InvokeAI
InvokeAI, professional creative-suite local image-generation app built on Stable Diffusion and Flux.
Release history
InvokeAI 7.0.0
InvokeAI v7 alpha adds board role-based sharing, Qwen-Image-2.1 support, and SageAttention for faster NVIDIA generation, with database migrations that are one-way from v6
InvokeAI Windows ARM64 wheels (win-arm64-wheels-v1)
Self-built Windows ARM64 wheels; Only relevant to ARM64 Windows users installing InvokeAI
InvokeAI 7.0.0
InvokeAI 7.0.0 alpha adds multi-board projects, MySQL/MariaDB backends, expanded GGUF transformer support, improved video handling, and VRAM tuning for reduced OOM errors
InvokeAI 7.0.0
Pointing v7 at an existing root directory upgrades the database irreversibly; Back up before installing, v6 compatibility is lost
InvokeAI Version 6.14.2
Bug fixes from 6.14.1 plus unspecified new features
InvokeAI Version 6.14.1
Bug fixes for 6.14; Adds minor features that missed the prior cut
InvokeAI 6.14.0
InvokeAI 6.14 adds video generation via Wan 2.2, supports Flux.2 Dev, Krea.2, Ernie, Ideogram 4, and enables multi-GPU, Intel XPU, and FP8 optimizations
InvokeAI 6.14.0
Adds video generation via Wan 2.2; Release candidate 2
InvokeAI 6.13.8
Patches two critical security vulnerabilities: arbitrary code execution via crafted URL payloads and unauthorized network connection attempts
InvokeAI 6.14.0
Adds video generation via Wan 2.2
InvokeAI 6.13.7
Closes config-file exposure affecting all versions through 6.13.6. Upgrade immediately
InvokeAI 6.13.6
Fixes dictionary key error crash in Qwen Image and Qwen Image Edit models with default single-file encoder
InvokeAI 6.13.5
InvokeAI 6.13.5 stabilizes image generation with bug fixes for prompt history, GPU crashes, and UI layout while updating React 19, ROCm 7.1, and Transformers 5.5.4
InvokeAI 6.13.5
Maintenance release focused on bug fixes and stability
InvokeAI 6.13.0
InvokeAI now supports Qwen Image 2.5, Qwen Image Edit 2.5, and Anima locally, plus externally-hosted models from OpenAI, Google, BytePlus, and Alibaba Cloud via API keys