We offer a wide range of tools, but we understand that when you’re just getting started with AI, you want to find the right fit quickly and comfortably.
Text-to-Video and Frame-by-Frame
At the core, there are two primary styles of video creation:
Text-to-Video - Lifelike, cinematic video that feels like it was shot with a real camera. Movements are smooth, characters and environments appear grounded, and the final output often resembles a high-budget film. Ideal for projects that lean into realism or suepr polished modern aesthetics.
Frame-by-Frame - Flickery, textured, and visually expressive. This style emphasizes stylized motion, and evolving imagery. Great for music videos, visualizers, and morphing storytelling that leans towards abstraction and surrealism.
Automation Tools
Each style also offers an automated creation option that removes the guesswork and flattens the learning curve of working with video AI. Both tools use powerful core features behind the scenes, including lyric transcription, BPM and key detection, and analysis of a song’s themes and tone.
Autopilot for Text-to-Video
Auto-Prompt for Frame-by-Frame
Manual video editors
The Text-to-Video editor lets you generate clips with cinematic camera movement while working in an interface that feels similar to tools like CapCut or Premiere Pro. You can trim, split, and reorder clips, import footage from other projects using the Asset Manager, apply fades and blurs for transitional storytelling, and apply audioreactive and modultion effects to sync with your video.
Our Frame-by-Frame editor builds projects from the ground up, which allows complete control, down to the frame. You have control over each parameter and camera movement, multiple ways to transition into new scenes, style reference capabilities, the ability to change models within the same project, changing the aspect ratio while keeping the project in tact, and so much more. The frame-by-frame editor is the purest reason why we're the synthesizer for the visual world.
Where to begin?
These three key factors should lead you into beginning your first project.
Visual style
For modern, cinematic video, use Text-to-Video
For trippy animation with morphing transitions, use Frame-by-Frame
Time efficiency: Automated tools for each primary style takes out the guesswork of manually creating a video
For Text-to-Video, use Autopilot
For Frame-by-Frame, use Auto-Prompt
Credit-efficiency: Manually creating a video is more credit-effective than our automated tools
The Text-to-Video editor uses less credits than Autopilot, starting as low as 3 credits per second
The Frame-by-Frame editor is the lowest credit-cost tool
All models and Auto-Prompt use 1 credit per second
Which tool is right for you? Real-world scenarios
A musician needs a video fast. Their album drops next week, and they want something strong for socials, with no time to learn or experiment.
We'd recommend Autopilot to create a strong, high-quality cinematic video that they can take to social media same-day.
A musician that's new to AI wants to create a full album visual experience. They plan to release a few singles and want to create videos for different social media platforms, so they'll want different aspect ratios.
We'd recommend Auto-Prompt to create a high-volume of videos in different aspect ratios while cutting out the guesswork on learning/adapting to AI tools.
A content manager at a record label needs reliable AI video output to keep social feeds active and build engagement. They don't have time to build videos one-by-one or view manuals/prompting guides
We'd recommend Autopilot for easy scaleability to produce clean, cinematic clips for reels, TikTok, or YouTube drops with minimal oversight.
A visual artist who's dabbled with AI wants to blend surreal transitions and scene morphing with full aesthetic control. They want to explore and experiment with multiple models and reference their own artwork.
We'd recommend the manual Frame-by-Frame editor where they can use style reference to blend in their own art, create custom models and switch models mid-project and create complex transitions for total visual experimentation.
An artist doesn’t have a strong visual concept but still wants something stunning. They want the AI to understand the song for them to create visuals.
We'd recommend Autopilot where the artist can let the AI do the work for them. The AI will create a video that aligns with the music by extracting lyrics, BPM, and themes/tones of the song.
An artist wants full control over a cinematic story-driven video. They have a clear vision and want to build out scenes with long durations, emotional pacing, and custom camera work.
We'd recommend the manual Text-to-Video editor for a cinematic narrative with full control, and the ability to build out long scenes and ability to control the camera with text-to-video camera sliders.