Models
22 AI models, one studio.
Pick the right model for each shot, then cut every clip together on the same timeline as your script and storyboard. Each page lists what the model does in MoviePro and what it costs.
Video
Video models
Seedance 2.5
Multimodal Video
ByteDance's flagship video model: native synchronized audio, clips up to 30 seconds, and large reference sets for character consistency.
Veo 3.1
Photoreal Video with Sound
Google DeepMind's Veo 3.1: photoreal text-to-video, image-to-video and first/last-frame transitions up to 1080p, with synchronized dialogue, effects and music.
Veo 3.1 Fast
Fast Video with Sound
Veo 3.1 Fast: Veo 3.1's text-to-video, image-to-video and first/last-frame transitions with sound, faster and at under half the cost.
Kling 3.0
Cinematic Video
Kuaishou's Kling 3.0: cinematic shots from 3 to 15 seconds at 720p, 1080p or 4K, from text, a first frame or first and last frames, with native audio.
LTX-2.3 Pro
High-Resolution Video
Lightricks' LTX-2.3 Pro: text-to-video and image-to-video from 1080p up to 4K, landscape or portrait, with generated audio.
Hailuo 2.3
Physics & Motion
MiniMax Hailuo 2.3: realistic physics and motion, text-to-video and image-to-video at 768p in 6 or 10 seconds.
Wan 3.0
Long-Take Video
Alibaba's Wan 3.0: text-to-video and image-to-video up to 1080p and up to 30 seconds, in landscape, portrait, square or 4:3.
Seedance 1 Pro
High-Fidelity Video
Seedance 1 Pro: text-to-video and image-to-video up to 1080p, with first/last frame control and a fixed-camera option.
Seedance 1 Lite
Fast Video
Seedance 1 Lite: faster, lower-cost text-to-video and image-to-video with reference images for consistent characters.
MiniMax Director
Camera-Controlled Video
MiniMax's camera-control model: native dolly, pan, tilt, truck, crane, zoom and handheld moves follow your shot list.
Runway Gen-4.5
Cinematic Motion
Runway Gen-4.5: state-of-the-art motion quality and prompt adherence, from text or a first frame, in six aspect ratios at 720p.
Cinema Studio 4.0
Director Controls
Higgsfield's Cinema Studio: set the camera move, lens, film stock, aperture, lighting, genre, era and colour grade as controls, with reference images and native audio, up to 30 seconds.
Image
Image models
GPT Image 2.5
High-Quality Image Synthesis
OpenAI's GPT Image 2.5: detailed, prompt-faithful images from a text description, including legible text.
FLUX1.1 [pro]
Photoreal Image Generation
Black Forest Labs' FLUX1.1 [pro]: sharp, photoreal images with strong composition and prompt following.
Ideogram 3.0 Turbo
Text-in-Image Specialist
Ideogram 3.0 Turbo: posters, titles and signage with readable typography, plus fast general image generation.
Imagen 4
Photoreal Image Generation
Google DeepMind's Imagen 4: photoreal images with fine detail and accurate prompt following.
Recraft V3
Design & Illustration
Recraft V3: illustrations, posters and brand-style artwork, including clean graphic shapes and legible text.
Gemini 2.5 Flash Image
Fast Image Generation
Google's Gemini 2.5 Flash Image: quick text-to-image and MoviePro's default image model.
Music
Music models
ElevenLabs Music
Songs & Scores
ElevenLabs Music: full tracks with or without vocals at 30, 60 or 120 seconds, from a prompt and optional lyrics.
Stable Audio 2.5
Music & Sound Design
Stability AI's Stable Audio 2.5: instrumental music and soundscapes up to 2 minutes.
MiniMax Music 1.5
Songs with Vocals
MiniMax Music 1.5: sung songs from a prompt and lyrics (written for you if you leave them blank); the model picks the length.
MusicGen
Open Source Music Synthesis
Meta's open source MusicGen (part of AudioCraft): instrumental tracks up to 60 seconds from a text prompt, for scoring and soundscapes.
Your first 50 credits are on us.
That is 16 storyboard frames, or 2 five-second Seedance 2.5 shots at 480p. No card needed.