AI Models in Luma (Dream Machine)
The AI models you can choose inside Luma (Dream Machine), grouped by type. Each model page shows the other apps that offer it, so you can compare prices for the same model.
Updated September 2026 · 12 listings
How to pick a model in Luma (Dream Machine)
Pick the model from the app's model selector (often under the prompt box or in settings). Credit costs usually differ per model, and some apps only offer the newest models on paid plans.
GPT Image 2.5 🧠 ModelFreemium
OpenAI's image model behind ChatGPT Images, with 4K output and up to 16 reference images
Nano Banana 2 🧠 ModelFreemium
Google's Gemini image models (Nano Banana 2, Pro and 2 Lite) for generation and editing up to 4K
Eleven v3 🧠 ModelFreemium
ElevenLabs' expressive text-to-speech model with audio tags and 70+ languages
Veo 3.1 🧠 ModelPaid
Google DeepMind's text- and image-to-video model with native sound, up to 4K
FLUX.2 🧠 ModelOpen source
Black Forest Labs' FLUX.2 family: hosted [max]/[pro]/[flex] plus open-weight [dev] and [klein]
Kling 3.0 🧠 ModelFreemium
Kuaishou's video model with native multilingual audio, lip sync and 15-second clips
Seedance 2.5 🧠 ModelPaid
ByteDance's video model: 30-second clips with audio, many references and local edits
Seedream 5.0 Pro 🧠 ModelFreemium
ByteDance's Seedream image models, used in CapCut, Dreamina and many creative apps
Whisper large-v3-turbo 🧠 ModelOpen source
OpenAI's open-source speech recognition for transcripts and subtitles in 99 languages
MiniMax H3 (Hailuo 3.0) 🧠 ModelFreemium
MiniMax's open-weight video model: native 2K, stereo sound, 15-second clips
Eleven Music v2.5 🧠 ModelFreemium
ElevenLabs' music model: songs up to 5 minutes with vocals, cleared for most uses
Luma Ray3.2 🧠 ModelPaid
Luma's HDR video model with up to 16 keyframes in a 20-second 1080p clip