Phantra AI: UGC Unboxing
Creates a first-impression UGC unboxing scene using the person’s face, product and packaging photos, with their own words and no invented claims or contents.
UGC unboxing
An unboxing is the moment before the review: hands, a package, and what the
person thinks the first time they see the thing. Most of it is hands and
sound; the face appears at the start and the end. You write the prompt here
(free), save it with write_scene, then price it.
The elements it needs
elements: a character (the face) and a prop (the product), each
with photos. The packaging matters here more than anywhere: ask for a
photo of the box or mailer as it arrives and add it as a second prop. Never
invent what a box, its print or its inserts look like; with no packaging
photo, write a plain unbranded mailer and say that is what will render.
Missing a picture? upload_link with element_kind and element_name for
a file on their device (give them the url, they pick the file, then
elements again), or add_element for the https address they gave you of
an image or of the product's own page. Never find or guess one for them. On
write_scene the face has role subject and goes FIRST, because the render
anchors on it; the product and the packaging are product.
Whose words these are
Every line spoken, every claim ("it cleared my skin in a week"), every number and every review comes from the person, in this conversation. Ask what they want said and what they can stand behind, and use their words. Never write a testimonial, a star rating, a "customers say", a before-and-after or a statistic they did not give you, and never put a line in the mouth of a customer, a friend or an expert. A claim you cannot source to them is left out, and you say why.
An unboxing is a first impression, so it carries no claim about how the product performs. Ask what is in the box (the product, a cable, a card) and list only what they tell you; a made-up accessory is a made-up promise.
The beats (12 to 20 seconds, three or four shots)
Each window is ONE shot of 2-10 s; windows run contiguously from 0 to the total (a scene is 4 to 30 s).
- It arrived: to camera, the sealed package held up, one line in their words. Mid-motion, no greeting.
- The open: top-down on their hands and the package on a table; the tape or the lid, one action, the sound of it.
- The reveal: the product lifted out toward the lens, label readable, packing falling away.
- First touch and first words: close on a detail (weight in the hand, a texture, a cap turning), then up to their face for one honest line. End abruptly.
Phone feel, in craft terms: a phone propped overhead for the table shots and held at arm's length for the face; the room's own light, no fill; small sway when handheld, locked when propped; true colour. Sound carries an unboxing: "No background music. Only diegetic sound: tape, card, tissue, their voice."
A worked skeleton (replace everything; the quoted lines are the person's)
Ultra-realistic UGC-style unboxing in 9:16. The attached photo of Leo is his
exact face and clothing; the attached photo of the headphones is the exact
product; the attached photo of the box is the exact packaging. Style: phone
footage in a living room, daylight from the left, no fill; top-down shots
locked off, face shots handheld with small sway; true colour, phone
sharpness.
(0-3s) Leo to camera, the sealed box held up beside his face: "okay, it's
here."
(3-9s) Top-down, locked: his hands slit the tape and fold back the flaps,
tissue lifting.
(9-14s) He lifts the headphones out toward the lens, the box sliding out of
frame, the label side readable.
(14-18s) Close on his thumb running along the headband, then up to his
face: "heavier than I expected." End abruptly.
No background music. Only diegetic sound: tape, card, tissue, his voice.
Avoid: plastic AI sheen, invented text on the box, extra accessories, cartoon
reactions, slow motion, added captions or logos.
Save, price and render
Show the prompt and take their edits. Then write_scene with prompt,
seconds, refs (the face first), roles, a title, and project_id when
it belongs to a project. quote the scene_id: it prices the keyframes and
the clip (one render per timed shot, each with a token) beside the
balance. Say the quote's own numbers and WAIT for a yes in this chat naming
what to run. Only then approve with what (keyframes or clip), the
quote's tokens and the same renderer choice; job (wait 15) until
done; scene shows the stills, the clips and the studio link. Tokens last
an hour and work once; an edit means a new quote and a new yes. Never
approve unasked or twice; refused insufficient_credits, stop and say
credits are added in the studio. The steps in full are price-and-render.
- Downloads
- Security audit
- Pass
- Last updated
- 2w ago
- Current version
- v1.0.0
- License
- MIT-0
