InvokeAI

InvokeAI suits creators who can provide suitable local hardware and want control over an image-generation setup. Its layered canvas supports composition and targeted edits, while node workflows make repeated operations inspectable. This listing covers the community-maintained software. The former officially hosted platform closed; it should not be confused with the active self-hosted project.

A practical workflow

1. Install the official launcher on a supported machine.
2. Add a compatible model with a suitable license.
3. Generate a small image or edit a canvas region.
4. Inspect the result and save the workflow settings.

Illustrative input

This example describes a task, not a tested output. Adjust the source material and settings to your own situation.

Create a simple still life with a cup and closed book. Use a reference sketch to guide layout, then edit only the background.

Result check: Check composition, mask boundaries and model permissions before sharing the result.

Access and alternatives

The community software is free and Apache-2.0 licensed. You supply compatible hardware, models and any paid hosting services; model licenses remain separate. The former hosted Invoke service is discontinued. Check the current installation requirements, including supported GPUs and Apple Silicon requirements, before downloading large models.

Choose another workflow when its emphasis fits better: Stable Diffusion for information on another image-model offering; Krea for a hosted creative workspace.