Overview
FTL Studio is an open-source AI video generator that turns one sentence into a directed, multi-shot cinematic film with the same character and set in every shot. It is built on Google Veo 3.1, Gemini and Claude. The system addresses the problem that AI video characters change every clip, because text prompts cannot lock a face. The fix is to compile prompts and animate approved images: a sentence is scattered into typed nodes, expanded through six lenses (form, material, motion, light, sound, physics), and converged under a precedence law so contradictions are resolved before the model sees them. A canon character still and set still are approved once, then every shot's first frame is composited from them and chained to the previous frame. Image-to-video preserves the still's identity, and motion prompts stay short and describe only what moves, the camera, and the audio. The output includes a compile plan.json, canon character.png and set.png, shot frames, shot videos via Veo 3.1 or Gemini Omni Flash, and a final film.mp4 that is graded, hard-cut, and mixed.
Pricing
Free
Detailed plans have not been confirmed in our catalog. Check the official website for current limits and billing terms.
Visit WebsitePrices and limits may change. Confirm the currency, billing period, seat minimum and usage caps on the official website.
Use Cases
- Teams use FTL Studio to generate a multi-shot film from a single prompt.
- Teams use FTL Studio to keep the same character across multiple AI video clips.
- Teams use FTL Studio to produce a reproducible film recipe with per-shot framing and audio.
- Teams use FTL Studio to approve plans and stills before spending on video.
- Teams use FTL Studio to emit the Veo 3 prompt format automatically.
- Teams use FTL Studio to edit like film with hard cuts and unified grade.
Features
Generate films from one sentence
Plan directed multi-shot sequences
Maintain consistent characters across shots
Maintain consistent sets across shots
Approve character and set stills
Create frames for individual shots
Assemble shots into a final film
Reviews
No reviews yet. Be the first to share your experience!
FAQ
How do I keep the same character across multiple AI video clips?
Generate a canon character still once, then composite every shot's first frame from that image and animate only approved frames. FTL Studio automates this and runs a vision judge on every frame before spending on video.
Can I generate a multi-shot AI film from a single prompt?
Yes — one command compiles the plan, generates the stills, animates each shot, and assembles the finished film.
What is the best prompt format for Veo 3?
Google's official formula: Cinematography + Subject + Action + Context + Style & Ambiance, with audio as separate SFX: and Ambient noise: sentences and dialogue in quotes. FTL Studio emits this automatically.
Which AI video models are supported?
Google Veo 3.1 and Gemini Omni Flash today, selected by one config line. Adapters for Sora, Kling, Runway and Luma are open contribution issues.
Is it free?
The code is MIT licensed and free. Model usage is billed by Google and Anthropic; a --skip-video mode lets you approve plans and stills for cents first.