New AI Filmmaking Workflow for Better Shot Control
Shows filmmakers how to bypass text prompt ambiguity by chaining rough hand-drawn sketches and timestamped video references within agentic workflows for granular scene control.
What this lesson covers
AI Video School demonstrates how to achieve precise shot framing and action choreography by combining hand-drawn Post-it note sketches with conversational prompting in CapCut's agentic mode. The resulting generation is then repurposed as a video reference in Seedance 2.0 with timestamped prompts to direct a continuous single-take action sequence.
Key takeaways from the creator
AI-extracted notes, not independently verified product claims. Timestamp links let you check each point in the original video.
- 0:38 ↗
Using a rudimentary hand-drawn sketch allows AI video generators to accurately interpret complex composition and framing where text prompts and start frames fail.
- 1:43 ↗
Describing a sketch in natural language within an agentic mode provides camera direction (e.g., horizontal tracking) and character actions without rigid prompting formulas.
- 2:25 ↗
Chaining an initial sketch-generated video output into Seedance 2.0 as a video reference enables advanced refinement of action and timing.
- 2:32 ↗
Breaking down complex multi-beat sequences into discrete timestamp brackets (e.g., 0-2s, 2-4s, 4-6s) provides precise pacing for unbroken single-take shots.
Workflow outlined in the video
- Draw a basic Post-it note sketch indicating scene framing, subject positioning, and direction of movement using simple visual cues like arrows.
- Upload the sketch to CapCut's agentic mode and describe the desired shot framing, camera movement, and character action in natural language.
- Generate the initial shot and review it for basic framing and compositional adherence.
- Import the initial generation into Seedance 2.0 as a video reference.
- Write a prompt structured with second-by-second timestamp segments detailing the specific sequence of actions to lock in pacing.
Before you use this workflow
These notes describe the source video at its publication date. Model access, pricing, connectors and interfaces may have changed. Check the original source and the provider’s current documentation before installing an add-on, connecting an account or spending credits.
ReelStack has not independently tested this workflow. Preview one representative shot and check motion, continuity and output quality before applying it to a full production. No result, cost saving or model capability is guaranteed.
Explore the tools
How to interpret the numbers
3,044 views captured 27 September 2026. ReelStack recommendation score: 23/100. Formula: radar-v5. This is ReelStack’s calculation, not a YouTube rating or a measure of factual accuracy.
Show the calculation
- 65% performance: 0.32× current views vs the channel's recent median; same-age history is not yet available. View-evidence factor 75% (views / (views + 1,000))
- 25% freshness: 5/100 with a 14-day half-life
- Momentum pending: collecting daily snapshots; its 20% weight goes to observed performance, not free points
- 10% engagement: 100/100; likes + 4× comments, smoothed with a 500-view neutral prior