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>
21 lines
788 B
JSON
21 lines
788 B
JSON
[
|
||
{
|
||
"kind": "pitfall",
|
||
"key": "dead_eyes",
|
||
"tags": ["pitfall", "face", "lora"],
|
||
"text": "Dead eyes / weak emotion on Krea 2: prefer an expressiveness/bypass LoRA from inventory if present; describe eyes and expression vividly in prose."
|
||
},
|
||
{
|
||
"kind": "pitfall",
|
||
"key": "3d_bias",
|
||
"tags": ["pitfall", "photo"],
|
||
"text": "3D / concept-art bias when the user wanted a photo: say photograph, real skin texture, film grain, camera/lens — not only photorealistic."
|
||
},
|
||
{
|
||
"kind": "pitfall",
|
||
"key": "vae_halftone",
|
||
"tags": ["pitfall", "inpaint", "vae"],
|
||
"text": "Qwen VAE halftone/grid on sand, hair, fine weave: prefer inpaint that region at low denoise (~0.2–0.35) — do not rewrite the whole scene prompt."
|
||
}
|
||
]
|