FluidCAD vs Midjourney Web Editor Inpainting & Reference Layers

“FluidCAD solves the thing OpenSCAD got wrong: the 'drag to prototype, lock to code' loop makes it accessible without sacrificing programmability. STEP export means it fits into actual hardware workflows, not just rendering. For software engineers doing mechanical work, this is the missing middle ground between Fusion 360's complexity and OpenSCAD's austerity.”

“Code-first CAD has a 30-year history of failing to reach mainstream adoption because engineers and designers don't want to write JavaScript. FluidCAD will appeal to a very narrow slice of software developers who also do mechanical work. The STEP import/export is table stakes, not a differentiator, and Onshape's API does everything this does for teams who need collaboration.”

“This is genuinely Midjourney catching up to Stable Diffusion workflows that have existed in ComfyUI and Automatic1111 for two years — credit where it's due for packaging it without requiring a local GPU and a PhD in node graphs. The specific scenario where this breaks is complex product photography: multi-layer references with fine texture like fabric or intricate logos still drift noticeably after inpaint cycles, which means professional retouching workflows aren't fully replaced yet. What kills this tool in 12 months isn't a competitor — it's Adobe Firefly and the Photoshop generative fill team, who now have a direct target to match feature-for-feature. Midjourney wins if their model quality gap holds; right now it does.”

“When AI can generate CAD from natural language, the tools that survive will be the ones with programmatic, diffable representations — not binary blob formats. FluidCAD's JavaScript-first approach puts it in exactly the right position for the AI-assisted hardware design wave that's coming. This is the OpenSCAD for the LLM era.”

“The thesis here is that non-destructive, multi-reference generative editing becomes a standard primitive in all creative software — not a specialty feature but a baseline expectation, the way layers were after Photoshop 3.0. Midjourney stacking inpainting and reference layers in the same session is a bet that the editing and generation workflows converge into a single surface, eliminating the round-trip between generator and editor that currently fragments creative pipelines. The second-order effect that matters: if this works at quality, it transfers creative leverage from production designers who own the toolchain to art directors and clients who only own taste — and that's a real power shift in agency workflows. The dependency that has to hold is Midjourney's model quality advantage over commodity diffusion endpoints; the moment that gap closes, the web editor is just a UI wrapper.”

“I appreciate the concept but the UI is clearly built by engineers for engineers. There's no real onboarding, the documentation assumes CAD literacy, and the JavaScript API surface is intimidating for anyone coming from traditional design tools. Until there's a visual-first entry point, this stays a curiosity for most designers.”

“The inpainting actually produces coherent output — fix a hand, swap a background element, adjust a face without nuking the rest of the composition. That's the hard problem other inpainters fumble. The reference layer system is the real unlock: stack a character ref on top of a style ref and the model holds both with real fidelity, not a mushy average. The editing surface is brush-based with adjustable hardness, which is the right call — it matches how illustrators already think about masking. The one failure is the layer stack has no blend mode controls, so if your references fight each other, you can't arbitrate who wins.”

“The inpainting brush tool is actually designed — there's a clear mask preview in a distinct overlay color, an undo stack that doesn't blow away your full session, and the strength slider gives you real feedback as you drag, not just after you regenerate. What's missing is any visual hierarchy between the reference layer panel and the generation controls; they sit at the same visual weight and the eye has nowhere to land when you're deciding what to adjust next. The empty-state handling is also lazy — drop into a blank editor with no image loaded and you get a generic placeholder instead of a guided first action. Strong fundamentals, unfinished information architecture.”