Luma Dream Machine
Text-to-video and image-to-video generation powered by the Ray 3 model.
About
Dream Machine is Luma AI's browser-based video generation platform, powered by its Ray 3 video model. It supports text-to-video, image-to-video, start and end frame control, video extension, and looping, plus a Modify feature that edits existing videos with plain-text descriptions and Character Reference for keeping a consistent character across generations. Paid plans also expose third-party models such as Sora 2, Veo 3, and Kling from the same dashboard.
Luma AI, founded in 2021, raised a $900M Series C in November 2025 at a valuation above $4B and reports more than 30M users. Pricing as of September 2026 lists Plus at $30/mo, Pro at $90/mo, and Ultra at $300/mo, with no free tier on the pricing page. Critics have noted limited transparency about training data, and the commercial-use terms deserve a careful read before production work.
What it can do
- Text-to-video and image-to-video
- Start/end frame control and video extension
- Character Reference for consistent characters
Setup
Create an account in the Dream Machine web app or iOS app and purchase a plan.
Prerequisites
A paid plan; descriptive prompts or source images.
Use cases
Works with
Trust score — 9/10
Scored 9/10 (verified tier, metrics-v1). Evidence: Verified via vendor site/docs/GitHub and reputable coverage, wave 77; Trending score 88/100 from researcher assessment.
Sources
Every fact above was checked against these sources. Where a claim comes from the provider and couldn't be independently verified, the text says so.