Luma

Luma launched Skills as reusable workflows that can be described in plain language, run on any asset, and shared by link, package, or file. The feature turns one-off agent outputs into repeatable brand, product, and character operations, so teams can reuse the same process instead of rebuilding it.

Luma opened Ray3.2 and its API with multi-keyframe control, 20-second 1080p video-to-video, reframe, motion transfer, and 16-bit EXR HDR export. Creators can now steer shot beats more precisely and composite AI clips into professional color and VFX workflows.

Luma Agents posted new examples for turning briefs and benefit hooks into UGC-style ad assets, while creators shared active boards for related ad builds. The evidence points to repeatable low-polish brand ad generation instead of single polished hero spots.

Luma Labs added Seedance 2.0 as a model option in Luma Agents, and creators quickly posted longer clips made inside the agent workspace. The change moves Seedance into an idea-to-video environment instead of a standalone generation step.

Luma Agents added Kling Omni as a generation option and paired the integration with demos that carry a reference moodboard through to finished ad visuals. The update gives creators another video model inside Luma's existing campaign workflow.

Luma opened Uni-1.1 as an API with built-in prompt enhancement, research, and reference gathering, while also pointing to lower price and latency. The release moves its image model into production pipelines for fashion, interiors, storyboards, and other brand-heavy visual work.

Luma posted new Agents workflows for translating videos with lip sync and localization, plus dropping a subject into new environments with matched blending and lighting. The additions matter because Luma is moving from generation-only output into post-production localization and scene editing.

Luma and creators kept pushing UNI-1 Pouty Pal self-avatar posts, and Luma said a how-to guide is now circulating for people to make their own. The meme is turning into a repeatable character workflow, though the evidence is still mostly demos and social sharing.

Luma launched Agents for creative work, with creator tests focused on keeping characters, lighting and environments coherent across multi-scene sequences. Use it to cut file juggling and lock image generation to Uni-1 when you need tighter control.

Luma launched Uni-1 and says it can reason through prompts while generating images. Creators report stronger composition on first pass for sketch-to-photo, multiview characters, and reference-led scenes, which should cut correction loops.

DreamLabLA posted a finished crash shot alongside a behind-the-scenes breakdown covering planning, setup, and final compositing with Luma Agents. Use the paired clips as a template for where generative agents fit inside a practical VFX pipeline.