Luma Relight Studio Relighting
This shot works. Let's try different lighting. Luma's Relight Studio lets you explore new lighting directions without redoing the work.
This shot works. Let's try different lighting. Luma's Relight Studio lets you explore new lighting directions without redoing the work.
During LA Tech Week, GMI Cloud, NVIDIA, SHÙ Studio and Real Reel will host the "Scaling Long-Form AI Video with MCP" brunch on October 14 in Santa Monica, focusing on the workflows needed for AI video to move from single-shot clips to 30-to-90-minute long-form narratives.
You already have product images. Now you need to put them somewhere else. Product Shots lets creative teams place the same product into new scenes without starting from scratch each time.
Budget once determined where a story could be filmed. Jon Erwin shot "Moses" on a stage in Manhattan Beach, using real actors plus AI to bring them into whatever world the story required.
Bring your @claudeai Motion animations into Luma and keep creating. Resize to the format you need, refine, and produce a deliverable version. Start in Claude Motion. Finish in Luma. Claude Motion is currently in beta and available to Claude Team and Enterprise plans.
New skills are developed collectively by people. Right now in Los Angeles, every "I figured out how to do this" becomes someone else's starting point.
Luma announced that Claude Motion animations can now be opened directly in Luma. Creators can import Claude-generated animations into Luma via MCP connection, then continue expanding, refining, and exporting them as finished videos in any format.
Why it matters: Claude Motion animations can now enter Luma directly via MCP connection, allowing creators to assess whether a cross-tool video production pipeline is worth integrating.
Keep the shot, just swap the face. Luma's face-swap feature lets you iterate without starting over.
"No single model rules them all." Creative ideation and the final image demand different things. What you need to do is route the creative work to the model best suited for each stage.
A model alone can never make a film. The real work is putting new capabilities into creators' hands, then making sure they can actually use them. That is how research becomes part of the craft of creation.
VIBE released a guide to cinematic AI B-roll generation, proposing a five-part prompt formula of "subject, action, camera, lighting, color grading," and listing specific parameters for models such as Kling 3 Pro, Luma Ray 3.2, Google Veo 3.1, and Sora 2 Pro.
Luma introduces Variants: after a user uploads an approved static ad, they select a layout and language, and the system automatically generates versions for each size and language combination, keeping the logo, headline, and CTA unchanged while only adjusting layout and copy.
Why it matters: Ad teams can use this to evaluate batch-adapting a single approved asset into multiple sizes and language versions, replacing manual rework.
Luma announced that Ideogram 4.5 is now available on Luma, and users can use it at app.lumalabs.ai, giving creative teams more control over deciding which content in the image changes and which is preserved. The cited official Ideogram introduction states that Ideogram 4.5 is a model focused on precise editing that can eliminate artifact accumulation in multi-round editing, thereby supporting multi-round editing; it is already available on Ideogram, the API, and launch partners, with open weights coming soon.
The ad is done. The versions aren't. Different sizes. Different markets. Same campaign. Take your ads further with Luma's Ad Variants.
Luxury brands need to create more and move faster, while still safeguarding the craftsmanship that makes their work feel premium. LBB spoke with Omnicom and Luma about how AI can help creative teams explore, iterate, and scale without giving up creative control. https://lbbonline.com/news/luma-ai-omnicom-luxury-fashion-brands
VIBE is an AI video generation app that can call models such as Kling, Sora, and Veo to turn a song, lyrics, or a single reference image into a music video ready to publish with a soundtrack. Its approach is to split the song into sections such as intro, verse, and hook, write visual prompts for each section separately and generate 4–15 second clips, then edit and stitch them together on a phone in song order.
Avid sets out four requirements for agentic media production: understand project context, operate within explicit permissions, know when human approval is needed, and leave an audit trail. Luma Agents, Runway Agent and Adobe Creative Cloud have each launched their own agent solutions, and Netflix acquired Ben Affleck's InterPositive for $587 million.
