."""
@@ -66,7 +66,9 @@ def sanitize_seed_value(seed: Any) -> int:
        raise ValueError(f"Invalid seed value: {seed}") from e


-def create_history_entry(seed: int, timestamp: Optional[float] = None) -> Dict[str, Any]:
+def create_history_entry(
+    seed: int, timestamp: Optional[float] = None
+) -> Dict[str, Any]:
    """
    Create a standardized history entry for a seed.

@@ -87,7 +89,9 @@ def create_history_entry(seed: int, timestamp: Optional[float] = None) -> Dict[s
    }


-def filter_duplicate_seeds(history: List[Dict[str, Any]], new_seed: int, dedup_window_ms: int = 500) -> bool:
+def filter_duplicate_seeds(
+    history: List[Dict[str, Any]], new_seed: int, dedup_window_ms: int = 500
+) -> bool:
    """
    Check if a seed should be filtered as a duplicate.

@@ -189,7 +193,9 @@ def format_time_ago(timestamp: float) -> str:
        return f"{seconds}s ago"


-def search_history_by_seed(history: List[Dict[str, Any]], seed: int) -> Optional[Dict[str, Any]]:
+def search_history_by_seed(
+    history: List[Dict[str, Any]], seed: int
+) -> Optional[Dict[str, Any]]:
    """
    Search history for a specific seed value.

@@ -28,7 +28,8 @@ class SeedHistoryNode(ComfyAssetsBaseNode):
                        "default": 12345,
                        "min": 0,
                        "max": 0xFFFFFFFFFFFFFFFF,
-                        "tooltip": "Seed value for generation processes. " "History UI tracks all changes automatically.",
+                        "tooltip": "Seed value for generation processes. "
+                        "History UI tracks all changes automatically.",
                    },
                ),
            }
@@ -56,7 +57,10 @@ class SeedHistoryNode(ComfyAssetsBaseNode):
                import logging

                logger = logging.getLogger(__name__)
-                logger.error(f"{self.__class__.__name__}: Invalid seed value: {seed}. " f"Using fallback seed 12345.")
+                logger.error(
+                    f"{self.__class__.__name__}: Invalid seed value: {seed}. "
+                    f"Using fallback seed 12345."
+                )
                return (12345,)

            clean_seed = sanitize_seed_value(seed)
@@ -68,7 +72,10 @@ class SeedHistoryNode(ComfyAssetsBaseNode):
            import logging

            logger = logging.getLogger(__name__)
-            logger.error(f"{self.__class__.__name__}: Error processing seed: {str(e)}. " f"Using fallback seed 12345.")
+            logger.error(
+                f"{self.__class__.__name__}: Error processing seed: {str(e)}. "
+                f"Using fallback seed 12345."
+            )
            return (12345,)

    def generate_new_seed(self) -> int:
@@ -5,7 +5,9 @@ from math import gcd
 from .presets import PRESET_OPTIONS


-def get_preset_dimensions(preset: str, custom_width: int, custom_height: int) -> Tuple[int, int]:
+def get_preset_dimensions(
+    preset: str, custom_width: int, custom_height: int
+) -> Tuple[int, int]:
    """
    Get dimensions from preset name or use custom dimensions.

@@ -112,7 +114,9 @@ def sanitize_dimensions(width: int, height: int) -> Tuple[int, int]:
    return width, height


-def get_dimension_info(preset: str, width: int, height: int, swap_enabled: bool) -> dict:
+def get_dimension_info(
+    preset: str, width: int, height: int, swap_enabled: bool
+) -> dict:
    """
    Get comprehensive dimension information including metadata.

@@ -201,7 +205,9 @@ def parse_dimension_string(dimension_str: str) -> Tuple[int, int]:
        raise ValueError(f"Could not parse dimensions from {dimension_str}: {e}")


-def get_optimal_scale_factor(current_width: int, current_height: int, target_width: int, target_height: int) -> float:
+def get_optimal_scale_factor(
+    current_width: int, current_height: int, target_width: int, target_height: int
+) -> float:
    """
    Calculate optimal scale factor to get from current to target dimensions.

@@ -36,7 +36,8 @@ class WidthHeightSelectorNode(ComfyAssetsBaseNode):
                metadata = PRESET_METADATA.get(preset_name)
                if metadata:
                    formatted_option = (
-                        f"{preset_name} - {metadata.aspect_ratio} " f"({metadata.megapixels:.1f}MP) - {metadata.model_group}"
+                        f"{preset_name} - {metadata.aspect_ratio} "
+                        f"({metadata.megapixels:.1f}MP) - {metadata.model_group}"
                    )
                    preset_options.append(formatted_option)
                else:
@@ -103,7 +104,9 @@ class WidthHeightSelectorNode(ComfyAssetsBaseNode):
            original_preset = self._extract_preset_name(preset)

            # Get base dimensions from preset or custom input
-            final_width, final_height = get_preset_dimensions(original_preset, width, height)
+            final_width, final_height = get_preset_dimensions(
+                original_preset, width, height
+            )

            # Sanitize dimensions to ensure they meet ComfyUI requirements
            final_width, final_height = sanitize_dimensions(final_width, final_height)
@@ -112,7 +115,8 @@ class WidthHeightSelectorNode(ComfyAssetsBaseNode):
            if not validate_dimensions(final_width, final_height):
                # This should not happen after sanitization, but handle gracefully
                self.handle_error(
-                    f"Generated invalid dimensions: {final_width}×{final_height}. " f"Using fallback dimensions 1024×1024."
+                    f"Generated invalid dimensions: {final_width}×{final_height}. "
+                    f"Using fallback dimensions 1024×1024."
                )
                final_width, final_height = 1024, 1024

@@ -120,7 +124,9 @@ class WidthHeightSelectorNode(ComfyAssetsBaseNode):

        except Exception as e:
            # Handle any unexpected errors gracefully
-            error_msg = f"Error processing dimensions: {str(e)}. Using fallback 1024×1024."
+            error_msg = (
+                f"Error processing dimensions: {str(e)}. Using fallback 1024×1024."
+            )
            self.handle_error(error_msg)
            return (1024, 1024)

@@ -170,7 +176,10 @@ class WidthHeightSelectorNode(ComfyAssetsBaseNode):

        metadata = get_preset_metadata(preset)
        if metadata.width > 0:  # Valid metadata
-            return f"{preset} - {metadata.aspect_ratio} ({metadata.megapixels:.1f}MP) - " f"{metadata.description}"
+            return (
+                f"{preset} - {metadata.aspect_ratio} ({metadata.megapixels:.1f}MP) - "
+                f"{metadata.description}"
+            )

        return f"Unknown preset: {preset}"

@@ -287,15 +287,21 @@ PRESET_METADATA: Dict[str, PresetMetadata] = {

 # Legacy compatibility - maintain old preset dictionaries
 SDXL_PRESETS: Dict[str, Tuple[int, int]] = {
-    k: (v.width, v.height) for k, v in PRESET_METADATA.items() if v.model_group == "SDXL"
+    k: (v.width, v.height)
+    for k, v in PRESET_METADATA.items()
+    if v.model_group == "SDXL"
 }

 FLUX_PRESETS: Dict[str, Tuple[int, int]] = {
-    k: (v.width, v.height) for k, v in PRESET_METADATA.items() if v.model_group == "FLUX"
+    k: (v.width, v.height)
+    for k, v in PRESET_METADATA.items()
+    if v.model_group == "FLUX"
 }

 ULTRA_WIDE_PRESETS: Dict[str, Tuple[int, int]] = {
-    k: (v.width, v.height) for k, v in PRESET_METADATA.items() if v.model_group == "Ultra-Wide"
+    k: (v.width, v.height)
+    for k, v in PRESET_METADATA.items()
+    if v.model_group == "Ultra-Wide"
 }

 # Combined preset options for ComfyUI dropdown
@@ -308,28 +314,78 @@ PRESET_OPTIONS: Dict[str, Tuple[int, int]] = {
 PRESET_CATEGORIES = {
    "Custom": ["custom"],
    # SDXL Categories
-    "SDXL Square": [k for k, v in PRESET_METADATA.items() if v.model_group == "SDXL" and v.category == "Square"],
-    "SDXL Portrait": [k for k, v in PRESET_METADATA.items() if v.model_group == "SDXL" and v.category == "Portrait"],
-    "SDXL Landscape": [k for k, v in PRESET_METADATA.items() if v.model_group == "SDXL" and v.category == "Landscape"],
+    "SDXL Square": [
+        k
+        for k, v in PRESET_METADATA.items()
+        if v.model_group == "SDXL" and v.category == "Square"
+    ],
+    "SDXL Portrait": [
+        k
+        for k, v in PRESET_METADATA.items()
+        if v.model_group == "SDXL" and v.category == "Portrait"
+    ],
+    "SDXL Landscape": [
+        k
+        for k, v in PRESET_METADATA.items()
+        if v.model_group == "SDXL" and v.category == "Landscape"
+    ],
    # FLUX Categories
-    "FLUX Square": [k for k, v in PRESET_METADATA.items() if v.model_group == "FLUX" and v.category == "Square"],
-    "FLUX Portrait": [k for k, v in PRESET_METADATA.items() if v.model_group == "FLUX" and v.category == "Portrait"],
-    "FLUX Cinematic": [k for k, v in PRESET_METADATA.items() if v.model_group == "FLUX" and v.category == "Cinematic"],
-    "FLUX Classic": [k for k, v in PRESET_METADATA.items() if v.model_group == "FLUX" and v.category == "Classic"],
-    "FLUX Photography": [k for k, v in PRESET_METADATA.items() if v.model_group == "FLUX" and v.category == "Photography"],
+    "FLUX Square": [
+        k
+        for k, v in PRESET_METADATA.items()
+        if v.model_group == "FLUX" and v.category == "Square"
+    ],
+    "FLUX Portrait": [
+        k
+        for k, v in PRESET_METADATA.items()
+        if v.model_group == "FLUX" and v.category == "Portrait"
+    ],
+    "FLUX Cinematic": [
+        k
+        for k, v in PRESET_METADATA.items()
+        if v.model_group == "FLUX" and v.category == "Cinematic"
+    ],
+    "FLUX Classic": [
+        k
+        for k, v in PRESET_METADATA.items()
+        if v.model_group == "FLUX" and v.category == "Classic"
+    ],
+    "FLUX Photography": [
+        k
+        for k, v in PRESET_METADATA.items()
+        if v.model_group == "FLUX" and v.category == "Photography"
+    ],
    # Ultra-Wide Categories
-    "Ultra-Wide Gaming": [k for k, v in PRESET_METADATA.items() if v.model_group == "Ultra-Wide" and v.category == "Gaming"],
+    "Ultra-Wide Gaming": [
+        k
+        for k, v in PRESET_METADATA.items()
+        if v.model_group == "Ultra-Wide" and v.category == "Gaming"
+    ],
    "Ultra-Wide Cinematic": [
-        k for k, v in PRESET_METADATA.items() if v.model_group == "Ultra-Wide" and v.category == "Cinematic"
+        k
+        for k, v in PRESET_METADATA.items()
+        if v.model_group == "Ultra-Wide" and v.category == "Cinematic"
    ],
    "Ultra-Wide Panoramic": [
-        k for k, v in PRESET_METADATA.items() if v.model_group == "Ultra-Wide" and v.category == "Panoramic"
+        k
+        for k, v in PRESET_METADATA.items()
+        if v.model_group == "Ultra-Wide" and v.category == "Panoramic"
+    ],
+    "Ultra-Wide Mobile": [
+        k
+        for k, v in PRESET_METADATA.items()
+        if v.model_group == "Ultra-Wide" and v.category == "Mobile"
    ],
-    "Ultra-Wide Mobile": [k for k, v in PRESET_METADATA.items() if v.model_group == "Ultra-Wide" and v.category == "Mobile"],
    "Ultra-Wide Vertical": [
-        k for k, v in PRESET_METADATA.items() if v.model_group == "Ultra-Wide" and v.category == "Vertical"
+        k
+        for k, v in PRESET_METADATA.items()
+        if v.model_group == "Ultra-Wide" and v.category == "Vertical"
+    ],
+    "Ultra-Wide Banner": [
+        k
+        for k, v in PRESET_METADATA.items()
+        if v.model_group == "Ultra-Wide" and v.category == "Banner"
    ],
-    "Ultra-Wide Banner": [k for k, v in PRESET_METADATA.items() if v.model_group == "Ultra-Wide" and v.category == "Banner"],
 }

