| --- |
| title: Chronicle Portrait Studio |
| emoji: ⚔️ |
| colorFrom: indigo |
| colorTo: gray |
| sdk: gradio |
| app_file: app.py |
| pinned: false |
| hf_oauth: true |
| --- |
| |
| # RPGPortrait Prompt Builder Pro |
|
|
| RPGPortrait is a Gradio-based web application that helps users build highly detailed prompts and generate character portraits using advanced AI like Gemini, Hugging Face, and Imagen. |
|
|
| ## Features |
| - **25+ Character Parameters**: Deep customization including Identity, Appearance, Equipment, Environment, VFX, and Technical settings. |
| - **🧠 AI Refinement**: Intelligent prompt enhancement using **Gemini (Cloud)**, **Curated Hugging Face Models**, or **Ollama (Local)**. |
| - **🛠️ Externalized Prompts**: Tweak the core AI system instructions by editing `prompts.yaml`. |
| - **🖼️ Multi-Backend Image Gen**: Toggle between **Gemini (Cloud)**, **Hugging Face (Cloud)**, and **ComfyUI (Local)**. |
| - **⚡ Hugging Face Pro Features**: |
| - Curated list of 4 text and 4 image models. |
| - Manual **Inference Provider** support (e.g., `fal-ai`, `black-forest-labs`) to bypass rate limits or use partner backends. |
| - Automated "auto" provider selection by default. |
| - **🔍 Dynamic Model Discovery**: Automatically pings local Ollama and ComfyUI servers to fetch available models and hide unavailable backends. |
| - **Workflow Injection**: Automated prompt, resolution, and seed injection into custom ComfyUI workflows. |
| - **💾 Save & Load**: Export your character configurations as JSON files and import them back to restore your exact selections. |
| - **⚔️ Exotic Arsenal**: Expanded collection of exotic weapons, armor, and accessories (Katanas, Bone Armor, Arcane Plate, etc.). |
| - **🎒 Dual Accessories**: Select up to two different accessories for your character. |
| - **📥 Pro Downloads**: Standard PNG downloads for portraits with friendly filenames. |
| - **Randomization**: Check individual 🎲 boxes to randomize specific features on regeneration. |
| - **🛡️ Robust Error Handling**: AI refinement errors are logged to the console and displayed in the UI status area without polluting your current prompt. |
| - **YAML Data Storage**: Easily add or modify races, classes, backgrounds, and templates in `features.yaml`. |
|
|
| ## Installation |
|
|
| 1. **Clone the repository** (or navigate to the project folder). |
| 2. **Create a virtual environment**: |
| ```bash |
| python -m venv venv |
| ``` |
| 3. **Activate the environment**: |
| - Windows: `.\venv\Scripts\activate` |
| - Linux/Mac: `source venv/bin/activate` |
| 4. **Install dependencies**: |
| ```bash |
| pip install -r requirements.txt |
| ``` |
| 5. **Set up API Keys**: |
| - Create a `.env` file in the root directory. |
| - Add your keys and connection info: |
| ```env |
| GEMINI_API_KEY=your_gemini_key |
| HF_TOKEN=your_huggingface_token # Required for Cloud backends |
| COMFY_HOST=127.0.0.1 |
| COMFY_PORT=8188 |
| OLLAMA_HOST=127.0.0.1 |
| OLLAMA_PORT=11434 |
| ``` |
|
|
| ## Usage |
|
|
| 1. **Run the application**: |
| ```bash |
| python app.py |
| ``` |
| 2. **Access the UI**: Open your browser and navigate to `http://127.0.0.1:7860`. |
| 3. **Build your prompt**: Select features in the left column; the technical prompt updates in real-time. |
| 4. **Refine Prompt**: |
| - Choose a **Refinement Backend** in the configuration panel. |
| - Click **🧠 Refine Prompt** in the right column to polish your description. |
| 5. **Generate Image**: |
| - Select an **Image Generation Backend**. |
| - Click **🖼️ Generate Image** (located directly under the portrait output) to create your character. |
| 6. **Save/Load**: Use the 💾 and 📂 buttons to manage your character library. |
|
|
| ## License |
|
|
| This project is licensed under the [MIT License](LICENSE). |
|
|