Post-shoot revisions are part of the job. Wardrobe, backgrounds, lighting—now more of these changes don't require everyone to return to set.
Hedra compared API pricing across 11 video models for the same task (10 seconds, 1080p, native audio, one starting frame plus a text prompt), with the lowest at $0.60 for LTX-2.3 Fast and the highest at $7.91 for Seedance 2.5—a 13x difference. Nine models meet the spec; Veo 3.1 maxes out at 8 seconds and MiniMax H3 has no 1080p setting, so both are listed separately as close substitutes.
Why it matters: For the same 10-second 1080p with audio task, API unit prices across 11 video models differ by 13x, along with a reusable method for model selection and cost verification.
Creative teams are already using AI. The bigger question now is whether it can integrate into real workflows without adding more fragmentation. At Brandweek, @AlexiaAdana demonstrated how Luma supports the creative process from early direction through production. ADWEEK explores the next phase here: https://www.adweek.com/creativity/ai-has-reached-creative-teamsnow-comes-the-hard-part/
VIBE's AI video aspect ratio guide notes that 9:16 is suited for TikTok, Instagram Reels, and YouTube Shorts; 16:9 is used for YouTube, websites, and most ad placements; 1:1 is used for feeds and carousels; and 21:9 is used for cinematic B-roll and trailers.
Underwater shooting typically requires a large amount of specialized equipment, building underwater sets is especially expensive, and green-screen lighting underwater presents additional unique challenges to overcome. Hybrid production makes underwater shooting much easier. Made with Luma.
The production process for our video exploration piece "Ichor," which made key use of Seedance 2.5's edit mode and the new keyframe interface. This helped us get more fitting performances and control the pacing of the keyframe scenes. This direct control made the process faster and easier.
Ever finished a shoot only to be asked for a back view? We have too. Camera Angles turns one photo into a whole shoot. Pick your angles and get the same subject back from every one, with details intact. For all the shots you wanted but never got.
Generative media in entertainment is no longer a set of tools you pick up casually—it's the infrastructure you build on. Meet Gray Crawford, taking the stage on behalf of Luma at GMI Summer Signal '26 in San Francisco on September 14.
Embedded text is exactly why you're still opening Photoshop. Layers can now extract it. Select a layer, click Extract, and the copy becomes live text, already automatically matched to the closest font in the font library. Retype. Change the font. Re-layout. Changing a line of copy takes two clicks instead of regenerating. Layers, powered by Uni-1.
Luma announced that GPT-Image-2.5 is now live in Luma Agents, alongside integration of two new OpenAI image models, both available the same day. Among them, Flare targets speed and batch work, while Sunburst targets edits that require precise placement; users can bring in reference images, change only what needs changing while preserving the rest, and then move into video.
Tomorrow night in San Francisco at tiat. Creative Intelligent Machines Continuum, a Luma creator night. Hands-on walkthroughs from Luma's senior creatives, a theme to create with, and on-site support.
Luma enterprise governance features are now live. Team isolation. Set spending caps per project. Billing doesn't stall because of spending caps.
Some faces deserve 4K. Even the six-eyed ones. FLUX Video Upscale can upscale video to 2K and 4K.
Hands-on walkthroughs from Luma's senior creatives, prompts you can practice along with, and on-site support. Creative Intelligent Machines Continuum, a Luma creator night. Tuesday, September 1, at tiat in San Francisco. Apply to join → https://luma.com/cimc2
Because some things deserve to be seen more clearly. Luma's image enhancement feature just got better.
At blue hour, a killer crosses a marble floor to end a contract he never thought to question. "L'heure Bleue" creator: Bryan Soegondo @DreamLabLA Made with Luma
/Dream Lab Weekly/ EP: 1 A series showcasing our creative professionals and their weekly explorations, dedicated to making Luma the best creative tool in the world.