 # Legacy compatibility - preset descriptions
@@ -339,7 +395,9 @@ PRESET_DESCRIPTIONS = {k: v.description for k, v in PRESET_METADATA.items()}
 MODEL_RECOMMENDATIONS = {
    "SDXL": [k for k, v in PRESET_METADATA.items() if v.model_group == "SDXL"],
    "FLUX": [k for k, v in PRESET_METADATA.items() if v.model_group == "FLUX"],
-    "Ultra-Wide": [k for k, v in PRESET_METADATA.items() if v.model_group == "Ultra-Wide"],
+    "Ultra-Wide": [
+        k for k, v in PRESET_METADATA.items() if v.model_group == "Ultra-Wide"
+    ],
 }


@@ -393,7 +451,9 @@ def validate_preset_dimensions() -> bool:

        # Check divisible by 8
        if width % 8 != 0 or height % 8 != 0:
-            print(f"ERROR: {preset_name} dimensions not divisible by 8: {width}×{height}")
+            print(
+                f"ERROR: {preset_name} dimensions not divisible by 8: {width}×{height}"
+            )
            return False

        # Check reasonable bounds
@@ -409,7 +469,9 @@ def validate_metadata_consistency() -> bool:
    """Validate metadata consistency and completeness."""
    for preset_name, metadata in PRESET_METADATA.items():
        # Verify aspect ratio calculation
-        expected_ratio, expected_decimal = calculate_aspect_ratio(metadata.width, metadata.height)
+        expected_ratio, expected_decimal = calculate_aspect_ratio(
+            metadata.width, metadata.height
+        )
        if abs(metadata.aspect_decimal - expected_decimal) > 0.001:
            print(
                f"ERROR: {preset_name} aspect ratio mismatch: "
@@ -420,7 +482,10 @@ def validate_metadata_consistency() -> bool:
        # Verify megapixel calculation
        expected_mp = (metadata.width * metadata.height) / 1_000_000
        if abs(metadata.megapixels - expected_mp) > 0.1:
-            print(f"ERROR: {preset_name} megapixel mismatch: " f"expected {expected_mp:.2f}, got {metadata.megapixels}")
+            print(
+                f"ERROR: {preset_name} megapixel mismatch: "
+                f"expected {expected_mp:.2f}, got {metadata.megapixels}"
+            )
            return False

    return True
@@ -5,7 +5,7 @@ build-backend = "setuptools.build_meta"
 [project]
 name = "kikotools"
 description = "Simple tools for ComfyUI"
-version = "1.0.7"
+version = "1.0.9"
 license = {text = "MIT"}
 dependencies = []

@@ -102,12 +102,18 @@ def assert_divisible_by_8(width: int, height: int) -> None:
    assert height % 8 == 0, f"Height {height} must be divisible by 8"


-def assert_reasonable_dimensions(width: int, height: int, min_size: int = 64, max_size: int = 8192) -> None:
+def assert_reasonable_dimensions(
+    width: int, height: int, min_size: int = 64, max_size: int = 8192
+) -> None:
    """
    Helper function to assert dimensions are within reasonable bounds
    """
-    assert min_size <= width <= max_size, f"Width {width} out of reasonable range [{min_size}, {max_size}]"
-    assert min_size <= height <= max_size, f"Height {height} out of reasonable range [{min_size}, {max_size}]"
+    assert (
+        min_size <= width <= max_size
+    ), f"Width {width} out of reasonable range [{min_size}, {max_size}]"
+    assert (
+        min_size <= height <= max_size
+    ), f"Height {height} out of reasonable range [{min_size}, {max_size}]"


 # Make helper functions available as pytest fixtures
@@ -32,7 +32,10 @@ class TestComfyAssetsBaseNode:
                node.handle_error("Test error message")

            mock_logger.error.assert_called_once()
-            assert "ComfyAssetsBaseNode: Test error message" in mock_logger.error.call_args[0][0]
+            assert (
+                "ComfyAssetsBaseNode: Test error message"
+                in mock_logger.error.call_args[0][0]
+            )

    def test_handle_error_with_exception_logs_exception(self):
        """Test error handling with original exception logs both messages"""
@@ -55,7 +58,10 @@ class TestComfyAssetsBaseNode:
            node.log_info("Test information")

            mock_logger.info.assert_called_once()
-            assert "ComfyAssetsBaseNode: Test information" in mock_logger.info.call_args[0][0]
+            assert (
+                "ComfyAssetsBaseNode: Test information"
+                in mock_logger.info.call_args[0][0]
+            )

