Image generation

3 aliases · Z-Image-Turbo · FLUX.2-klein · Qwen Image. Local image generation through an OpenAI-compatible /v1/images API — the same server the desktop app's Images tab uses.

rapid-mlx serves POST /v1/images/generations (and POST /v1/images/edits) in the OpenAI Images shape, rendering through mflux-converted checkpoints entirely on your Mac. One image model is resident at a time — same single-worker discipline as the video lane. In the desktop app, the Images tab drives the same endpoints: pick a model, prompt, refine, and every render lands in a filmstrip you can step back through.

family

Image generation (mflux)

aliases

3

install

pip install 'rapid-mlx[image]'

OpenAI base URL

http://localhost:8000/v1

Usage

pip install 'rapid-mlx[image]'
rapid-mlx serve z-image-turbo

curl http://localhost:8000/v1/images/generations \
  -H 'Content-Type: application/json' \
  -d '{"model":"z-image-turbo","prompt":"a lighthouse at dusk, oil painting","size":"1024x1024"}'

The three families

Each image model is a family in its own right, with its own page — usage, download, RAM requirements:

Notes & caveats

• Requests are validated against the served model — a mismatched model field returns a clear error instead of silently ignoring it.
• Generation is compute-bound: seconds to tens of seconds per image depending on model and Mac. Turbo-distilled checkpoints (z-image-turbo) are the fast path.
• The desktop app keeps a chat model and an image model warm at once, so switching tabs doesn't evict either.

Frequently asked questions

Can I generate images locally on a Mac?

Yes — POST /v1/images/generations renders entirely on Apple Silicon through mflux-converted checkpoints. No cloud, no per-image cost. The desktop Images tab uses the same server.

Which image models run on Apple Silicon?

Three aliases: z-image-turbo (5.9 GB, 16 GB RAM), flux2-klein-4b (4.6 GB, 12 GB RAM — the smallest), and qwen-image (31 GB, 64 GB RAM).

Where next