Move prompts into Config/_base and persona folders; seed model facts into SQLite via Ollama embed and retrieve as memory_hits each turn. Co-authored-by: Cursor <cursoragent@cursor.com>
9 lines
315 B
JSON
9 lines
315 B
JSON
{
|
|
"categories": ["cinematic", "portrait"],
|
|
"styles": ["film still", "editorial"],
|
|
"aspects": ["2.35:1", "16:9", "4:5"],
|
|
"lighting": ["key/fill/rim", "practicals"],
|
|
"camera": ["focal length feel", "depth of field", "blocking", "camera movement"],
|
|
"notes": ["lens, framing, lighting, blocking"]
|
|
}
|