Seedance Prompt Library

A structured template library for writing Seedance 2.5 / 2.0 video prompts, sourced from references/style-library.md — templates distilled from real, human-verified, high-heat cases on goodcase.ai. Do not invent prompt structure from general video-generation knowledge when a matching template exists here; use the template.

Workflow

1. Identify intent. Work out what kind of shot the user wants: narrative short, ad/commercial, UGC talk-to-camera, dialogue with lip-sync, action/movement, product reveal, retro found footage, travel, pets and animals, comedy, horror, fantasy or sci-fi spectacle, 3D cartoon, cars, fashion and portrait, sports, storyboard grid to video, or something else. The reference file lists every template with its useWhen; skim those headings first. Ask a clarifying question only if the intent is genuinely ambiguous (e.g. "a video of my product" could be a commercial orbit shot or a UGC review — ask which).

2. Select a template. Read references/style-library.md and pick the template whose useWhen matches the identified intent. If no template matches closely, say so and build the prompt from first principles instead of forcing a mismatched template.

3. Fill the structure. Walk the template's structure field block by block (shot type, subject, setting, camera behavior, etc.) and fill each with specifics from the user's request. Don't skip blocks — an empty block in the structure is where prompts usually go generic and vague.

4. Apply guidance, avoid pitfalls. Cross-check the draft against the template's guidance and pitfalls lists before finalizing. These come from what actually worked (or broke) in real published cases, not general advice.

5. Output. Return:

   • The finished prompt as a single copy-pasteable block.
   • Which template was used (by title).
   • Links to the template's exampleCaseUrls so the user can see it working on goodcase.ai.