Leonid PershinandCursor
fe4d8d3a3a
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>
33 lines
1.7 KiB
JSON
33 lines
1.7 KiB
JSON
[
|
||
{
|
||
"kind": "model",
|
||
"key": "krea2_architecture",
|
||
"tags": ["krea", "architecture"],
|
||
"text": "Krea 2 is a 12B DiT architecture. Not FLUX, not SDXL, not FLUX.1-Krea. Text encoder: Qwen3-VL 4B. VAE: Qwen Image VAE. Use only Krea2-trained LoRAs — never suggest FLUX/SDXL LoRAs."
|
||
},
|
||
{
|
||
"kind": "model",
|
||
"key": "krea2_turbo",
|
||
"tags": ["krea", "turbo", "params"],
|
||
"text": "Krea 2 Turbo defaults: steps 8 (min 4), CFG 1 (never CFG 0 — broken output), sigma shift 1.15, side ~1024 (128–4096 OK)."
|
||
},
|
||
{
|
||
"kind": "model",
|
||
"key": "krea2_raw",
|
||
"tags": ["krea", "raw", "params"],
|
||
"text": "Krea 2 RAW/Base: steps ~20–52, CFG ~4–4.5. If checkpoint name/title looks like RAW (not Turbo), prefer RAW settings. If a turbo LoRA exists, weight ~0.6 for photoreal (1.0 ≈ full turbo). Swarm Generate cannot run dual-sampler Comfy graphs — only suggest LoRA weight + steps/CFG the UI can set."
|
||
},
|
||
{
|
||
"kind": "model",
|
||
"key": "krea2_negatives",
|
||
"tags": ["krea", "prompting"],
|
||
"text": "Negative prompts are nearly useless with Qwen3-VL. Prefer positives (sharp focus, empty street) over no blur / no people. Built-in NSFW text-refiner may strip risque words; LoRAs/finetunes may restore — stay practical."
|
||
},
|
||
{
|
||
"kind": "model",
|
||
"key": "krea2_prompt_images",
|
||
"tags": ["krea", "board"],
|
||
"text": "Prompt Images (refs in the prompt box) often overpower text — use sparingly and warn. Init Image = structure (img2img). Mask = local fix. They are not interchangeable. Cloud-only features (moodboards, Generative Sliders) are not in Swarm — emulate with prompt language + board refs."
|
||
}
|
||
]
|