InvokeAI

What is InvokeAI?

Invoke is a web-based creative engine for open image models (SD1.5, SDXL, FLUX, Z-Image, Qwen-Image and others) plus optional API-backed models. It offers a unified canvas with layers, inpainting and outpainting, a gallery with boards, and a node-based workflow editor. It can run single-user or in a multi-user mode with accounts and an administrator, and is installed with a desktop launcher, Docker or a manual Python install.

Where it fits in a 10–200 person business

• Marketing visuals, product mock-ups and social images edited on a layered canvas
• Shared image-generation server for a small design team with per-user accounts
• Repeatable image pipelines built in the workflow editor

These use cases are our editorial suggestions, not claims made by the project.

Can a business use InvokeAI? (license)

This is a plain-English summary of the license text, not legal advice. Third-party models you run with it have their own licenses.

Data & compliance: does InvokeAI phone home?

Checked against the project's own docs and repository on Oct 23, 2026. "Not documented" means we could not find the answer in official sources; it does not mean the feature is missing or that no data is sent. Third-party services you connect (model APIs, vector databases, search engines) have their own data policies. Compare all apps.

What hardware does InvokeAI need?

The project does not publish a minimum CPU/RAM figure, so we leave the official value blank rather than guess.

GPU: Nvidia GPUs with compute capability 7.5+ (GTX 16xx, RTX 20xx and later, driver R580+), AMD via ROCm and Intel Arc are supported; Apple Silicon works with 16 GB+ memory recommended. Linux ARM64 runs CPU-only, where local generation is slow.

Requirements depend on the model. The docs give per-model "rough guidelines", e.g. SD1.5 4 GB VRAM / 8 GB RAM, SDXL 8 GB VRAM / 16 GB RAM, FLUX.1 10 GB VRAM / 32 GB RAM. These are per-model figures, not a server minimum.

Source: invoke.ai/start-here/system-requirements/

How much does it cost to host InvokeAI per month?

How to deploy InvokeAI

Method: Docker (Nvidia GPU)

docker run --runtime=nvidia --gpus=all --publish 9090:9090 ghcr.io/invoke-ai/invokeai
# open http://localhost:9090 and install some models

From the official instructions: invoke.ai/configuration/docker/. Always check the source for the current version before you run it.

Known gotchas when self-hosting InvokeAI

• Docker on macOS cannot use the GPU, so generation is slow there; the docs point Mac users to the launcher instead. source
• Without multiuser true in invokeai.yaml it runs single-user. Multi-user mode adds logins, but OAuth2/OpenID Connect and full audit logging are only "planned for a future release", and the team says the software has not had a rigorous security audit. Use HTTPS via a reverse proxy for internet deployments. source
• Switching an existing install to multi-user mode assigns all earlier boards and images to an internal "system" user that only administrators can see; a migration utility is not available yet. source
• Older Nvidia cards (Maxwell, Pascal, Volta, e.g. GTX 10xx, Tesla P40/V100) are not supported by the CUDA build; with a driver that is too old, Invoke starts on the CPU and logs an error saying so. source

Alternatives in Image & media generation

• ComfyUI Node-based engine for generating images, video, 3D and audio with open models. Compare ComfyUI vs InvokeAI

Sources

• GitHub repository: github.com/invoke-ai/InvokeAI
• Official documentation: invoke.ai/
• License text: github.com/invoke-ai/InvokeAI/blob/main/LICENSE
• Hardware requirements, Gotcha 4: invoke.ai/start-here/system-requirements/
• Deploy instructions, Gotcha 1: invoke.ai/configuration/docker/
• Gotcha 2, Gotcha 3: github.com/invoke-ai/InvokeAI/blob/main/docs/src/content/docs/configuration/Multi-User%20Mode/admin-guide.mdx
• Hetzner Cloud pricing (cost estimate): www.hetzner.com/cloud/regular-performance
• GitHub stars, commits and releases: GitHub REST API, fetched Oct 23, 2026