Input: instructor reference sheet and approved script
Output: consistent instructor shots across modules
Aspect: 16:9 for courses; 9:16 for social explainers
Build log
1. Build a reference sheet
I save frontal face, side profile, clothing, hair, background, and light. Without clothing and light, the “same person” often fails between lessons.
2. Test identity at 5 seconds
I keep the same camera and gesture and change only the lesson line. Agnes Video at 10 credits is enough to reject a bad reference.
3. Upgrade only the winner
After identity passes, I render the approved line on Seedance 480p at 90 credits for 5 seconds or Kling without audio at 195 credits for 5 seconds.
4. Save the module set
I tag the reference set and approved prompt in the asset library. The next lesson starts from the same instructor, not a new idea.
Complete execution record
Task boundary and source gate
Treat AI virtual instructor video as a deliverable, not a definition. The job receives instructor reference sheet and approved script and owes consistent instructor shots across modules in 16:9 for courses; 9:16 for social explainers. Write the rejection reason first, then turn it into the first hard constraint.
Require the objective verb, terminology sheet, worked example, assessment item, and the source of any claim. If a slide contains two ideas, split the node before spending credits. Do not let a caption introduce a claim that the approved source does not contain. A pretty diagram cannot override wrong terminology.
The imgmov route
Break the outline into Canvas nodes before generating media: one observable objective, one example, one check. Slides, notation, and approved screenshots are references. Subtitles, review questions, and progress markers go to the external editor after picture lock.
Keep platform requirements outside the model prompt. The prompt can describe a scene; a named checklist records the crop, claim, consent, and console check that make it deliverable.
Lock the variables that cannot drift
Lock terminology, notation, example numbers, instructor identity, clothing, background light, diagram style, and caption format. A course should feel like one teacher with one method.
Put the locked fields at the top of the prompt, not at the end: Lock identity before content. Reuse the same reference sheet and shot length; change only the sentence. A 5-second Agnes probe is 10 credits, so identity tests stay cheap before a paid Seedance or Kling render. Save that prompt with the reference, ratio, and model so the next run starts from a decision instead of a guess.
Step-by-step build path
1) Build a reference sheet: I save frontal face, side profile, clothing, hair, background, and light. Without clothing and light, the “same person” often fails between lessons. Leave one checkable artifact from this step; do not start the next until it exists. 2) Test identity at 5 seconds: I keep the same camera and gesture and change only the lesson line. Agnes Video at 10 credits is enough to reject a bad reference. Leave one checkable artifact from this step; do not start the next until it exists. 3) Upgrade only the winner: After identity passes, I render the approved line on Seedance 480p at 90 credits for 5 seconds or Kling without audio at 195 credits for 5 seconds. Leave one checkable artifact from this step; do not start the next until it exists. 4) Save the module set: I tag the reference set and approved prompt in the asset library. The next lesson starts from the same instructor, not a new idea. Leave one checkable artifact from this step; do not start the next until it exists.
Change one named variable per rerun: prompt, reference, camera, duration, model, ratio, or export crop. If two variables change together, a better output cannot be reused because nobody knows which fix worked.
Review gates and evidence
Mute the video and read the captions. Then play it once and ask whether the learner can complete the ending check without rewinding.
Keep source, approved wording, rejected version, correction, credit cost, and final crop next to the asset. The record exists so the next reviewer can reproduce the decision without a chat thread.
Failure diagnosis and retry ladder
If learners fail the check, cut a concept instead of adding a recap. If notation drifts, return to the approved slide. If captions lag, split the sentence at a phrase boundary.
Do not upgrade on hope. A 5-second Agnes Video probe is 10 credits. If the concept passes, Seedance 2.5 costs 90 credits at 480p or 195 at 720p for 5 seconds; Kling is 195 without audio or 245 with audio. Veo enters only when a 4/6/8-second cinematic bucket is genuinely worth 80/125/165 credits. Prove hook, subject, and rhythm first, then pay to clean up motion that already worked.
Versioning and handoff
Deliver classroom, mobile, and captioned versions separately. Save the objective, reference set, prompt, and check as the next module's starting point.
The folder is boring on purpose: source, approved reference, generation settings, caption file, platform cuts, QA screenshots, and one correction line. A reusable asset is boring in the right way.
Why this is not a generic answer
The imgmov advantage is the chain: Asset Library preserves the subject reference, Canvas fixes shot order and first/last frames, the workspace routes Agnes to Seedance, Kling, or Veo only after proof, and your external editor adds captions and CTA without regenerating the media.
Do not let a caption introduce a claim that the approved source does not contain. A pretty diagram cannot override wrong terminology. If the request only asks what ai virtual instructor video means, a search page is faster. This page is useful when someone must deliver consistent instructor shots across modules under real constraints.
Frequently asked questions
Can it replace a real instructor?
It can present approved material. It should not impersonate a real person without rights.
The workflow is specific about its stopping point: it starts with instructor reference sheet and approved script and stops at consistent instructor shots across modules. In imgmov, upload the source, lock it as a reference, set 16:9 for courses; 9:16 for social explainers, run one proof, and save the passing settings. If a reviewer cannot tell which version is approved, the workflow has failed even when the media looks good.
What usually breaks consistency?
Changing clothing, light, camera distance, or the gesture set between lessons.
Do not upgrade on hope. A 5-second Agnes Video probe is 10 credits. If the concept passes, Seedance 2.5 costs 90 credits at 480p or 195 at 720p for 5 seconds; Kling is 195 without audio or 245 with audio. Veo enters only when a 4/6/8-second cinematic bucket is genuinely worth 80/125/165 credits. Prove hook, subject, and rhythm first, then pay to clean up motion that already worked.
How much is an identity test?
A 5-second Agnes Video probe is 10 credits.
The check is not “does it look AI-nice?” It is: Mute the video and read the captions. Then play it once and ask whether the learner can complete the ending check without rewinding. Then the source, approved copy, rejected version, correction, and final crop stay in the same handoff folder.
When should I use Kling?
When the approved shot needs native audio and 5 or 10 seconds; audio costs 49 credits/second instead of 39 credits/second without audio.
If learners fail the check, cut a concept instead of adding a recap. If notation drifts, return to the approved slide. If captions lag, split the sentence at a phrase boundary. Change one named variable, keep the old version, and record the credit cost. If the same failure repeats, fix the reference or scope rather than asking the prompt for forgiveness.
How do I reuse the instructor?
Save the reference sheet, prompt, ratio, camera, and light as one named asset set.
The imgmov advantage is the chain: Asset Library preserves the subject reference, Canvas fixes shot order and first/last frames, the workspace routes Agnes to Seedance, Kling, or Veo only after proof, and your external editor adds captions and CTA without regenerating the media. The handoff is reusable only when the source, reference ID, prompt, model, cost, rejection reason, and approved cut are linked. That chain is what makes the next ai virtual instructor video task faster.