Bump Assistent to 0.7.0: Config personas, skills, and vector memory.

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>
This commit is contained in:
Leonid Pershin
2026-08-21 22:47:04 +03:00
co-authored by Cursor
parent 46264d7227
commit fe4d8d3a3a
72 changed files with 2593 additions and 507 deletions
+50
View File
@@ -0,0 +1,50 @@
[
{
"kind": "aspect",
"key": "1:1",
"tags": ["aspect", "1k"],
"text": "Aspect 1:1 maps to 1024×1024 on the official Krea 1K table. Prefer patch field aspect over raw width/height."
},
{
"kind": "aspect",
"key": "4:3",
"tags": ["aspect", "1k"],
"text": "Aspect 4:3 maps to 1184×896."
},
{
"kind": "aspect",
"key": "3:2",
"tags": ["aspect", "1k"],
"text": "Aspect 3:2 maps to 1248×832."
},
{
"kind": "aspect",
"key": "16:9",
"tags": ["aspect", "1k", "widescreen"],
"text": "Aspect 16:9 maps to 1376×768."
},
{
"kind": "aspect",
"key": "2.35:1",
"tags": ["aspect", "1k", "cinematic"],
"text": "Aspect 2.35:1 (cinematic ultrawide) maps to 1568×672."
},
{
"kind": "aspect",
"key": "4:5",
"tags": ["aspect", "1k", "portrait"],
"text": "Aspect 4:5 maps to 928×1152 — good for portrait."
},
{
"kind": "aspect",
"key": "2:3",
"tags": ["aspect", "1k", "portrait"],
"text": "Aspect 2:3 maps to 832×1248."
},
{
"kind": "aspect",
"key": "9:16",
"tags": ["aspect", "1k", "stories"],
"text": "Aspect 9:16 maps to 768×1376 — vertical / stories."
}
]
+32
View File
@@ -0,0 +1,32 @@
[
{
"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 (1284096 OK)."
},
{
"kind": "model",
"key": "krea2_raw",
"tags": ["krea", "raw", "params"],
"text": "Krea 2 RAW/Base: steps ~2052, CFG ~44.5. 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."
}
]
+20
View File
@@ -0,0 +1,20 @@
[
{
"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 (~0.20.35) — do not rewrite the whole scene prompt."
}
]