    def test_get_node_info_returns_metadata(self):
        """Test get_node_info returns correct metadata"""
@@ -0,0 +1,287 @@
+"""Unit tests for DisplayAny node."""
+
+import numpy as np
+import pytest
+import torch
+
+from kikotools.tools.display_any import DisplayAnyNode
+from kikotools.tools.display_any.logic import (
+    format_display_value,
+    get_tensor_shapes,
+    validate_display_mode,
+)
+from kikotools.tools.display_any.node import AnyType
+
+
+class TestAnyType:
+    """Test cases for AnyType class."""
+
+    def test_anytype_not_equal(self):
+        """Test that AnyType is never equal to other types."""
+        any_type = AnyType("*")
+
+        # Should not be equal to any other type
+        assert not (any_type != "STRING")
+        assert not (any_type != "IMAGE")
+        assert not (any_type != "LATENT")
+        assert not (any_type != 123)
+        assert not (any_type != None)
+        assert not (any_type != ["LIST"])
+
+    def test_anytype_string_representation(self):
+        """Test string representation of AnyType."""
+        any_type = AnyType("*")
+        assert str(any_type) == "*"
+
+
+class TestDisplayAnyNode:
+    """Test cases for DisplayAnyNode."""
+
+    def test_node_properties(self):
+        """Test node has correct properties."""
+        assert DisplayAnyNode.CATEGORY == "ComfyAssets"
+        assert DisplayAnyNode.FUNCTION == "display"
+        assert DisplayAnyNode.RETURN_TYPES == ("STRING",)
+        assert DisplayAnyNode.RETURN_NAMES == ("display_text",)
+        assert DisplayAnyNode.OUTPUT_NODE is True
+
+    def test_input_types(self):
+        """Test INPUT_TYPES configuration."""
+        input_types = DisplayAnyNode.INPUT_TYPES()
+
+        # Check required inputs
+        assert "required" in input_types
+        assert "input" in input_types["required"]
+        # Check that input is AnyType with wildcard
+        input_type = input_types["required"]["input"]
+        assert len(input_type) == 2
+        assert isinstance(input_type[0], AnyType)
+        assert str(input_type[0]) == "*"
+        assert input_type[1] == {}
+        assert "mode" in input_types["required"]
+        assert input_types["required"]["mode"] == (["raw value", "tensor shape"],)
+
+    def test_validate_inputs(self):
+        """Test VALIDATE_INPUTS always returns True."""
+        assert DisplayAnyNode.VALIDATE_INPUTS() is True
+        assert DisplayAnyNode.VALIDATE_INPUTS(input="test") is True
+        assert DisplayAnyNode.VALIDATE_INPUTS(input=123, mode="raw value") is True
+
+    def test_display_raw_value_string(self):
+        """Test displaying raw string value."""
+        node = DisplayAnyNode()
+        result = node.display("Hello, World!", "raw value")
+
+        assert "ui" in result
+        assert "text" in result["ui"]
+        assert result["ui"]["text"] == "Hello, World!"
+        assert "result" in result
+        assert result["result"] == ("Hello, World!",)
+
+    def test_display_raw_value_number(self):
+        """Test displaying raw number value."""
+        node = DisplayAnyNode()
+        result = node.display(42, "raw value")
+
+        assert result["ui"]["text"] == "42"
+        assert result["result"] == ("42",)
+
+    def test_display_raw_value_list(self):
+        """Test displaying raw list value."""
+        node = DisplayAnyNode()
+        test_list = [1, 2, 3, "test"]
+        result = node.display(test_list, "raw value")
+
+        assert result["ui"]["text"] == str(test_list)
+        assert result["result"] == (str(test_list),)
+
+    def test_display_raw_value_dict(self):
+        """Test displaying raw dictionary value."""
+        node = DisplayAnyNode()
+        test_dict = {"key": "value", "number": 123}
+        result = node.display(test_dict, "raw value")
+
+        assert result["ui"]["text"] == str(test_dict)
+        assert result["result"] == (str(test_dict),)
+
+    def test_display_tensor_shape_numpy(self):
+        """Test displaying numpy tensor shape."""
+        node = DisplayAnyNode()
+        tensor = np.random.rand(4, 3, 224, 224)
+        result = node.display(tensor, "tensor shape")
+
+        assert result["ui"]["text"] == "[[4, 3, 224, 224]]"
+        assert result["result"] == ("[[4, 3, 224, 224]]",)
+
+    @pytest.mark.skipif(not torch, reason="PyTorch not installed")
+    def test_display_tensor_shape_torch(self):
+        """Test displaying PyTorch tensor shape."""
+        node = DisplayAnyNode()
+        tensor = torch.randn(2, 10, 512, 512)
+        result = node.display(tensor, "tensor shape")
+
+        assert result["ui"]["text"] == "[[2, 10, 512, 512]]"
+        assert result["result"] == ("[[2, 10, 512, 512]]",)
+
+    def test_display_nested_tensors(self):
+        """Test displaying shapes from nested structure with tensors."""
+        node = DisplayAnyNode()
+        nested_data = {
+            "images": np.random.rand(1, 3, 256, 256),
+            "masks": [
+                np.random.rand(256, 256),
+                np.random.rand(256, 256, 1),
+            ],
+            "metadata": {"info": "test", "tensor": np.random.rand(10)},
+        }
+        result = node.display(nested_data, "tensor shape")
+
+        expected = "[[1, 3, 256, 256], [256, 256], [256, 256, 1], [10]]"
+        assert result["ui"]["text"] == expected
+        assert result["result"] == (expected,)
+
+    def test_display_no_tensors(self):
+        """Test displaying when no tensors are present."""
+        node = DisplayAnyNode()
+        data = {"text": "hello", "number": 42, "list": [1, 2, 3]}
+        result = node.display(data, "tensor shape")
+
+        assert result["ui"]["text"] == "No tensors found in input"
+        assert result["result"] == ("No tensors found in input",)
+
+    def test_invalid_mode_defaults_to_raw(self):
+        """Test that invalid mode defaults to raw value."""
+        node = DisplayAnyNode()
+        result = node.display("test", "invalid_mode")
+
+        assert result["ui"]["text"] == "test"
+        assert result["result"] == ("test",)
+
+
+class TestDisplayAnyLogic:
+    """Test cases for DisplayAny logic functions."""
+
+    def test_get_tensor_shapes_single(self):
+        """Test getting shape from single tensor."""
+        tensor = np.random.rand(3, 224, 224)
+        shapes = get_tensor_shapes(tensor)
+
+        assert len(shapes) == 1
+        assert shapes[0] == [3, 224, 224]
+
+    def test_get_tensor_shapes_nested_dict(self):
+        """Test getting shapes from nested dictionary."""
+        data = {
+            "level1": {
+                "tensor1": np.random.rand(10, 20),
+                "level2": {"tensor2": np.random.rand(5, 5, 5)},
+            }
+        }
+        shapes = get_tensor_shapes(data)
+
+        assert len(shapes) == 2
+        assert [10, 20] in shapes
+        assert [5, 5, 5] in shapes
+
+    def test_get_tensor_shapes_nested_list(self):
+        """Test getting shapes from nested list."""
+        data = [
+            np.random.rand(1, 2, 3),
+            [np.random.rand(4, 5), np.random.rand(6, 7, 8)],
+            "not a tensor",
+        ]
+        shapes = get_tensor_shapes(data)
+
+        assert len(shapes) == 3
+        assert [1, 2, 3] in shapes
+        assert [4, 5] in shapes
+        assert [6, 7, 8] in shapes
+
+    def test_get_tensor_shapes_tuple(self):
+        """Test getting shapes from tuple."""
+        data = (np.random.rand(2, 2), np.random.rand(3, 3))
+        shapes = get_tensor_shapes(data)
+
+        assert len(shapes) == 2
+        assert [2, 2] in shapes
+        assert [3, 3] in shapes
+
+    def test_format_display_value_raw(self):
+        """Test formatting for raw value display."""
+        result = format_display_value({"key": "value"}, "raw value")
+        assert result == "{'key': 'value'}"
+
+    def test_format_display_value_tensor_shape(self):
+        """Test formatting for tensor shape display."""
+        tensor = np.random.rand(10, 10)
+        result = format_display_value(tensor, "tensor shape")
+        assert result == "[[10, 10]]"
+
+    def test_format_display_value_no_tensors(self):
+        """Test formatting when no tensors present."""
+        result = format_display_value("just a string", "tensor shape")
+        assert result == "No tensors found in input"
+
+    def test_validate_display_mode(self):
+        """Test display mode validation."""
+        assert validate_display_mode("raw value") is True
+        assert validate_display_mode("tensor shape") is True
+        assert validate_display_mode("invalid") is False
+        assert validate_display_mode("") is False
+        assert validate_display_mode(None) is False
+
+
+class TestDisplayAnyEdgeCases:
+    """Test edge cases for DisplayAny."""
+
+    def test_display_none(self):
+        """Test displaying None value."""
+        node = DisplayAnyNode()
+        result = node.display(None, "raw value")
+        assert result["ui"]["text"] == "None"
+
+    def test_display_empty_list(self):
+        """Test displaying empty list."""
+        node = DisplayAnyNode()
+        result = node.display([], "raw value")
+        assert result["ui"]["text"] == "[]"
+
+    def test_display_empty_dict(self):
+        """Test displaying empty dictionary."""
+        node = DisplayAnyNode()
+        result = node.display({}, "raw value")
+        assert result["ui"]["text"] == "{}"
+
+    def test_display_complex_nested_structure(self):
+        """Test displaying complex nested structure."""
+        node = DisplayAnyNode()
+        complex_data = {
+            "images": [np.random.rand(1, 3, 64, 64) for _ in range(3)],
+            "config": {
+                "steps": 20,
+                "cfg": 7.5,
+                "sampler": "euler",
+                "latents": np.random.rand(1, 4, 32, 32),
+            },
+            "prompts": ["test1", "test2"],
+        }
+        result = node.display(complex_data, "tensor shape")
+
+        # Should find 4 tensors total (3 images + 1 latent)
+        shapes_text = result["ui"]["text"]
+        assert "[1, 3, 64, 64]" in shapes_text
+        assert "[1, 4, 32, 32]" in shapes_text
+
+    def test_display_very_long_string(self):
+        """Test displaying very long string."""
+        node = DisplayAnyNode()
+        long_string = "x" * 10000
+        result = node.display(long_string, "raw value")
+        assert result["ui"]["text"] == long_string
+
+    def test_display_unicode(self):
+        """Test displaying unicode characters."""
+        node = DisplayAnyNode()
+        unicode_text = "Hello 世界 🌍"
+        result = node.display(unicode_text, "raw value")
+        assert result["ui"]["text"] == unicode_text
@@ -0,0 +1,280 @@
+"""Unit tests for Gemini Prompt Engineer node."""
+
+import pytest
+import numpy as np
+from unittest.mock import patch, MagicMock
+from PIL import Image
+
+from kikotools.tools.gemini_prompt import GeminiPromptNode
+from kikotools.tools.gemini_prompt.logic import (
+    tensor_to_pil,
+    image_to_base64,
+    get_api_key,
+    validate_prompt_type,
+    analyze_image_with_gemini,
+)
+from kikotools.tools.gemini_prompt.prompts import (
+    PROMPT_OPTIONS,
+    PROMPT_TEMPLATES,
+    GEMINI_MODELS,
+)
+
+
+class TestGeminiPromptNode:
+    """Test cases for GeminiPromptNode."""
+
+    def test_node_properties(self):
+        """Test node has correct properties."""
+        assert GeminiPromptNode.CATEGORY == "ComfyAssets"
+        assert GeminiPromptNode.FUNCTION == "generate_prompt"
+        assert GeminiPromptNode.RETURN_TYPES == ("STRING", "STRING")
+        assert GeminiPromptNode.RETURN_NAMES == ("prompt", "negative_prompt")
+
+    def test_input_types(self):
+        """Test INPUT_TYPES configuration."""
+        input_types = GeminiPromptNode.INPUT_TYPES()
+
+        # Check required inputs
+        assert "required" in input_types
+        assert "image" in input_types["required"]
+        assert input_types["required"]["image"] == ("IMAGE",)
+        assert "prompt_type" in input_types["required"]
+        assert input_types["required"]["prompt_type"][0] == PROMPT_OPTIONS
+        assert "model" in input_types["required"]
+        assert input_types["required"]["model"][0] == GEMINI_MODELS
+
+        # Check optional inputs
+        assert "optional" in input_types
+        assert "api_key" in input_types["optional"]
+        assert "custom_prompt" in input_types["optional"]
+
+    def test_gemini_models_available(self):
+        """Test that all expected Gemini models are available."""
+        expected_models = [
+            "gemini-1.5-pro",
+            "gemini-1.5-flash",
+            "gemini-1.5-flash-8b",
+            "gemini-pro-vision",
+            "gemini-1.0-pro",
+        ]
+        for model in expected_models:
+            assert model in GEMINI_MODELS
+
+    @patch("kikotools.tools.gemini_prompt.node.analyze_image_with_gemini")
+    def test_generate_prompt_success(self, mock_analyze):
+        """Test successful prompt generation."""
+        # Setup
+        node = GeminiPromptNode()
+        test_image = np.random.rand(1, 512, 512, 3).astype(np.float32)
+        mock_analyze.return_value = ("A beautiful landscape with mountains", None)
+
+        # Execute
+        result = node.generate_prompt(test_image, "flux")
+
+        # Assert
+        assert result == ("A beautiful landscape with mountains", "")
+        mock_analyze.assert_called_once()
+
+    @patch("kikotools.tools.gemini_prompt.node.analyze_image_with_gemini")
+    def test_generate_prompt_sdxl_format(self, mock_analyze):
+        """Test SDXL format with positive and negative prompts."""
+        # Setup
+        node = GeminiPromptNode()
+        test_image = np.random.rand(1, 512, 512, 3).astype(np.float32)
+        mock_analyze.return_value = (
+            "Positive: beautiful landscape, mountains, sunset\nNegative: blurry, low quality",
+            None,
+        )
+
+        # Execute
+        result = node.generate_prompt(test_image, "sdxl")
+
+        # Assert
+        assert result == (
+            "beautiful landscape, mountains, sunset",
+            "blurry, low quality",
+        )
+
+    @patch("kikotools.tools.gemini_prompt.node.analyze_image_with_gemini")
+    def test_generate_prompt_error(self, mock_analyze):
+        """Test error handling in prompt generation."""
+        # Setup
+        node = GeminiPromptNode()
+        test_image = np.random.rand(1, 512, 512, 3).astype(np.float32)
+        mock_analyze.return_value = ("", "API key not found")
+
+        # Execute
+        result = node.generate_prompt(test_image, "flux")
+
+        # Assert
+        assert result[0].startswith("Error:")
+        assert result[1] == ""
+
+    def test_invalid_prompt_type(self):
+        """Test handling of invalid prompt type."""
+        node = GeminiPromptNode()
+        test_image = np.random.rand(1, 512, 512, 3).astype(np.float32)
+
+        with pytest.raises(ValueError, match="Invalid prompt type"):
+            node.generate_prompt(test_image, "invalid_type")
+
+
+class TestGeminiLogic:
+    """Test cases for Gemini logic functions."""
+
+    def test_tensor_to_pil(self):
+        """Test tensor to PIL conversion."""
+        # Test 4D tensor
+        tensor_4d = np.random.rand(1, 64, 64, 3)
+        result = tensor_to_pil(tensor_4d)
+        assert isinstance(result, Image.Image)
+        assert result.size == (64, 64)
+        assert result.mode == "RGB"
+
+        # Test 3D tensor
+        tensor_3d = np.random.rand(64, 64, 3)
+        result = tensor_to_pil(tensor_3d)
+        assert isinstance(result, Image.Image)
+        assert result.size == (64, 64)
+
+    def test_image_to_base64(self):
+        """Test image to base64 conversion."""
+        # Create test image
+        image = Image.new("RGB", (64, 64), color="red")
+
+        # Convert to base64
+        result = image_to_base64(image)
+        assert isinstance(result, str)
+        assert len(result) > 0
+
+        # Test JPEG format
+        result_jpeg = image_to_base64(image, format="JPEG")
+        assert isinstance(result_jpeg, str)
+        assert (
+            result != result_jpeg
+        )  # Different formats should produce different results
+
+    @patch.dict("os.environ", {"GEMINI_API_KEY": "test_key_123"})
+    def test_get_api_key_from_env(self):
+        """Test getting API key from environment."""
+        result = get_api_key()
+        assert result == "test_key_123"
+
+    @patch.dict("os.environ", {}, clear=True)
+    @patch("os.path.exists")
+    @patch("builtins.open")
+    def test_get_api_key_from_config(self, mock_open, mock_exists):
+        """Test getting API key from config file."""
+        # Setup
+        mock_exists.return_value = True
+        mock_open.return_value.__enter__.return_value.read.return_value = (
+            '{"api_key": "config_key_456"}'
+        )
+
+        # Execute
+        result = get_api_key()
+
+        # Assert
+        assert result == "config_key_456"
+
+    def test_validate_prompt_type(self):
+        """Test prompt type validation."""
+        # Valid types
+        for prompt_type in PROMPT_OPTIONS:
+            assert validate_prompt_type(prompt_type) is True
+
+        # Invalid types
+        assert validate_prompt_type("invalid") is False
+        assert validate_prompt_type("") is False
+        assert validate_prompt_type(None) is False
+
+    @patch("google.generativeai.configure")
+    @patch("google.generativeai.GenerativeModel")
+    def test_analyze_image_with_gemini_success(self, mock_model_class, mock_configure):
+        """Test successful image analysis with Gemini."""
+        # Setup
+        mock_model = MagicMock()
+        mock_response = MagicMock()
+        mock_response.text = "A beautiful sunset over mountains"
+        mock_model.generate_content.return_value = mock_response
+        mock_model_class.return_value = mock_model
+
+        test_image = np.random.rand(64, 64, 3)
+
+        # Execute
+        result, error = analyze_image_with_gemini(
+            test_image, "flux", api_key="test_key"
+        )
+
+        # Assert
+        assert result == "A beautiful sunset over mountains"
+        assert error is None
+        mock_configure.assert_called_once_with(api_key="test_key")
+        mock_model.generate_content.assert_called_once()
+
+    def test_analyze_image_no_api_key(self):
+        """Test analysis without API key."""
+        test_image = np.random.rand(64, 64, 3)
+
+        with patch(
+            "kikotools.tools.gemini_prompt.logic.get_api_key", return_value=None
+        ):
+            result, error = analyze_image_with_gemini(test_image, "flux")
+
+        assert result == ""
+        assert "API key not found" in error
+
+    @patch("google.generativeai.configure")
+    @patch("google.generativeai.GenerativeModel")
+    def test_analyze_image_with_custom_prompt(self, mock_model_class, mock_configure):
+        """Test analysis with custom prompt."""
+        # Setup
+        mock_model = MagicMock()
+        mock_response = MagicMock()
+        mock_response.text = "Custom analysis result"
+        mock_model.generate_content.return_value = mock_response
+        mock_model_class.return_value = mock_model
+
+        test_image = np.random.rand(64, 64, 3)
+        custom_prompt = "Analyze this image and describe the colors"
+
+        # Execute
+        result, error = analyze_image_with_gemini(
+            test_image, "flux", api_key="test_key", custom_prompt=custom_prompt
+        )
+
+        # Assert
+        assert result == "Custom analysis result"
+        assert error is None
+
+        # Check that custom prompt was used
+        call_args = mock_model.generate_content.call_args[0][0]
+        assert custom_prompt in call_args
+
+
+class TestPromptTemplates:
+    """Test prompt template configurations."""
+
+    def test_all_prompt_types_have_templates(self):
+        """Test that all prompt options have corresponding templates."""
+        for prompt_type in PROMPT_OPTIONS:
+            assert prompt_type in PROMPT_TEMPLATES
+            assert isinstance(PROMPT_TEMPLATES[prompt_type], str)
+            assert len(PROMPT_TEMPLATES[prompt_type]) > 0
+
+    def test_prompt_template_content(self):
+        """Test that prompt templates contain expected content."""
+        # FLUX prompt should mention FLUX
+        assert "FLUX" in PROMPT_TEMPLATES["flux"]
+
+        # SDXL prompt should mention positive and negative
+        assert "Positive" in PROMPT_TEMPLATES["sdxl"]
+        assert "Negative" in PROMPT_TEMPLATES["sdxl"]
+
+        # Danbooru should mention tags and underscores
+        assert "tag" in PROMPT_TEMPLATES["danbooru"].lower()
+        assert "underscore" in PROMPT_TEMPLATES["danbooru"].lower()
+
+        # Video should mention motion and temporal
+        assert "motion" in PROMPT_TEMPLATES["video"].lower()
+        assert "temporal" in PROMPT_TEMPLATES["video"].lower()
@@ -52,7 +52,9 @@ class TestKikoSaveImageLogic:
        """Test save path generation"""
        with tempfile.TemporaryDirectory() as temp_dir:
            # Test basic path generation
-            full_path, filename = get_save_image_path("test_prefix", 0, ".png", temp_dir)
+            full_path, filename = get_save_image_path(
+                "test_prefix", 0, ".png", temp_dir
+            )

