google-labs-jules[bot]
8e22e3808c
- Added `deleteFile` to `FileService` and `deleteAsset` to `AssetService` to support file deletion. - Implemented cascading deletion in `CharacterService` (delete looks -> delete character image -> delete character). - Updated `GenerationService`, `PoseService`, and `ExpressionService` to delete associated image assets upon deletion. - Added `DELETE /api/generations/:id` endpoint. - Created `DropdownMenu` and `DeleteConfirmDialog` UI components. - Updated `VibeCard` to include an internal `DropdownMenu` driven by a new `actions` prop. - Updated `Characters`, `Poses`, and `Expressions` pages to use the new `VibeCard` `actions` prop for deletion. - Updated `FittingRoom` page to use the `DropdownMenu` and `DeleteConfirmDialog` for deleting looks. - Updated `CreateLookDialog` to enforce single selection for equipment categories. - Added necessary tests adjustments.
Forgery
Your personal AI studio for equipment extraction and character look generation.
About
Forgery is a local-first application designed to help you build a digital wardrobe and generate stunning new looks for your characters. It specializes in two key workflows: extracting equipment from existing images and fitting that equipment onto your characters.
Unlike traditional character generators, Forgery focuses on consistency and customization. You start by uploading a base image for your character, then use the powerful "Fitting Room" to generate new variations (Looks) by mixing and matching extracted equipment, poses, and expressions.
Features
- Equipment Extraction: Analyze images to identify and extract equipment (outfits, weapons, accessories) into your library.
- Look Generation: Generate new images of your character wearing selected equipment.
- Character Management: Organize your characters and their base reference images.
- Fitting Room: The core studio interface for combining characters, equipment, poses, and expressions into new Looks.
- Pose & Expression Control: Fine-tune your generation with a library of poses and facial expressions.
- Local & Private: All data, including your image library and generated results, is stored locally on your machine.
- Flexible AI Integration: seamlessly switch between Google Gemini and OpenAI models for different stages of the extraction and generation pipeline.
Prerequisites
Getting Started
1. Clone the Repository
git clone https://github.com/yourusername/forgery.git
cd forgery
2. Install Dependencies
bun install
3. Initialize the Database
Forgery uses a local SQLite database. Run the following command to set up the schema:
bun run prisma migrate dev
4. Run the Application
Start the development server:
bun run dev
Open your browser and navigate to http://localhost:3000.
Running with Docker
You can also run Forgery using Docker Compose.
docker compose up -d
The application will be available at http://localhost:3000.
Data (database and generated files) will be persisted in the ./data directory on your host machine.
Configuration
Forgery requires API keys for AI generation services (Google Gemini and/or OpenAI).
- Launch the application and go to the Settings page (accessed via the sidebar).
- Enter your Google API Key and/or OpenAI API Key.
- Configure your preferred models for text and image generation.
- (Optional) Customize the "Extraction Flow" to choose specific models for different steps of the asset analysis and generation process.