Invoke
Open SourceFree and open-source self-hosted creative engine for AI image generation and editing
工具信息
什么是 Invoke？
Invoke is a free and open-source creative engine for AI-powered image generation and editing. It provides a professional, fully customizable, and private toolkit that runs locally on user hardware, featuring a layer-based canvas, node-based workflows, and support for model training. Built by creatives for creatives, it emphasizes full user control over data, prompts, and creations under an Apache 2.0 license.
核心功能
Unified Canvas
Layer-based canvas editing that supports drawing, painting, sketching, and independent manipulation of layers for seamless scene composition.
Node-based Workflows
Visual graph backend for building complex, reproducible pipelines with custom UI parameters that can be shared and updated easily.
Leading Model Support
Out-of-the-box support for foundational models including Flux, SDXL, and SD 1.5, plus an intuitive Model Manager for checkpoints, LoRAs, Textual Inversions, and ControlNets.
Local and Private Execution
Completely local and self-hosted operation on user hardware so that data, prompts, and creations remain under full user control.
ControlNet Mastery
Extensive ControlNet support for guiding image generations using depth maps, edges, poses, and other conditioning inputs.
Seamless Iteration Tools
Batch generation, prompt wildcards, and high-resolution upscaling available directly inside the application.
Invoke Training
Dedicated user interface for training Textual Inversion and LoRA models on custom styles.
Intuitive Interface
Clean, polished professional-grade interface that prioritizes artwork and places essential tools where expected.
使用场景
- #1
AI Image Generation
Generate images with the latest foundational models while maintaining full local control and privacy.
- #2
Layer-based Image Editing
Compose and refine intricate scenes using a true layer-based canvas with drawing and painting tools.
- #3
Custom Production Pipelines
Build, share, and iterate on complex reproducible workflows via a visual node graph for professional production use.
- #4
Custom Model Training
Train personal LoRA and Textual Inversion models to capture specific styles or subjects.
- #5
Controlled Composition
Guide exact image layouts and structures using ControlNet with depth, edges, poses, and related inputs.
定价方案
Free and open-source under the Apache 2.0 license. Self-hosted and fully customizable. The former official hosted platform has been shut down.