            assert full_path.startswith(temp_dir)
            assert filename.startswith("test_prefix_")
@@ -211,20 +213,28 @@ class TestKikoSaveImageLogic:
        images = torch.rand(1, 32, 32, 3)

        # Quality out of range
-        with pytest.raises(ValueError, match="quality must be an integer between 1 and 100"):
+        with pytest.raises(
+            ValueError, match="quality must be an integer between 1 and 100"
+        ):
            validate_save_inputs(images, "JPEG", 0, 4)

-        with pytest.raises(ValueError, match="quality must be an integer between 1 and 100"):
+        with pytest.raises(
+            ValueError, match="quality must be an integer between 1 and 100"
+        ):
            validate_save_inputs(images, "JPEG", 101, 4)

    def test_validate_save_inputs_invalid_compress_level(self):
        """Test validation with invalid PNG compression level"""
        images = torch.rand(1, 32, 32, 3)

-        with pytest.raises(ValueError, match="png_compress_level must be an integer between 0 and 9"):
+        with pytest.raises(
+            ValueError, match="png_compress_level must be an integer between 0 and 9"
+        ):
            validate_save_inputs(images, "PNG", 90, -1)

-        with pytest.raises(ValueError, match="png_compress_level must be an integer between 0 and 9"):
+        with pytest.raises(
+            ValueError, match="png_compress_level must be an integer between 0 and 9"
+        ):
            validate_save_inputs(images, "PNG", 90, 10)

    def test_save_image_with_format_png(self):
@@ -56,9 +56,13 @@ class TestDimensionExtraction:
        with pytest.raises(ValueError, match="Either image or latent must be provided"):
            extract_dimensions()

-    def test_extract_dimensions_both_inputs_prefers_image(self, mock_image_tensor, mock_latent_tensor):
+    def test_extract_dimensions_both_inputs_prefers_image(
+        self, mock_image_tensor, mock_latent_tensor
+    ):
        """Test that when both inputs provided, image takes precedence"""
-        width, height = extract_dimensions(image=mock_image_tensor, latent=mock_latent_tensor)
+        width, height = extract_dimensions(
+            image=mock_image_tensor, latent=mock_latent_tensor
+        )

        # Should return image dimensions, not latent
        assert width == 832
@@ -89,7 +93,9 @@ class TestScaledDimensionsCalculation:
        original_width, original_height = 832, 1216
        scale_factor = 1.5

-        new_width, new_height = calculate_scaled_dimensions(original_width, original_height, scale_factor)
+        new_width, new_height = calculate_scaled_dimensions(
+            original_width, original_height, scale_factor
+        )

        # Check aspect ratio is preserved (within floating point precision)
        original_ratio = original_width / original_height
@@ -101,7 +107,9 @@ class TestScaledDimensionsCalculation:
        base_width, base_height = 1024, 1024

        for scale_factor in sample_scale_factors:
-            width, height = calculate_scaled_dimensions(base_width, base_height, scale_factor)
+            width, height = calculate_scaled_dimensions(
+                base_width, base_height, scale_factor
+            )

            expected_width = int(base_width * scale_factor)
            expected_height = int(base_height * scale_factor)
@@ -205,7 +213,9 @@ class TestResolutionCalculatorNode:
        """Test node calculation with IMAGE input"""
        node = ResolutionCalculatorNode()

-        width, height = node.calculate_resolution(scale_factor=2.0, image=mock_image_tensor)
+        width, height = node.calculate_resolution(
+            scale_factor=2.0, image=mock_image_tensor
+        )

        # Original: 832x1216, 2x scale = 1664x2432
        assert isinstance(width, int)
@@ -220,7 +230,9 @@ class TestResolutionCalculatorNode:
        """Test node calculation with LATENT input"""
        node = ResolutionCalculatorNode()

-        width, height = node.calculate_resolution(scale_factor=1.5, latent=mock_latent_tensor)
+        width, height = node.calculate_resolution(
+            scale_factor=1.5, latent=mock_latent_tensor
+        )

        # Original: 832x1216, 1.5x scale = 1248x1824
        assert isinstance(width, int)
@@ -238,12 +250,16 @@ class TestResolutionCalculatorNode:
        with pytest.raises(ValueError):
            node.calculate_resolution(scale_factor=2.0)

-    def test_calculate_resolution_with_various_scale_factors(self, mock_image_tensor_square, sample_scale_factors):
+    def test_calculate_resolution_with_various_scale_factors(
+        self, mock_image_tensor_square, sample_scale_factors
+    ):
        """Test calculation with various scale factors"""
        node = ResolutionCalculatorNode()

        for scale_factor in sample_scale_factors:
-            width, height = node.calculate_resolution(scale_factor=scale_factor, image=mock_image_tensor_square)
+            width, height = node.calculate_resolution(
+                scale_factor=scale_factor, image=mock_image_tensor_square
+            )

            # All results should be integers divisible by 8
            assert isinstance(width, int)
@@ -331,7 +331,9 @@ class TestSamplerComboIntegration:

            # Test that recommendations work with the node
            for scheduler in suggestions[:2]:  # Test first 2 suggestions
-                result = node.get_sampler_combo(sampler, scheduler, steps_rec["default"], cfg_rec["default"])
+                result = node.get_sampler_combo(
+                    sampler, scheduler, steps_rec["default"], cfg_rec["default"]
+                )
                assert result[0] == sampler
                assert result[1] == scheduler
                assert result[2] == steps_rec["default"]
@@ -70,7 +70,9 @@ class TestWidthHeightSelectorNode:

        # Test formatted preset if available
        formatted_preset = "832×1216 - 13:19 (1.0MP) - SDXL"
-        result = self.node.get_dimensions(preset=formatted_preset, width=512, height=512)
+        result = self.node.get_dimensions(
+            preset=formatted_preset, width=512, height=512
+        )
        assert result == (832, 1216)

    def test_sdxl_landscape_preset(self):
@@ -81,7 +83,9 @@ class TestWidthHeightSelectorNode:

        # Test formatted preset if available
        formatted_preset = "1216×832 - 19:13 (1.0MP) - SDXL"
-        result = self.node.get_dimensions(preset=formatted_preset, width=512, height=512)
+        result = self.node.get_dimensions(
+            preset=formatted_preset, width=512, height=512
+        )
        assert result == (1216, 832)

    def test_flux_preset(self):
@@ -92,7 +96,9 @@ class TestWidthHeightSelectorNode:

        # Test formatted preset
        formatted_preset = "1920×1080 - 16:9 (2.1MP) - FLUX"
-        result = self.node.get_dimensions(preset=formatted_preset, width=512, height=512)
+        result = self.node.get_dimensions(
+            preset=formatted_preset, width=512, height=512
+        )
        assert result == (1920, 1080)

    def test_ultra_wide_preset(self):
@@ -103,7 +109,9 @@ class TestWidthHeightSelectorNode:

        # Test formatted preset if available
        formatted_preset = "2560×1080 - 64:27 (2.8MP) - Ultra-Wide"
-        result = self.node.get_dimensions(preset=formatted_preset, width=512, height=512)
+        result = self.node.get_dimensions(
+            preset=formatted_preset, width=512, height=512
+        )
        assert result == (2560, 1080)

    def test_all_presets_available(self):
@@ -135,7 +143,9 @@ class TestWidthHeightSelectorNode:
    def test_invalid_preset_fallback(self):
        """Test handling of invalid preset."""
        # Should fall back to custom dimensions
-        result = self.node.get_dimensions(preset="invalid_preset", width=800, height=600)
+        result = self.node.get_dimensions(
+            preset="invalid_preset", width=800, height=600
+        )
        assert result == (800, 600)


