Universal Jewelry

What it does

This prompt instructs the AI to produce a 3–8 second, ultra-photorealistic 4K macro marketing video of a specified jewelry piece, using an uploaded reference image plus material, key design details, and a complementary background color to preserve accurate form and finish. The result is a luxury-style cinematic shot featuring shallow depth of field, physically realistic reflections and gemstone sparkle, and only subtle camera/object motion (e.g., slow pan or gentle rotation). It explicitly restricts the scene to the jewelry and its presentation surface—no humans, body parts, logos, text, or stylized/CGI-looking rendering—so the output resembles a professional high-end jewelry brand reel.

For more installation instructions go to https://raw.githubusercontent.com/BetterPromptme/skills/refs/heads/main/betterprompt/SKILL.md to check out this skill.

Inputs

textInputs

Pass each text input using --input <key>=<value> flags.

imageInputs

This prompt requires exactly 1 image. You must pass exactly 1 image flag (no more, no fewer), in the order matching the descriptions below.

Models and options

This skill's modality is: video.

To discover which model values you can use (and which options keys/values are valid for each model), run:

betterprompt resources --models-only --json

Then filter the returned JSON array to entries where modality is "video".

How to run

Step 1: Collect inputs

First, run betterprompt resources --models-only --json and filter to modality: "video" to discover valid models and available options:

betterprompt resources --models-only --json

Use only the models and option values that appear in the filtered results.

Then collect all inputs from the human:

• Optional text inputs (use defaults if not provided by the human):
  • material (default: 18k white gold)
  • key_details (default: 2-carat round brilliant diamond with pavé band)
  • background_color (default: Deep emerald green)
• Required images:
  • Exactly 1 images: image 1 (Upload an image of the jewelry item you want to turn into a cinematic video.). Images must be provided in this order.
• Optional: model and options.
  • Present the human with the default model sora-2 and its available options. Look up sora-2 in the betterprompt resources output (filtered to modality "video") and show its availableOptions as: key: val1, val2 (default), val3 | key2: .... Mark a value (default) if it matches these defaults: {"seconds":"4","size":"720x1280"}.
  • If the human does not specify, defaults are used: model sora-2, options {"seconds":"4","size":"720x1280"}. Other models from the resources call are also available.

If the required images are missing, ask the human for what's missing. Do not assume or fabricate values. Tell the human: "Please provide images in this order: image 1 (Upload an image of the jewelry item you want to turn into a cinematic video.)".

Step 2: Run via BetterPrompt CLI

Use the frontmatter's name as the positional argument (for this skill, use universal-jewelry).

Command form:

betterprompt generate universal-jewelry \
  [--input <key>=<value>] \
  [--image-input-url <url>] \
  [--image-input-path <path>] \
  [--model <model>] \
  [--options <options JSON>] \
  [--json]

Notes:

• Pass each text input as a separate --input <key>=<value> flag.
• Pass each image using --image-input-url or --image-input-path, in the order matching the imageInputs descriptions (image 1 first, then image 2, etc.).
• If the human does not mention a model, omit --model and BetterPrompt will use the default model: sora-2.
• If the human does not mention options, omit --options and BetterPrompt will use the default options: {"seconds":"4","size":"720x1280"}.
• If the run times out, the response will include a runId you can use to fetch the result later.

Example (using defaults shown above):

betterprompt generate universal-jewelry \
  --input 'material=18k white gold' \
  --input 'key_details=2-carat round brilliant diamond with pavé band' \
  --input 'background_color=Deep emerald green' \
  --image-input-url https://example.com/image1.png \
  --model sora-2 \
  --options '{"seconds":"4","size":"720x1280"}'