01 · GeneratedOriginal
Local-first · open core · Apple Silicon
Every open image model.
Every open image model.
Running on your machine.
Planar is a local studio for image generation — from a one-click result to iterative, instruction-driven refinement. Diffusion and beyond, on the hardware you already own.
Latest release · Loading… · macOS on Apple Silicon (arm64)
Prompt
a leviathan rising from black water, 1990s painted fantasy illustration▏
Photoreal
Illustration
3D
Anime
+ preset
Size
Steps 30Images 4
Runs the open ecosystem you already use
Diffusers
stable-diffusion.cpp
SDXL
FLUX
ControlNet
LoRA
Qwen-Image-Edit
One prompt · then keep going
Generate a result. Then talk it into shape.
Most images aren't right on the first roll. Planar's refine loop lets you describe a change in plain language — "make the sword glow blue" — and applies it with an instruction-edit model, without re-rolling the whole image.
Generate
Refine
Prompt
a leviathan rising from black water, 1990s painted fantasy illustration▏
Photoreal
Illustration
3D
Anime
+ preset
Size
Steps 30Images 4
Built for the whole open stack
From a first generation to a research rig.
The same app handles a one-line prompt and a deep model-management workflow, running locally on Apple Silicon.
Apple Silicon (arm64)
Planar is available for macOS on Apple Silicon. Generate images locally on your Mac with compatible models you provide or download.
macOS · arm64Sandboxed plugin pipeline
Extend Planar with WASM plugins — no network or filesystem access by default. Load one, activate it, and batch-run it across every image in your gallery.
WASM · no WASI · plugin APIExperimental research models
Because it speaks Hugging Face Diffusers natively, Planar runs the newest research checkpoints the day they drop — not months later.
HF Diffusers nativeBeyond diffusion
Background removal ships built in. Upscalers, segmentation and restoration models run as plugins on the same ONNX runtime.
ONNX runtime · bg removal bundled100% local & private
Generation runs on your hardware. No uploads, no prompt telemetry, no queue — your work never leaves the machine.
No cloud · no accountAgent & MCP ready
Drive Planar from an agent session over MCP — queue jobs, poll status, stream results — while the same queue powers the UI you click through by hand.
MCP server · async job queue
Models
Bring any checkpoint. Planar figures out the rest.
Point it at a folder or a Hugging Face repo. Planar detects the architecture, picks sane VAE and sampler defaults, and loads — swapping backends without leaving your project.
- Diffusers & stable-diffusion.cpp backends, hot-swappable
- Auto VAE, sampler and resolution detection
- LoRA stacks and ControlNet built in
Model · backend
stable-diffusion.cpp▾
juggernautXL_v2●
Sampler
Euler A ↩
DPM++ 2M ●
LCM ↩
Inference engines
Two backends. One switch.
Run the same project on whichever engine fits the job — a lean quantized runtime or the full research stack. Pick per project, swap anytime, no reinstall.
C++
stable-diffusion.cpp
lean · quantized · low-VRAM
- GGUF quantization — run big models on small GPUs
- CPU, Metal, CUDA & Vulkan acceleration
- Fast cold starts and a tiny memory footprint
Best for laptops & quick iteration
⇄
swapanytime
HF
Hugging Face Diffusers
maximal · research-ready
- Every architecture — SD, SDXL, FLUX and new research
- Day-one support for checkpoints as they drop
- Full pipeline: LoRA, ControlNet, schedulers
Best for breadth & the bleeding edge
Beyond diffusion · WASM plugins
Bring your own image models.
Planar runs any ONNX image model as a plugin, sandboxed with no network or filesystem access. One ships in the box; drop in the rest.
BGBackground removerbundled
clean alpha matte
One-click subject isolation with a crisp alpha channel — ready for compositing nodes. Ships with the app, u2net-based.
DTPS1 / Bayer ditheringexample plugin
ordered dithering
A reference WASM plugin that applies retro ordered dithering — the template for building your own image-processing nodes.
+Add ONNX model
+
Point Planar at any
.onnx graph, wrap it with the plugin SDK, and it shows up as a loadable, batch-runnable plugin.
Getting started
Local image generation on your Mac
Planar brings open image models, generation and instruction-based editing into one macOS workspace.
Which Macs can run Planar?
The current release is for macOS on Apple Silicon (arm64). Model memory needs vary by model, image size and backend.
Does Planar generate images in the cloud?
Image generation runs on your Mac. Planar does not upload your prompts or generated images for cloud processing. Models must be available locally before you generate.
Which image models does Planar support?
Use the stable-diffusion.cpp or Hugging Face Diffusers backend with compatible models, plus LoRAs and ControlNet workflows. See the model and backend guide for setup details.
How do I install and get started?
Download the macOS app, add or download a compatible model, then generate from a prompt. Follow the getting started guide for steps and requirements.
Open core
Free to create. Pro when you scale.
The full studio is free, forever. Pro adds team and power-user features down the line — you’ll never lose access to what’s open today.
Planar
Free / forever
The complete local studio.
- Generate & iterative refine modes
- Both open backends & every model they support
- Plugins & custom nodes
- Latest release · Loading… for macOS on Apple Silicon
Loading… · macOS on Apple Silicon (arm64)
Download requests: Loading…
Pro — coming later
Soon
For teams and heavy pipelines.
- Shared model & plugin library
- Batch & queue orchestration
- Priority model support
- Everything in Free
Pro features are planned for a future release.
Generate locally. Refine until it's right.
Download the current Planar release for macOS on Apple Silicon (arm64).