@@ -258,14 +268,18 @@ class TestPresetDefinitions:
        for preset_dict in [SDXL_PRESETS, FLUX_PRESETS, ULTRA_WIDE_PRESETS]:
            for preset_name, (width, height) in preset_dict.items():
                assert width % 8 == 0, f"{preset_name} width {width} not divisible by 8"
-                assert height % 8 == 0, f"{preset_name} height {height} not divisible by 8"
+                assert (
+                    height % 8 == 0
+                ), f"{preset_name} height {height} not divisible by 8"

    def test_preset_dimensions_within_limits(self):
        """Test that all preset dimensions are within acceptable limits."""
        for preset_dict in [SDXL_PRESETS, FLUX_PRESETS, ULTRA_WIDE_PRESETS]:
            for preset_name, (width, height) in preset_dict.items():
                assert 64 <= width <= 8192, f"{preset_name} width {width} out of range"
-                assert 64 <= height <= 8192, f"{preset_name} height {height} out of range"
+                assert (
+                    64 <= height <= 8192
+                ), f"{preset_name} height {height} out of range"


 class TestEdgeCases:
@@ -467,7 +481,9 @@ class TestFormattedPresets:

        for formatted_preset, expected in test_cases:
            result = self.node._extract_preset_name(formatted_preset)
-            assert result == expected, f"Expected {expected}, got {result} for input {formatted_preset}"
+            assert (
+                result == expected
+            ), f"Expected {expected}, got {result} for input {formatted_preset}"

    def test_formatted_preset_dimensions(self):
        """Test that formatted presets return correct dimensions."""
@@ -509,22 +525,34 @@ class TestFormattedPresets:
    def test_formatted_preset_metadata_accuracy(self):
        """Test that formatted presets contain accurate metadata."""
        input_types = self.node.INPUT_TYPES()
-        formatted_presets = [opt for opt in input_types["required"]["preset"][0] if " - " in opt]
+        formatted_presets = [
+            opt for opt in input_types["required"]["preset"][0] if " - " in opt
+        ]

        for formatted_preset in formatted_presets:
            # Extract components
            parts = formatted_preset.split(" - ")
-            assert len(parts) == 3, f"Formatted preset should have 3 parts: {formatted_preset}"
+            assert (
+                len(parts) == 3
+            ), f"Formatted preset should have 3 parts: {formatted_preset}"

            resolution = parts[0]
            aspect_and_mp = parts[1]
            model_group = parts[2]

            # Verify resolution exists in metadata
-            assert resolution in PRESET_METADATA, f"Resolution {resolution} not in metadata"
+            assert (
+                resolution in PRESET_METADATA
+            ), f"Resolution {resolution} not in metadata"

