Logo
Deploy Now

Categories

Self-Hosted AI Machine Learning Creative Tools Stable Diffusion Image Generation Generative Art

Stars

27,923

Forks

2,939

Watchers

205

Developer links

Last Updated: 08-21-2026 11:46 AM (UTC)

InvokeAI

With over 27,500 GitHub stars, 350 contributors, and 220 releases since 2022, InvokeAI delivers an industry-leading creative engine that serves as the foundation for multiple commercial AI art products. The web-based UI supports an extensive model ecosystem including Stable Diffusion 1.5 through 3.5, SDXL, Flux.1 Dev, Flux.1 Schnell, Flux.1 Kontext, Flux.2 Klein 4B and 9B, CogView 4, Z-Image, Anima, and Qwen Image — plus externally-hosted models from OpenAI GPT Image, Google Gemini, BytePlus, and Alibaba Cloud via API key integration. The Unified Canvas provides a fully integrated workspace with in-painting, out-painting, brush tools, layer management, and regional guidance for compositing AI-generated content with existing artwork. The node-based Workflow Editor enables building complex generation pipelines with branching logic, connecting text encoders, VAEs, ControlNets, IP-Adapters, and LoRA weights into reusable graphs. Model management handles automatic downloading from HuggingFace and Civitai with conversion between safetensors, diffusers, and checkpoint formats. The backend runs on Python with CUDA, ROCm, and MPS acceleration supporting NVIDIA, AMD, and Apple Silicon GPUs. Multi-user accounts allow shared access to a single InvokeAI server with per-user galleries and settings. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.

InvokeAI
InvokeAI
InvokeAI
InvokeAI
InvokeAI

Benefits

  • Unified Canvas Creative Workspace
  • Fully integrated canvas with inpainting, outpainting, brush tools, layer management, and regional guidance for compositing AI generations with existing photography, renders, and sketches.
  • Node-Based Workflow Editor
  • Visual pipeline builder connects text encoders, VAEs, ControlNets, IP-Adapters, LoRAs, and custom nodes into reusable generation graphs with branching logic and parameter sweeps.
  • Extensive Model Ecosystem Support
  • Runs Stable Diffusion 1.5 through 3.5, SDXL, Flux.1 variants, CogView 4, Qwen Image, and externally-hosted models from OpenAI, Gemini, BytePlus, and Alibaba Cloud.
  • Multi-GPU and Multi-User Server
  • Backend supports CUDA, ROCm, and Apple MPS acceleration with multi-user accounts providing per-user galleries, settings, and concurrent access to a single shared InvokeAI instance.

Features

  • Unified Canvas
  • Infinite canvas workspace with inpainting, outpainting, masking brushes, layer blending, and regional guidance for precision control over AI-generated compositions.
  • Workflow Editor
  • Node-based visual editor builds generation pipelines connecting models, encoders, ControlNets, IP-Adapters, and LoRA weights into shareable and reusable graph definitions.
  • Model Manager
  • Downloads from HuggingFace and Civitai with automatic format conversion between safetensors, diffusers, and checkpoint formats, plus one-click installation of new models.
  • ControlNet and IP-Adapter
  • Spatial conditioning via ControlNet (depth, canny, pose) and image-prompt conditioning via IP-Adapter provide fine-grained compositional control over generation output.
  • Image Gallery
  • Searchable gallery stores all generations with full metadata including prompts, seeds, model parameters, and workflow definitions for exact reproducibility.