What you'll make
A checked final video that follows the source workflow and is ready for export.
Create multiple camera angles from one shot
Who this is for
Creators, marketers, founders, and small teams producing short AI-assisted videos from source media.
Step by step
Run the workflow
- 01
Workflow behind how I made this exact video
Use the source inputs to complete this stage and produce a result that can be checked before continuing.
- Click here to open Google Flow (opens in a new tab)Official tool link added because the source does not include a working tool destination.
- These are key frames from my reel. This source breaks down the full

Use this visual to confirm the expected setup or result. 
Use this visual to confirm the expected setup or result. 
Use this visual to confirm the expected setup or result. 
Use this visual to confirm the expected setup or result. 
Use this visual to confirm the expected setup or result. Common failure modes- The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
- Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
- 02
Prepare the source material
Use the source inputs to complete this stage and produce a result that can be checked before continuing.
- Record a talking video of yourself.

Use this visual to confirm the expected setup or result. Common failure modes- The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
- Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
- 03
Use the supplied prompts
Use the source inputs to complete this stage and produce a result that can be checked before continuing.
- Modify the provided prompts and for Phase 3. Phase 2: Use My Prompts Phase 2: Use My Prompts
- Change the purple text
- Maintain the original room, environment, lighting, and the person's identity exactly as they are. Do not alter the face, facial features, hairstyle, clothing, body proportions, room layout, background objects, or overall appearance. The room and the person must remain perfectly consistent throughout the entire video.
- Do not modify the dialogue, voice, speech timing, pacing, lip sync, facial performance, or audio in any way. The spoken content must remain identical to the source. The only changes should be the virtual camera framing and angle.
- Use fast, clean hard cuts between camera angles. Do not morph, blend, interpolate, zoom, or animate the transition. Every camera change should feel like an instant cut to another camera while maintaining perfect continuity.
- * At [X] to [X]: Cut to a left-side B-roll style framing. Keep the subject naturally speaking to the original conversation while viewed from the left.
- * At [X] to [X]: Hard cut to a slightly high angle. The man briefly looks upward toward the camera while continuing to speak naturally. Do not change the speech or expression beyond the required eye direction.
- * At [X] to [X]: Hard cut to an extreme close-up focused on the eyes and upper face. Preserve facial proportions and identity exactly.
- * At [X] to [X]: Hard cut back to the original camera position and framing, matching the opening shot perfectly.
- Critical requirements:
- * Preserve the person's face exactly. * Preserve the room exactly. * No changes to audio. * No changes to speech pacing or timing. * No changes to lip sync. * No changes to facial identity or room layout. * Only the camera position changes through hard cuts. * Every shot should appear as if captured simultaneously by multiple professional cameras in the same room.
Common failure modes- The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
- Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
- 04
Generate the video from the prompt
Use the source inputs to complete this stage and produce a result that can be checked before continuing.
- Now Generate the video from scratch without needing any asset.
- Input the edited prompt 1

Check the prompt field, reference order, and visible settings. 
Check the prompt field, reference order, and visible settings. Common failure modes- The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
- Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
Before you use it
Final checks
- Check the full result for changed people, products, text, timing, or layout.
- Confirm the tool, model, controls, and cost before generating.
- Keep private or unreleased material out of third-party tools.
Share your work
Made it? Show me.
Post your finished result on Instagram and tag @terencesia. I'll share a few standout results with the community.
Tag @terencesia on Instagram (opens in a new tab)Next step
Run one low-cost test, record the first visible failure, and revise only the instruction or source asset tied to that problem.
Back to the tutorial library