            # Verify metadata matches format
            metadata = PRESET_METADATA[resolution]
-            assert metadata.model_group == model_group, f"Model group mismatch for {resolution}"
-            assert metadata.aspect_ratio in aspect_and_mp, f"Aspect ratio not in {aspect_and_mp}"
-            assert f"{metadata.megapixels:.1f}MP" in aspect_and_mp, f"Megapixels not in {aspect_and_mp}"
+            assert (
+                metadata.model_group == model_group
+            ), f"Model group mismatch for {resolution}"
+            assert (
+                metadata.aspect_ratio in aspect_and_mp
+            ), f"Aspect ratio not in {aspect_and_mp}"
+            assert (
+                f"{metadata.megapixels:.1f}MP" in aspect_and_mp
+            ), f"Megapixels not in {aspect_and_mp}"
@@ -0,0 +1,595 @@
+import { app } from "../../../scripts/app.js";
+import { ComfyWidgets } from "../../../scripts/widgets.js";
+
+app.registerExtension({
+    name: "ComfyAssets.DisplayText",
+    async beforeRegisterNodeDef(nodeType, nodeData, app) {
+        if (nodeData.name === "DisplayText") {
+            const onExecuted = nodeType.prototype.onExecuted;
+            
+            nodeType.prototype.onExecuted = function(message) {
+                onExecuted?.apply(this, arguments);
+                
+                if (message?.text) {
+                    // Create or update the text widget
+                    this.updateTextDisplay(message.text[0]);
+                }
+            };
+            
+            nodeType.prototype.updateTextDisplay = function(text) {
+                // Remove existing text widget if any
+                const existingWidget = this.widgets?.find(w => w.name === "displayed_text");
+                if (existingWidget) {
+                    const index = this.widgets.indexOf(existingWidget);
+                    this.widgets.splice(index, 1);
+                }
+                
+                // Parse the text to detect positive/negative prompt format
+                function parsePrompts(text) {
+                    const posMatch = text.match(/Positive prompt:\s*([\s\S]*?)(?=Negative prompt:|$)/i);
+                    const negMatch = text.match(/Negative prompt:\s*([\s\S]*?)(?=\*\*|$)/i);
+                    
+                    if (posMatch && negMatch) {
+                        // Extract just the prompt content, stopping at the first ** marker
+                        let positiveText = posMatch[1].trim();
+                        let negativeText = negMatch[1].trim();
+                        
+                        // Remove any trailing ** markers and everything after them
+                        const posEndIndex = positiveText.indexOf('**');
+                        if (posEndIndex > 0) {
+                            positiveText = positiveText.substring(0, posEndIndex).trim();
+                        }
+                        
+                        const negEndIndex = negativeText.indexOf('**');
+                        if (negEndIndex > 0) {
+                            negativeText = negativeText.substring(0, negEndIndex).trim();
+                        }
+                        
+                        return {
+                            type: 'prompts',
+                            positive: positiveText,
+                            negative: negativeText
+                        };
+                    }
+                    
+                    return {
+                        type: 'text',
+                        content: text
+                    };
+                }
+                
+                const parsedContent = parsePrompts(text);
+                
+                // Create custom widget for text display
+                const widget = {
+                    type: "custom_text_display",
+                    name: "displayed_text",
+                    size: [this.size[0] - 20, this.size[1] - 60], // Adjust for node chrome
+                    parsedContent: parsedContent,
+                    scrollOffset: 0,
+                    posScrollOffset: 0,
+                    negScrollOffset: 0,
+                    
+                    draw: function(ctx, node, widget_width, y, H) {
+                        const margin = 10;
+                        const padding = 10;
+                        const lineHeight = 20;
+                        const buttonHeight = 30;
+                        const buttonWidth = 90;
+                        
+                        // Use the actual widget height from node size
+                        const availableHeight = node.size[1] - 60; // Account for node header and margins
+                        this.size[1] = Math.max(100, availableHeight);
+                        
+                        // Calculate available width for text
+                        const availableWidth = widget_width - margin * 2 - padding * 2;
+                        
+                        // Word wrap function with better performance
+                        function wrapText(text, maxWidth) {
+                            const words = text.split(' ');
+                            const lines = [];
+                            let currentLine = '';
+                            
+                            ctx.font = "14px monospace";
+                            
+                            for (const word of words) {
+                                const testLine = currentLine + (currentLine ? ' ' : '') + word;
+                                const metrics = ctx.measureText(testLine);
+                                
+                                if (metrics.width > maxWidth && currentLine) {
+                                    lines.push(currentLine);
+                                    currentLine = word;
+                                } else {
+                                    currentLine = testLine;
+                                }
+                            }
+                            
+                            if (currentLine) {
+                                lines.push(currentLine);
+                            }
+                            
+                            return lines.length > 0 ? lines : [''];
+                        }
+                        
+                        // Draw background
+                        ctx.fillStyle = "#2a2a2a";
+                        ctx.fillRect(margin, y, widget_width - margin * 2, this.size[1]);
+                        
+                        // Draw border
+                        ctx.strokeStyle = "#444";
+                        ctx.strokeRect(margin, y, widget_width - margin * 2, this.size[1]);
+                        
+                        if (this.parsedContent.type === 'prompts') {
+                            // Simple split view for positive/negative prompts
+                            const headerHeight = 25;
+                            const buttonAreaHeight = buttonHeight + padding;
+                            const totalTextHeight = this.size[1] - buttonAreaHeight;
+                            const halfHeight = totalTextHeight / 2;
+                            
+                            // Draw positive prompt header
+                            ctx.fillStyle = "#3a3a3a";
+                            ctx.fillRect(margin + 1, y + 1, widget_width - margin * 2 - 2, headerHeight);
+                            ctx.fillStyle = "#8f8";
+                            ctx.font = "12px sans-serif";
+                            ctx.fillText("✓ Positive Prompt", margin + padding, y + headerHeight - 7);
+                            
+                            // Positive prompt text area
+                            const posTextY = y + headerHeight;
+                            const posTextHeight = halfHeight - headerHeight;
+                            ctx.fillStyle = "#1e1e1e";
+                            ctx.fillRect(margin + 1, posTextY, widget_width - margin * 2 - 2, posTextHeight);
+                            
+                            // Draw separator
+                            const separatorY = y + halfHeight;
+                            ctx.strokeStyle = "#555";
+                            ctx.beginPath();
+                            ctx.moveTo(margin, separatorY);
+                            ctx.lineTo(widget_width - margin, separatorY);
+                            ctx.stroke();
+                            
+                            // Draw negative prompt header
+                            ctx.fillStyle = "#3a3a3a";
+                            ctx.fillRect(margin + 1, separatorY + 1, widget_width - margin * 2 - 2, headerHeight);
+                            ctx.fillStyle = "#f88";
+                            ctx.font = "12px sans-serif";
+                            ctx.fillText("✗ Negative Prompt", margin + padding, separatorY + headerHeight - 7);
+                            
+                            // Negative prompt text area
+                            const negTextY = separatorY + headerHeight;
+                            const negTextHeight = halfHeight - headerHeight;
+                            ctx.fillStyle = "#1e1e1e";
+                            ctx.fillRect(margin + 1, negTextY, widget_width - margin * 2 - 2, negTextHeight);
+                            
+                            // Draw text for both sections
+                            ctx.font = "14px monospace";
+                            ctx.fillStyle = "#ddd";
+                            
+                            // Wrap text for both prompts
+                            const posLines = [];
+                            const posParagraphs = this.parsedContent.positive.split('\n');
+                            for (const para of posParagraphs) {
+                                if (para.trim() === '') {
+                                    posLines.push('');
+                                } else {
+                                    posLines.push(...wrapText(para, availableWidth - 10));
+                                }
+                            }
+                            
+                            const negLines = [];
+                            const negParagraphs = this.parsedContent.negative.split('\n');
+                            for (const para of negParagraphs) {
+                                if (para.trim() === '') {
+                                    negLines.push('');
+                                } else {
+                                    negLines.push(...wrapText(para, availableWidth - 10));
+                                }
+                            }
+                            
+                            // Draw positive prompt text with clipping
+                            ctx.save();
+                            ctx.beginPath();
+                            ctx.rect(margin + padding, posTextY + padding, availableWidth - 10, posTextHeight - padding * 2);
+                            ctx.clip();
+                            
+                            let currentY = posTextY + padding + lineHeight - 5;
+                            const posVisibleLines = Math.floor((posTextHeight - padding * 2) / lineHeight);
+                            const posStartLine = Math.floor(this.posScrollOffset);
+                            const posEndLine = Math.min(posStartLine + posVisibleLines, posLines.length);
+                            
+                            for (let i = posStartLine; i < posEndLine; i++) {
+                                ctx.fillText(posLines[i], margin + padding, currentY);
+                                currentY += lineHeight;
+                            }
+                            ctx.restore();
+                            
+                            // Draw positive scroll indicator if needed
+                            if (posLines.length > posVisibleLines) {
+                                const scrollBarWidth = 6;
+                                const scrollBarX = widget_width - margin - scrollBarWidth - 2;
+                                const scrollBarHeight = posTextHeight - padding * 2;
+                                const maxScroll = posLines.length - posVisibleLines;
+                                const scrollRatio = this.posScrollOffset / maxScroll;
+                                const thumbHeight = Math.max(20, (posVisibleLines / posLines.length) * scrollBarHeight);
+                                const thumbY = posTextY + padding + scrollRatio * (scrollBarHeight - thumbHeight);
+                                
+                                ctx.fillStyle = "#333";
+                                ctx.fillRect(scrollBarX, posTextY + padding, scrollBarWidth, scrollBarHeight);
+                                ctx.fillStyle = "#666";
+                                ctx.fillRect(scrollBarX, thumbY, scrollBarWidth, thumbHeight);
+                            }
+                            
+                            // Draw negative prompt text with clipping
+                            ctx.save();
+                            ctx.beginPath();
+                            ctx.rect(margin + padding, negTextY + padding, availableWidth - 10, negTextHeight - padding * 2);
+                            ctx.clip();
+                            
+                            ctx.fillStyle = "#ddd";
+                            currentY = negTextY + padding + lineHeight - 5;
+                            const negVisibleLines = Math.floor((negTextHeight - padding * 2) / lineHeight);
+                            const negStartLine = Math.floor(this.negScrollOffset);
+                            const negEndLine = Math.min(negStartLine + negVisibleLines, negLines.length);
+                            
+                            for (let i = negStartLine; i < negEndLine; i++) {
+                                ctx.fillText(negLines[i], margin + padding, currentY);
+                                currentY += lineHeight;
+                            }
+                            ctx.restore();
+                            
+                            // Draw negative scroll indicator if needed
+                            if (negLines.length > negVisibleLines) {
+                                const scrollBarWidth = 6;
+                                const scrollBarX = widget_width - margin - scrollBarWidth - 2;
+                                const scrollBarHeight = negTextHeight - padding * 2;
+                                const maxScroll = negLines.length - negVisibleLines;
+                                const scrollRatio = this.negScrollOffset / maxScroll;
+                                const thumbHeight = Math.max(20, (negVisibleLines / negLines.length) * scrollBarHeight);
+                                const thumbY = negTextY + padding + scrollRatio * (scrollBarHeight - thumbHeight);
+                                
+                                ctx.fillStyle = "#333";
+                                ctx.fillRect(scrollBarX, negTextY + padding, scrollBarWidth, scrollBarHeight);
+                                ctx.fillStyle = "#666";
+                                ctx.fillRect(scrollBarX, thumbY, scrollBarWidth, thumbHeight);
+                            }
+                            
+                            // Draw copy buttons
+                            const buttonY = y + this.size[1] - buttonHeight - padding / 2;
+                            const halfWidth = (widget_width - margin * 2) / 2;
+                            
+                            // Positive copy button
+                            const posButtonX = margin + halfWidth / 2 - buttonWidth / 2;
+                            ctx.fillStyle = this.posCopyHovered ? "#5a5a5a" : "#4a4a4a";
+                            ctx.fillRect(posButtonX, buttonY, buttonWidth, buttonHeight);
+                            ctx.strokeStyle = "#666";
+                            ctx.strokeRect(posButtonX, buttonY, buttonWidth, buttonHeight);
+                            
+                            ctx.fillStyle = "#fff";
+                            ctx.font = "12px sans-serif";
+                            ctx.textAlign = "center";
+                            ctx.textBaseline = "middle";
+                            ctx.fillText(this.posCopySuccess ? "✓ Copied!" : "📋 Positive", posButtonX + buttonWidth/2, buttonY + buttonHeight/2);
+                            
+                            // Negative copy button
+                            const negButtonX = margin + halfWidth + halfWidth / 2 - buttonWidth / 2;
+                            ctx.fillStyle = this.negCopyHovered ? "#5a5a5a" : "#4a4a4a";
+                            ctx.fillRect(negButtonX, buttonY, buttonWidth, buttonHeight);
+                            ctx.strokeStyle = "#666";
+                            ctx.strokeRect(negButtonX, buttonY, buttonWidth, buttonHeight);
+                            
+                            // Ensure text color and alignment are set
+                            ctx.fillStyle = "#fff";
+                            ctx.font = "12px sans-serif";
+                            ctx.textAlign = "center";
+                            ctx.textBaseline = "middle";
+                            ctx.fillText(this.negCopySuccess ? "✓ Copied!" : "📋 Negative", negButtonX + buttonWidth/2, buttonY + buttonHeight/2);
+                            
+                            ctx.textAlign = "left";
+                            ctx.textBaseline = "alphabetic";
+                            
+                        } else {
+                            // Regular text display
+                            const textAreaHeight = this.size[1] - buttonHeight - padding;
+                            
+                            // Draw text area background
+                            ctx.fillStyle = "#1e1e1e";
+                            ctx.fillRect(margin + 1, y + 1, widget_width - margin * 2 - 2, textAreaHeight);
+                            
+                            // Process text
+                            ctx.font = "14px monospace";
+                            const paragraphs = this.parsedContent.content.split('\n');
