NextCreator is a visual, node-based workflow tool designed for AI-powered content generation across text, images, and video. It targets engineers, researchers, and power users seeking a unified platform to chain complex AI creation processes, offering a streamlined and flexible approach to multi-modal content production.

How It Works

The core of NextCreator is a drag-and-drop node editor that allows users to visually construct AI content generation pipelines. Users connect various nodes, each representing specific AI models or functionalities (e.g., image generation, LLM text processing, video synthesis, PPT creation), to define a sequential or parallel workflow. This approach simplifies complex AI interactions by abstracting model APIs into a visual interface, enabling rapid prototyping and iteration of content generation strategies.

Quick Start & Requirements

• Installation: Download pre-built binaries from the Releases page: macOS (.dmg) or Windows (.exe).
• Platform: macOS, Windows.
• Prerequisites: For editable PPT export, an OCR service (EasyOCR) and an Inpaint service (IOPaint) are required. These can be configured via public services (http://152.67.202.21:8866 for OCR, http://152.67.202.21:8877 for IOPaint) or recommended local deployment using Docker (docker-compose up -d). Local deployment requires an initial model download of 3-5 minutes.
• Local Development: Requires bun for dependency installation (bun install) and running development (bun run tauri dev) or build (bun run tauri build) commands.
• macOS Security: Users may need to run xattr -rc "/Applications/NextCreator.app" in the terminal to bypass "unverified developer" warnings for unsigned applications.

Highlighted Details

• Node Editor: Features drag-and-drop design, undo/redo, copy/paste, and auto-layout.
• AI Image Generation: Supports models including NanoBanana, Z-Image, Dall-e, GPT-Image, 豆包Image, and Flux (text-to-image, image-to-image).
• AI Video Generation: Integrates with models like Sora, Veo, and Kling.
• LLM Text Generation: Handles multi-modal inputs (text, images, PDFs).
• PPT Workflow: Automates outline and page generation, exporting editable PPTX files.
• Prompt Library: Includes a library of pre-built prompts and supports custom additions.
• Workflow Orchestration: Enables batch parallel execution of workflows.

Maintenance & Community

The project acknowledges inspiration from awesome-nanobanana-pro and banana-prompt-quicker. No specific details regarding active maintainers, sponsorships, or community channels (like Discord/Slack) are provided in the README.

Licensing & Compatibility

The project is licensed under the GNU Affero General Public License v3 (AGPL v3). This strong copyleft license requires that any derivative works, especially those made available over a network, must also be released under the AGPL v3. This may impose significant restrictions on integration with closed-source commercial products.

Limitations & Caveats

The public OCR and Inpaint services provided are subject to performance limitations and availability issues; local deployment is recommended for reliable use. The application is version 0.2.2, suggesting it may still be in active development and potentially subject to breaking changes or incomplete features.