InvokeAI

InvokeAI is a free, open-source image generation application for artists who want to create and edit artwork on their own hardware. Its locally hosted browser interface combines direct canvas work with repeatable generation workflows.

• Canvas editing: Draw, paint and revise images with independently editable layers, brushes, inpainting and outpainting.
• Composition guidance: Use ControlNet with poses, edges or depth maps to guide the structure of a generated image.
• Visual workflows: Build and share node-based generation pipelines, then expose selected controls without requiring users to edit the graph.
• Image iteration: Explore variations with batch generation and prompt wildcards, upscale results, and recall prompts and settings from gallery metadata.
• Model management: Manage checkpoints, LoRAs, Textual Inversions and ControlNets, with support for Flux, SDXL and SD 1.5, plus ckpt, diffusers and some GGUF models.

InvokeAI uses the Apache 2.0 license and runs on Windows, macOS and Linux, with Docker as another self-hosted option. Windows requires Windows 10 or later and an NVIDIA or AMD GPU; Linux also requires an NVIDIA or AMD GPU. macOS requires Apple Silicon and doesn't support Intel Macs.

With local models, generation takes place on the hardware you control. Third-party hosted GPU options include AI Badgr, RunPod and Railway; using those services places the application on external infrastructure. The former official hosted platform is closed.