+                            const allLines = [];
+                            
+                            for (const paragraph of paragraphs) {
+                                if (paragraph.trim() === '') {
+                                    allLines.push('');
+                                } else {
+                                    const wrappedLines = wrapText(paragraph, availableWidth);
+                                    allLines.push(...wrappedLines);
+                                }
+                            }
+                            
+                            // Draw text with clipping
+                            ctx.save();
+                            ctx.beginPath();
+                            ctx.rect(margin + padding, y + padding, availableWidth, textAreaHeight - padding * 2);
+                            ctx.clip();
+                            
+                            const visibleLines = Math.floor((textAreaHeight - padding * 2) / lineHeight);
+                            const maxScroll = Math.max(0, allLines.length - visibleLines);
+                            this.scrollOffset = Math.max(0, Math.min(this.scrollOffset, maxScroll));
+                            
+                            ctx.fillStyle = "#ddd";
+                            let currentY = y + padding + lineHeight - 5 - (this.scrollOffset * lineHeight);
+                            
+                            for (let i = 0; i < allLines.length; i++) {
+                                if (currentY > y && currentY < y + textAreaHeight) {
+                                    ctx.fillText(allLines[i], margin + padding, currentY);
+                                }
+                                currentY += lineHeight;
+                            }
+                            
+                            ctx.restore();
+                            
+                            // Draw scroll indicator if needed
+                            if (allLines.length > visibleLines) {
+                                const scrollBarWidth = 6;
+                                const scrollBarX = widget_width - margin - scrollBarWidth - 2;
+                                const scrollBarHeight = textAreaHeight - 4;
+                                const thumbHeight = Math.max(20, (visibleLines / allLines.length) * scrollBarHeight);
+                                const thumbY = y + 2 + (this.scrollOffset / maxScroll) * (scrollBarHeight - thumbHeight);
+                                
+                                ctx.fillStyle = "#333";
+                                ctx.fillRect(scrollBarX, y + 2, scrollBarWidth, scrollBarHeight);
+                                ctx.fillStyle = "#666";
+                                ctx.fillRect(scrollBarX, thumbY, scrollBarWidth, thumbHeight);
+                            }
+                            
+                            // Draw copy button
+                            const buttonX = widget_width - margin - buttonWidth - padding;
+                            const buttonY = y + textAreaHeight + padding / 2;
+                            
+                            ctx.fillStyle = this.copyButtonHovered ? "#5a5a5a" : "#4a4a4a";
+                            ctx.fillRect(buttonX, buttonY, buttonWidth, buttonHeight);
+                            ctx.strokeStyle = "#666";
+                            ctx.strokeRect(buttonX, buttonY, buttonWidth, buttonHeight);
+                            
+                            ctx.fillStyle = "#fff";
+                            ctx.font = "12px sans-serif";
+                            ctx.textAlign = "center";
+                            ctx.textBaseline = "middle";
+                            ctx.fillText(this.copySuccess ? "✓ Copied!" : "📋 Copy", buttonX + buttonWidth/2, buttonY + buttonHeight/2);
+                            ctx.textAlign = "left";
+                            ctx.textBaseline = "alphabetic";
+                        }
+                        
+                        return this.size[1];
+                    },
+                    
+                    mouse: function(event, pos, node) {
+                        const margin = 10;
+                        const padding = 10;
+                        const buttonWidth = 90;
+                        const buttonHeight = 30;
+                        const lineHeight = 20;
+                        
+                        // Check if mouse is over the widget
+                        const isOver = pos[1] > this.last_y && pos[1] < this.last_y + this.size[1];
+                        if (!isOver) return false;
+                        
+                        if (this.parsedContent.type === 'prompts') {
+                            // Handle split view
+                            const headerHeight = 25;
+                            const buttonAreaHeight = buttonHeight + padding;
+                            const totalTextHeight = this.size[1] - buttonAreaHeight;
+                            const halfHeight = totalTextHeight / 2;
+                            
+                            const posTextY = this.last_y + headerHeight;
+                            const posTextHeight = halfHeight - headerHeight;
+                            const negTextY = this.last_y + halfHeight + headerHeight;
+                            const negTextHeight = halfHeight - headerHeight;
+                            
+                            const buttonY = this.last_y + this.size[1] - buttonHeight - padding / 2;
+                            const halfWidth = (node.size[0] - margin * 2) / 2;
+                            
+                            // Check which section for scrolling
+                            const inPosSection = pos[1] > posTextY && pos[1] < posTextY + posTextHeight;
+                            const inNegSection = pos[1] > negTextY && pos[1] < negTextY + negTextHeight;
+                            
+                            // Handle scrolling
+                            if (event.type === "wheel") {
+                                if (inPosSection) {
+                                    const delta = event.deltaY > 0 ? 1 : -1;
+                                    this.posScrollOffset = (this.posScrollOffset || 0) + delta;
+                                    
+                                    // Calculate max scroll
+                                    const visibleLines = Math.floor((posTextHeight - padding * 2) / lineHeight);
+                                    const totalLines = this.parsedContent.positive.split('\n').length * 2; // Estimate
+                                    const maxScroll = Math.max(0, totalLines - visibleLines);
+                                    this.posScrollOffset = Math.max(0, Math.min(this.posScrollOffset, maxScroll));
+                                    
+                                    node.setDirtyCanvas(true);
+                                    return true;
+                                } else if (inNegSection) {
+                                    const delta = event.deltaY > 0 ? 1 : -1;
+                                    this.negScrollOffset = (this.negScrollOffset || 0) + delta;
+                                    
+                                    // Calculate max scroll
+                                    const visibleLines = Math.floor((negTextHeight - padding * 2) / lineHeight);
+                                    const totalLines = this.parsedContent.negative.split('\n').length * 2; // Estimate
+                                    const maxScroll = Math.max(0, totalLines - visibleLines);
+                                    this.negScrollOffset = Math.max(0, Math.min(this.negScrollOffset, maxScroll));
+                                    
+                                    node.setDirtyCanvas(true);
+                                    return true;
+                                }
+                            }
+                            
+                            // Check button hovers
+                            const posButtonX = margin + halfWidth / 2 - buttonWidth / 2;
+                            const negButtonX = margin + halfWidth + halfWidth / 2 - buttonWidth / 2;
+                            
+                            const oldPosHover = this.posCopyHovered;
+                            const oldNegHover = this.negCopyHovered;
+                            
+                            this.posCopyHovered = pos[0] > posButtonX && pos[0] < posButtonX + buttonWidth &&
+                                                 pos[1] > buttonY && pos[1] < buttonY + buttonHeight;
+                            this.negCopyHovered = pos[0] > negButtonX && pos[0] < negButtonX + buttonWidth &&
+                                                 pos[1] > buttonY && pos[1] < buttonY + buttonHeight;
+                            
+                            if (oldPosHover !== this.posCopyHovered || oldNegHover !== this.negCopyHovered) {
+                                node.setDirtyCanvas(true);
+                            }
+                            
+                            // Handle button clicks
+                            if (event.type === "pointerdown") {
+                                if (this.posCopyHovered) {
+                                    this.copyToClipboard(this.parsedContent.positive, 'positive');
+                                    return true;
+                                } else if (this.negCopyHovered) {
+                                    this.copyToClipboard(this.parsedContent.negative, 'negative');
+                                    return true;
+                                }
+                            }
+                        } else {
+                            // Regular text handling
+                            const textAreaHeight = this.size[1] - buttonHeight - padding;
+                            const buttonX = node.size[0] - margin - buttonWidth - padding;
+                            const buttonY = this.last_y + textAreaHeight + padding / 2;
+                            
+                            // Handle scrolling
+                            if (event.type === "wheel" && pos[1] < this.last_y + textAreaHeight) {
+                                const delta = event.deltaY > 0 ? 1 : -1;
+                                this.scrollOffset = (this.scrollOffset || 0) + delta;
+                                
+                                const visibleLines = Math.floor((textAreaHeight - padding * 2) / lineHeight);
+                                const totalLines = this.parsedContent.content.split('\n').length * 2; // Estimate
+                                const maxScroll = Math.max(0, totalLines - visibleLines);
+                                this.scrollOffset = Math.max(0, Math.min(this.scrollOffset, maxScroll));
+                                
+                                node.setDirtyCanvas(true);
+                                return true;
+                            }
+                            
+                            // Check button hover
+                            const oldHover = this.copyButtonHovered;
+                            this.copyButtonHovered = pos[0] > buttonX && pos[0] < buttonX + buttonWidth &&
+                                                   pos[1] > buttonY && pos[1] < buttonY + buttonHeight;
+                            
+                            if (oldHover !== this.copyButtonHovered) {
+                                node.setDirtyCanvas(true);
+                            }
+                            
+                            // Handle button click
+                            if (event.type === "pointerdown" && this.copyButtonHovered) {
+                                this.copyToClipboard(this.parsedContent.content, 'regular');
+                                return true;
+                            }
+                        }
+                        
+                        return false;
+                    },
+                    
+                    copyToClipboard: function(text, type) {
+                        const node = this._node;
+                        navigator.clipboard.writeText(text).then(() => {
+                            if (type === 'positive') {
+                                this.posCopySuccess = true;
+                            } else if (type === 'negative') {
+                                this.negCopySuccess = true;
+                            } else {
+                                this.copySuccess = true;
+                            }
+                            node.setDirtyCanvas(true);
+                            
+                            setTimeout(() => {
+                                this.posCopySuccess = false;
+                                this.negCopySuccess = false;
+                                this.copySuccess = false;
+                                node.setDirtyCanvas(true);
+                            }, 1500);
+                        }).catch(err => {
+                            console.error('Failed to copy:', err);
+                            // Fallback copy method
+                            const textArea = document.createElement("textarea");
+                            textArea.value = text;
+                            textArea.style.position = "fixed";
+                            textArea.style.opacity = "0";
+                            document.body.appendChild(textArea);
+                            textArea.select();
+                            try {
+                                document.execCommand('copy');
+                                if (type === 'positive') {
+                                    this.posCopySuccess = true;
+                                } else if (type === 'negative') {
+                                    this.negCopySuccess = true;
+                                } else {
+                                    this.copySuccess = true;
+                                }
+                                node.setDirtyCanvas(true);
+                                setTimeout(() => {
+                                    this.posCopySuccess = false;
+                                    this.negCopySuccess = false;
+                                    this.copySuccess = false;
+                                    node.setDirtyCanvas(true);
+                                }, 1500);
+                            } catch (err) {
+                                console.error('Fallback copy failed:', err);
+                            }
+                            document.body.removeChild(textArea);
+                        });
+                    },
+                    
+                    computeSize: function(width) {
+                        return [width, this.size[1]];
+                    }
+                };
+                
+                // Store reference to node for callbacks
+                widget._node = this;
+                
+                // Store the last y position for mouse detection
+                const originalDraw = widget.draw;
+                widget.draw = function(ctx, node, widget_width, y, H) {
+                    this.last_y = y;
+                    return originalDraw.call(this, ctx, node, widget_width, y, H);
+                };
+                
+                // Add the widget
+                if (!this.widgets) {
+                    this.widgets = [];
+                }
+                this.widgets.push(widget);
+                
+                // Adjust node size to accommodate the widget
+                this.computeSize();
+            };
+            
+            // Handle node resizing
+            const onResize = nodeType.prototype.onResize;
+            nodeType.prototype.onResize = function(size) {
+                onResize?.apply(this, arguments);
+                
+                // Update widget size when node is resized
+                const textWidget = this.widgets?.find(w => w.name === "displayed_text");
+                if (textWidget) {
+                    textWidget.size[0] = size[0] - 20;
+                    textWidget.size[1] = size[1] - 60;
+                    this.setDirtyCanvas(true);
+                }
+            };
+            
+            // Initialize on node creation
+            const onNodeCreated = nodeType.prototype.onNodeCreated;
+            nodeType.prototype.onNodeCreated = function() {
+                onNodeCreated?.apply(this, arguments);
+                
+                // Set default size
+                this.size[0] = Math.max(this.size[0], 350);
+                this.size[1] = Math.max(this.size[1], 300);
+                
+                // Add placeholder text
+                this.updateTextDisplay("Text will appear here after execution...");
+            };
+        }
+    }
+});
@@ -0,0 +1,204 @@
+import { app } from "../../../scripts/app.js";
+import { api } from "../../../scripts/api.js";
+
+app.registerExtension({
+    name: "ComfyAssets.GeminiPrompt",
+    
+    async beforeRegisterNodeDef(nodeType, nodeData, app) {
+        if (nodeData.name === "GeminiPrompt") {
+            // Add visual enhancements to the node
+            const onNodeCreated = nodeType.prototype.onNodeCreated;
+            
+            nodeType.prototype.onNodeCreated = function() {
+                const result = onNodeCreated?.apply(this, arguments);
+                
+                // Store reference to widgets
+                this.promptTypeWidget = this.widgets.find(w => w.name === "prompt_type");
+                this.modelWidget = this.widgets.find(w => w.name === "model");
+                this.apiKeyWidget = this.widgets.find(w => w.name === "api_key");
+                this.customPromptWidget = this.widgets.find(w => w.name === "custom_prompt");
+                
+                // Add helper text button
+                const helpButton = this.addWidget("button", "Help / API Setup", null, () => {
+                    this.showHelpDialog();
+                });
+                
+                // Style the button
+                helpButton.serialize = false;
+                
