One-Shot Avatar Sequence: Example Prompt

What This Prompt Produces

A 15-second time-freeze sequence at Santa Monica Pier:

• Opens on a busy pier in full motion
• Your avatar walks calmly toward camera
• They snap their fingers and a shockwave freezes everything in place
• They speak directly to camera mid-freeze
• A playful cotton candy gag with a frozen pedestrian
• They snap again and motion resumes
• They blend back into the crowd

This is a Pattern 1 (Single-Shot Reveal) prompt. Paste it once, get one continuous cinematic.

What You'll Need

HeyGen account with Avatar Shots access.Avatar 5 set up with:A trained voice (referenced via @your-name in the prompt)A character sheet with your desired appearance and outfit (referenced via @character-sheet)

💡 HeyGen @ syntax lets you reference your saved avatar voice and character sheet directly inside the prompt. Swap @dylan and @character-sheet with your own bindings.

The Prompt

use @dylan for the voice and @character-sheet as the appearance and outfit for my avatar in the video.

15-second ultra-photorealistic cinematic time-freeze sequence with an ARRI Alexa Mini look, 50mm lens, natural daylight, strong shadows, shallow depth of field, subtle film grain.

The scene opens at the busy Santa Monica Pier in full motion, captured in a front-facing steadicam shot tracking backward as a man walks calmly toward camera through a natural flow of pedestrians while seagulls cross the bright sky above.

Without breaking stride, he casually raises his hand and snaps his fingers. Instantly, a bright spherical shockwave erupts from his hand, with visible air distortion and refracted light, expanding rapidly across the environment, freezing dust and debris mid-air, locking pedestrians in place mid-motion, and suspending birds mid-flight. Everything falls into complete stillness and silence, with fine particles hanging in the sunlight.

The camera continues gliding backward as he walks through the frozen world. He subtly studies the frozen environment around him, then looks directly into the camera and says:

"This sequence was made entirely inside HeyGen with just a few assets."

As he finishes speaking, he notices a frozen woman with striking blonde hair in a flowing yellow sundress. Her hair is suspended mid-motion as she holds a large pink cotton candy. He approaches her, briefly studies the frozen moment, gently removes the cotton candy from her hand, takes a playful bite, then carefully places it back in the exact same position.

He then turns back toward the camera, raises his hand again, and snaps his fingers. A more powerful spherical shockwave bursts outward, rapidly spreading across the pier and reversing the effect. Motion instantly resumes—pedestrians continue walking naturally, birds scatter into flight, the woman carries on completely unaware while still holding the cotton candy, suspended debris falls naturally to the ground, and the full ambient sound of the pier returns.

He pauses for a brief beat, gives a subtle knowing smile, then continues walking forward, gradually blending into the crowd while the camera keeps tracking backward, maintaining distance as he disappears into the flow of people.

Ultra-realistic physics, cinematic VFX, seamless time-freeze transitions, volumetric lighting, realistic shockwave refraction, natural human motion, perfect object continuity, Hollywood-level visual effects, highly detailed facial performance, photorealistic crowd simulation, natural audio transitions, premium commercial quality. [no music]

Plug-and-Play Template

Copy the template below and fill in the bracketed parts for your own one-shot. The structure mirrors the Santa Monica example: setup, first action, dialogue, optional mid-beat, second action, resolution, VFX closer. Leave the unbracketed text as-is.

use @[VOICE_NAME] for the voice and @[CHARACTER_SHEET_NAME] as the appearance and outfit for my avatar in the video.

[DURATION, e.g. 15-second] ultra-photorealistic cinematic [GENRE/EFFECT, e.g. time-freeze sequence] with an ARRI Alexa Mini look, 50mm lens, [LIGHTING, e.g. natural daylight], strong shadows, shallow depth of field, subtle film grain.

The scene opens at [LOCATION, e.g. the busy Santa Monica Pier] in full motion, captured in a [CAMERA SHOT, e.g. front-facing steadicam tracking backward] as my avatar walks calmly toward camera through [ENVIRONMENTAL DETAILS, e.g. a natural flow of pedestrians while seagulls cross the bright sky].

[FIRST TRIGGER ACTION, e.g. Without breaking stride, he raises his hand and snaps his fingers]. Instantly, [VFX EFFECT: be specific about visual and physical impact]. Everything falls into [NEW STATE, e.g. complete stillness and silence].

The camera continues gliding backward as the avatar moves through the changed world. He subtly [MID-EFFECT BEAT, e.g. studies the frozen environment around him], then looks directly into the camera and says:

"[YOUR EXACT SPOKEN LINE HERE]"

[OPTIONAL CREATIVE BEAT, e.g. a playful or surprising moment that uses the established effect. Skip this if your sequence is more focused.]

[SECOND TRIGGER ACTION, e.g. He turns back toward camera, raises his hand, snaps his fingers again]. [VFX REVERSAL: describe how the effect resolves and motion returns to normal].

[RESOLUTION, e.g. He pauses, gives a subtle smile, then continues walking forward, blending into the crowd as the camera keeps tracking backward].

Ultra-realistic physics, cinematic VFX, [SIGNATURE VFX KEYWORDS: pick 2 to 3 specific to your effect], volumetric lighting, natural human motion, perfect object continuity, Hollywood-level visual effects, highly detailed facial performance, photorealistic crowd simulation, natural audio transitions, premium commercial quality. [no music]

💡Tip: The more specific you are inside the brackets, the better the result. Vague placeholders like "a place" or "a vibe" give vague videos. Mirror the level of detail in the Santa Monica example.

Assets Used (Starting Frame + Character Sheet)

Why This Prompt Works

Six techniques that make this one-shot prompt deliver:

• Avatar binding via @ syntax. @dylan (voice) and @character-sheet (appearance) lock identity in from the first frame.
• Camera spec up front. ARRI Alexa Mini, 50mm, shallow depth of field, film grain. Gives the model a specific cinematographic baseline.
• Beat-by-beat choreography. The prompt walks through every action in order: walk → snap → freeze → speak → cotton candy gag → snap → unfreeze → walk away. No ambiguity for the model.
• Embedded dialogue in quotes. The exact spoken line lives inside the prompt, so the avatar delivers it word-for-word.
• VFX vocabulary at the end. Volumetric lighting, shockwave refraction, perfect object continuity. These tell the model what kind of VFX you want.
• [no music] tag at the very end. Stops the model from layering its own soundtrack on top.

Customize This for Your Scene

To adapt this prompt for your own one-shot sequence:

1. Swap the avatar bindings. Replace @dylan with your voice handle and @character-sheet with your appearance reference.'
2. Change the location. Santa Monica Pier → your setting (NYC subway, mountain trail, conference floor, anywhere).
3. Rewrite the beat sequence. Keep the structure: action → trigger → effect → dialogue → second action → resolution → exit. Swap the specific beats.
4. Update the spoken line. Drop your new dialogue in quotes after says:.
5. Keep the VFX vocabulary at the end unless you're going for a different visual style.
6. Keep [no music] unless you want a soundtrack.

✅ Ready to ship when: Your generated MP4 shows your avatar (face and outfit matching the character sheet), the spoken line plays exactly as written, the time-freeze effect lands cleanly, and the sequence resolves with your avatar walking back into the crowd.