Midjourney Web Editor Inpainting & Reference Layers vs Runway Gen-4 Video Editor

“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 motion brush is the feature I didn't know I needed — painting directional movement onto a specific object without it bleeding into the background is the kind of control that separates 'AI slop' from 'actually usable footage.' The output fingerprint is still there if you look for it: that slightly uncanny softness on fast motion, the way Gen-4 handles cloth physics a beat too perfectly. But the temporal consistency fix for clips over 10 seconds is real — I stopped getting that weird structural drift at the 8-second mark that made longer takes unusable. The specific craft decision that earns the ship: motion brushes delegate taste back to the user instead of making every clip look like a Runway clip.”

“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.”

“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.”

“Real-time collaboration in an AI video tool is genuinely differentiated — Pika and Kling don't have it, and Adobe's Firefly Video still treats multi-user as an afterthought. The scenario where this breaks is any team above 5 people with a real review-and-approval workflow: there's no version history, no comment threading, no asset management. It's Google Docs collaboration bolted onto a generation tool, not a production pipeline. What kills this in 12 months isn't a competitor — it's that the collaboration feature stays shallow while teams need it to go deep. But the motion brush is a genuine primitive improvement, not a marketing slide, and that's enough to ship.”

“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.”

“The thesis here is that AI video generation becomes a collaborative production layer — not a solo prompt box but an environment where a director, VFX artist, and editor work simultaneously on synthetic footage. That's a falsifiable bet: it requires that teams adopt AI-generated footage as a primary production input rather than a supplementary effect, which currently only a narrow slice of creators do. The second-order effect that matters isn't the collaboration feature itself — it's that real-time collab creates artifact provenance questions nobody has solved yet: who made what, which generation prompt is canonical, how do you credit a collaboratively prompted clip. Runway is early to collaboration-as-infrastructure and on-time to the temporal consistency problem, which is the actual gating factor for professional adoption.”

“The job-to-be-done just expanded from 'generate a video clip' to 'produce video with a team,' and that's a meaningful product leap — but the onboarding for the collaboration feature is unfinished. Getting a collaborator into an existing project requires sharing a workspace link through settings buried two levels deep; a user reaching value in under two minutes is not happening for first-time collaborators. The motion brush earns its place because it maps to a real editing job creators already have: 'move this thing but not that thing.' The specific product decision that earns the ship is temporal consistency at 10+ seconds — that's the threshold where Runway clips were previously unusable in real cuts, and fixing it makes the tool completeable for an actual production workflow without needing a second tool.”