+                // Add refresh models button
+                const refreshButton = this.addWidget("button", "Refresh Model List", null, () => {
+                    this.refreshModelList();
+                });
+                refreshButton.serialize = false;
+                
+                // Add status indicator
+                this.status = this.addWidget("text", "status", "Ready", () => {}, {
+                    serialize: false
+                });
+                this.status.disabled = true;
+                
+                // Update custom prompt visibility based on selection
+                if (this.promptTypeWidget && this.customPromptWidget) {
+                    const originalCallback = this.promptTypeWidget.callback;
+                    this.promptTypeWidget.callback = (value) => {
+                        if (originalCallback) originalCallback.call(this.promptTypeWidget, value);
+                        this.updateCustomPromptVisibility();
+                    };
+                }
+                
+                return result;
+            };
+            
+            // Add method to show help dialog
+            nodeType.prototype.showHelpDialog = function() {
+                const helpContent = `
+                    <div style="padding: 20px; max-width: 600px;">
+                        <h2>Gemini Prompt Engineer Setup</h2>
+                        
+                        <h3>1. Get API Key</h3>
+                        <p>Get your free API key from: <a href="https://makersuite.google.com/app/apikey" target="_blank">Google AI Studio</a></p>
+                        
+                        <h3>2. Set API Key</h3>
+                        <p>Choose one of these methods:</p>
+                        <ul>
+                            <li><strong>Environment Variable:</strong> Set GEMINI_API_KEY in your system</li>
+                            <li><strong>Config File:</strong> Create gemini_config.json in ComfyUI root with {"api_key": "your-key"}</li>
+                            <li><strong>Node Input:</strong> Enter directly in the api_key field</li>
+                        </ul>
+                        
+                        <h3>3. Install Dependencies</h3>
+                        <code>pip install google-generativeai</code>
+                        
+                        <h3>Prompt Types</h3>
+                        <ul>
+                            <li><strong>FLUX:</strong> Detailed artistic prompts with quality markers</li>
+                            <li><strong>SDXL:</strong> Positive/negative prompt pairs with weights</li>
+                            <li><strong>Danbooru:</strong> Anime-style booru tags</li>
+                            <li><strong>Video:</strong> Motion and temporal descriptions</li>
+                        </ul>
+                        
+                        <h3>Gemini Models</h3>
+                        <ul>
+                            <li><strong>gemini-1.5-flash:</strong> Fast and efficient (recommended for most uses)</li>
+                            <li><strong>gemini-1.5-flash-8b:</strong> Smaller and faster, good for simple prompts</li>
+                            <li><strong>gemini-1.5-pro:</strong> Most capable, best quality results</li>
+                            <li><strong>gemini-1.0-pro:</strong> Previous generation, stable option</li>
+                        </ul>
+                        
+                        <h3>Custom Prompts</h3>
+                        <p>You can override any template by entering your own system prompt in the custom_prompt field.</p>
+                    </div>
+                `;
+                
+                app.ui.dialog.show(helpContent);
+            };
+            
+            // Add method to update custom prompt visibility
+            nodeType.prototype.updateCustomPromptVisibility = function() {
+                // You could implement logic here to show/hide custom prompt based on selection
+                // For now, it's always visible but this method provides extensibility
+            };
+            
+            // Add method to refresh model list
+            nodeType.prototype.refreshModelList = function() {
+                if (this.status) {
+                    this.status.value = "Refreshing models...";
+                }
+                
+                // Set the refresh_models flag
+                const refreshWidget = this.widgets.find(w => w.name === "refresh_models");
+                if (refreshWidget) {
+                    refreshWidget.value = true;
+                }
+                
+                // Show message
+                alert("Model list will refresh on next execution. Make sure API key is set and run the node.");
+                
+                if (this.status) {
+                    setTimeout(() => {
+                        this.status.value = "Ready - Run node to refresh";
+                    }, 2000);
+                }
+            };
+            
+            // Override execute to show status
+            const onExecute = nodeType.prototype.onExecute;
+            nodeType.prototype.onExecute = function() {
+                if (this.status) {
+                    this.status.value = "Processing...";
+                }
+                const result = onExecute?.apply(this, arguments);
+                return result;
+            };
+            
+            // Handle execution feedback
+            const onExecuted = nodeType.prototype.onExecuted;
+            nodeType.prototype.onExecuted = function(message) {
+                const result = onExecuted?.apply(this, arguments);
+                
+                if (this.status) {
+                    // Check if there was an error in the output
+                    const outputs = message.output;
+                    if (outputs && outputs.prompt && outputs.prompt[0] && outputs.prompt[0].startsWith("Error:")) {
+                        this.status.value = "Error - Check output";
+                        this.bgcolor = "#552222";
+                    } else {
+                        this.status.value = "Success!";
+                        this.bgcolor = "#225522";
+                    }
+                    
+                    // Reset color after delay
+                    setTimeout(() => {
+                        this.bgcolor = "";
+                        if (this.status) {
+                            this.status.value = "Ready";
+                        }
+                    }, 3000);
+                }
+                
+                return result;
+            };
+        }
+    },
+    
+    // Add custom styling
+    async setup() {
+        const style = document.createElement("style");
+        style.textContent = `
+            .gemini-prompt-help {
+                background: #1a1a1a;
+                border: 1px solid #444;
+                border-radius: 8px;
+                color: #fff;
+            }
+            
+            .gemini-prompt-help h2 {
+                color: #4285f4;
+                margin-top: 0;
+            }
+            
+            .gemini-prompt-help h3 {
+                color: #8ab4f8;
+                margin-top: 20px;
+            }
+            
+            .gemini-prompt-help code {
+                background: #333;
+                padding: 2px 6px;
+                border-radius: 4px;
+                font-family: monospace;
+            }
+            
+            .gemini-prompt-help a {
+                color: #8ab4f8;
+                text-decoration: none;
+            }
+            
+            .gemini-prompt-help a:hover {
+                text-decoration: underline;
+            }
+        `;
+        document.head.appendChild(style);
+    }
+});
Author	SHA1	Message	Date
VitoandCopilot Autofix powered by AI	34f54e515d	Potential fix for code scanning alert no. 8: Workflow does not contain permissions Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>	2025-08-02 08:38:37 -07:00
Vito	c844abea51	Merge pull request #25 from ComfyAssets/alert-autofix-1 Potential fix for code scanning alert no. 1: Workflow does not contain permissions	2025-08-02 08:22:06 -07:00
VitoandCopilot Autofix powered by AI	404a1efd61	Potential fix for code scanning alert no. 1: Workflow does not contain permissions Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>	2025-08-02 08:14:03 -07:00
Vito	4ae514dacf	Merge pull request #24 from ComfyAssets/alert-autofix-10 Potential fix for code scanning alert no. 10: Workflow does not contain permissions	2025-08-02 08:12:04 -07:00
VitoandCopilot Autofix powered by AI	5efae8eeb8	Potential fix for code scanning alert no. 10: Workflow does not contain permissions Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>	2025-08-02 08:00:10 -07:00
Vito	85288c8fd8	Create SECURITY.md	2025-08-02 07:54:21 -07:00
Vito	7a97f7c2bc	Create CODE_OF_CONDUCT.md	2025-08-02 07:50:25 -07:00
Vito	a4692a286c	Merge pull request #22 from ComfyAssets/dependabot/github_actions/softprops/action-gh-release-2 build(deps): bump softprops/action-gh-release from 1 to 2	2025-08-02 07:48:07 -07:00
Vito	72a3fea3cb	Merge pull request #23 from ComfyAssets/dependabot/github_actions/actions/cache-4 build(deps): bump actions/cache from 3 to 4	2025-08-02 07:47:44 -07:00
Vito	d5d4145a04	Merge pull request #21 from ComfyAssets/dependabot/github_actions/actions/setup-python-5 build(deps): bump actions/setup-python from 4 to 5	2025-08-02 07:46:49 -07:00
dependabot[bot]	0e288dd109	build(deps): bump actions/cache from 3 to 4 Bumps [actions/cache](https://github.com/actions/cache) from 3 to 4. - [Release notes](https://github.com/actions/cache/releases) - [Changelog](https://github.com/actions/cache/blob/main/RELEASES.md) - [Commits](https://github.com/actions/cache/compare/v3...v4) --- updated-dependencies: - dependency-name: actions/cache dependency-version: '4' dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] <support@github.com>	2025-08-02 14:43:46 +00:00
dependabot[bot]	c4882f894e	build(deps): bump softprops/action-gh-release from 1 to 2 Bumps [softprops/action-gh-release](https://github.com/softprops/action-gh-release) from 1 to 2. - [Release notes](https://github.com/softprops/action-gh-release/releases) - [Changelog](https://github.com/softprops/action-gh-release/blob/master/CHANGELOG.md) - [Commits](https://github.com/softprops/action-gh-release/compare/v1...v2) --- updated-dependencies: - dependency-name: softprops/action-gh-release dependency-version: '2' dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] <support@github.com>	2025-08-02 14:43:43 +00:00
dependabot[bot]	6cbe6e5ae6	build(deps): bump actions/setup-python from 4 to 5 Bumps [actions/setup-python](https://github.com/actions/setup-python) from 4 to 5. - [Release notes](https://github.com/actions/setup-python/releases) - [Commits](https://github.com/actions/setup-python/compare/v4...v5) --- updated-dependencies: - dependency-name: actions/setup-python dependency-version: '5' dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] <support@github.com>	2025-08-02 14:43:40 +00:00
Vito Sansevero	df20afb83e	style(dependabot): fix indentation in config file	2025-08-02 07:42:56 -07:00
Vito	7d63e11e18	Create dependabot.yml	2025-08-02 07:40:43 -07:00
Vito	a8364b5c57	Merge pull request #20 from ComfyAssets/feature/add-tools-toc docs: add tools table of contents to README	2025-08-02 07:35:13 -07:00
Vito Sansevero	332a74225d	docs: add tools table of contents to README - Add comprehensive TOC table under Current Tools section - Include tool names with emojis as clickable links - Add brief descriptions for each tool - Categorize tools by functionality (Image Processing, Debugging, etc.) - Improve navigation and tool discovery for users	2025-08-02 07:31:06 -07:00
Vito	d757b623d6	Merge pull request #19 from ComfyAssets/feature/add-readme-screenshots docs: add screenshots and complete documentation for all nodes	2025-08-02 07:24:25 -07:00
Vito Sansevero	64e844ec42	style: fix code formatting with black - Add missing newlines at end of files - Fix whitespace and indentation issues - Format long function calls properly	2025-08-02 07:20:40 -07:00
Vito Sansevero	3ed188d63f	docs: add screenshots and complete documentation for all nodes - Add PNG screenshots for 7 nodes in README.md - Create missing documentation files (display_text.md, kiko_save_image.md) - Update gemini_prompt.md with new features (model refresh, enhanced SDXL) - Add missing example workflow JSON files for 5 nodes - Include Display Any and Image to Multiple Of nodes in README - Update node count from 8 to 10 in stats section	2025-08-02 07:03:46 -07:00
Vito	b9cc9f295d	Merge pull request #18 from ComfyAssets/feature/display-text-and-gemini-improvements feat: add Display Text node with smart formatting and enhance Gemini …	2025-08-01 21:26:54 -07:00
Vito Sansevero	271cd020c1	merge: resolve conflicts with main branch model management improvements	2025-08-01 16:35:39 -07:00
Vito Sansevero	e34807855a	feat: add Display Text node with smart formatting and enhance Gemini with model refresh Display Text improvements: - Add new DisplayText node with intelligent prompt detection and split view - Implement text wrapping that reflows when node is resized - Add scrollable content with mouse wheel support and visual indicators - Include always-visible copy button with visual feedback for easy prompt copying - Auto-detect SDXL-style prompts and display in side-by-side format - Strip prompt labels when copying for direct use in workflows Gemini model refresh functionality: - Add refresh button to fetch latest available Gemini models dynamically - Implement model caching system with persistent storage - Support for Gemini 2.0 and 2.5 models with automatic detection - Enhanced SDXL prompt template with improved layered structure - Better error handling and status feedback for model operations Documentation and version updates: - Update README with comprehensive Display Text and Gemini feature descriptions - Add detailed usage examples and workflow patterns - Bump version to 1.0.9 in pyproject.toml - Update stats to reflect 8 total nodes and new AI integration features	2025-08-01 14:57:56 -07:00
Vito	d32e18f844	Merge pull request #17 from ComfyAssets/feature/gemini-dynamic-models Feature/gemini dynamic models	2025-08-01 13:36:04 -07:00
Vito Sansevero	228b74ae5e	chore: add flake8 complexity exceptions for Gemini module	2025-08-01 13:30:38 -07:00
Vito Sansevero	6197b482df	feat: implement dynamic model fetching for Gemini node - Add dynamic model fetching with 24-hour caching - Update prompt templates based on 2025 best practices: - FLUX: Natural language descriptions - SDXL: Simplified with natural language support - Danbooru: Strict tagging conventions - Video: Optimized for WAN 2.2 - Add cache file to .gitignore - Handle missing API key gracefully on initial load	2025-08-01 13:30:31 -07:00
Vito Sansevero	f62129afda	fix: update pre-commit config to use line-length 88 - Update black line-length from 127 to 88 to match pyproject.toml - Update flake8 max-line-length from 127 to 88 for consistency - Remove broken pre-commit hook that was referencing non-existent pyenv	2025-08-01 11:02:44 -07:00
Vito Sansevero	8d5065c975	chore: bump version to 1.0.8 in pyproject.toml	2025-08-01 10:58:57 -07:00
Vito	2d27c32bfd	Merge pull request #16 from ComfyAssets/feature/display-any Feature/display any	2025-08-01 10:51:23 -07:00
Vito Sansevero	3ecab5ac08	fix: implement proper AnyType class for wildcard input matching - Add AnyType class that inherits from str and overrides __ne__ to always return False - This matches ComfyUI's type checking system for wildcard inputs - Based on implementation from ComfyUI_essentials - Add comprehensive tests for AnyType behavior - Fixes type mismatch errors when connecting any node type	2025-08-01 10:47:20 -07:00
Vito Sansevero	70592114f9	fix: correct wildcard input type syntax for DisplayAny node - Change from ('', {}) to ('') for proper ComfyUI wildcard type - Update test to match the corrected syntax - Fixes 'Return type mismatch' error when connecting nodes	2025-08-01 10:47:20 -07:00
Vito Sansevero	407fc4ca7b	feat: add DisplayAny node for debugging and inspection - Universal input acceptance for any data type - Two display modes: raw value and tensor shape - Extracts tensor shapes from nested structures - Comprehensive unit tests with 100% coverage - Full documentation with usage examples - OUTPUT_NODE for UI display functionality	2025-08-01 10:47:20 -07:00
Vito	cb7d5246f9	Merge pull request #15 from ComfyAssets/chore/housekeeping Chore/housekeeping	2025-08-01 10:31:39 -07:00
Vito	9829fc001d	Merge pull request #14 from ComfyAssets/fix/black-config-main fix: update black line-length to 88 and reformat codebase	2025-08-01 09:50:10 -07:00
Vito Sansevero	e84ec6721c	fix: update black line-length to 88 and reformat codebase - Update pyproject.toml to use black's default line-length of 88 - This matches what the CI workflow expects (black --check without args) - Reformat all Python files to comply with the new line length - This will prevent CI failures due to formatting discrepancies	2025-08-01 09:45:43 -07:00
Vito	80fac8e544	Merge pull request #12 from ComfyAssets/feature/gemini-prompt feat: add Gemini Prompt Engineer node	2025-08-01 09:45:09 -07:00
Vito Sansevero	efc079a95b	fix: reformat with black default settings (88 char) to match CI	2025-08-01 09:41:21 -07:00
Vito Sansevero	bbd239cbd6	fix: apply black formatting with line-length 127 for CI compliance	2025-08-01 09:41:21 -07:00
Vito Sansevero	589fbf3568	fix: remove trailing whitespace in gemini_prompt node.py	2025-08-01 09:41:21 -07:00
Vito Sansevero	c595cabaa0	chore: trigger CI	2025-08-01 09:41:21 -07:00
Vito Sansevero	ca504d5f74	fix: code formatting for Gemini prompt node - Fix missing newlines at end of files - Apply black formatting - Remaining non-critical warnings for long lines in prompts	2025-08-01 09:41:21 -07:00
Vito Sansevero	f559fe220e	feat: add Gemini Prompt Engineer node - Add GeminiPromptNode for AI-powered prompt engineering - Integrates with Google's Gemini API for prompt generation - Includes various prompt templates and generation modes - Add comprehensive tests and documentation - Register node in ComfyAssets category	2025-08-01 09:41:21 -07:00