Per-chat Generate session with sparse deltas; drop Cards/Civitai/wanted hops; rolling history summary via the same Ollama model with a budget chip and /compress. Co-authored-by: Cursor <cursoragent@cursor.com>
2.2 KiB
2.2 KiB
Skill: prompting
The chat model prepares the Generate-box text for Krea 2 (Qwen3-VL). Do this prep as fully as you can in the same turn (or the dedicated prep hop). Chat with the user may be RU/EN; the JSON prompt is always English.
Hard rules (Krea / Qwen3-VL)
promptlanguage = English only — never put Russian into the JSONprompt. Translate the idea, then structure it.- Natural photographer/director prose — not Danbooru tag soup, not
(word:1.5), notmasterpiece / best quality / 8k. - Order (front-load):
subject → pose/action → body/wardrobe → setting → materials/textures → camera/framing → lighting → medium/mood. - Put LoRA trigger phrases (exact English spelling) near the subject they affect.
negativeon every Generate — create if live is empty (Exactgeneration.negative), supplement if the scene needs a specific omit, or echo live unchanged. Put “no blur / no people” ideas as positives inpromptinstead of stuffing the negative box. Never clearnegative.- Short ideas: expand into a full Krea paragraph. Thin or RU drafts: rewrite before Generate — do not hand Krea a half-ready line.
Prep checklist (before "generate": true)
- English only in
prompt negativepresent when needed (new / supplemented / echoed — not omitted if live empty)- Subject and action clear in the first sentence
- Wardrobe / body / setting concrete
- Camera + lighting present
- One coherent scene; NSFW stated in plain English if needed
- Triggers placed next to what they modify
- Only changed fields in the JSON — session already holds the rest
Deliverable
User-facing prose: short, in the user’s language.
JSON prompt: English, structured as above — ready for Swarm Generate / Krea 2.
Bad → good
Bad: cute fox, snow, masterpiece, best quality, 8k, detailed, no blur
Good: A fluffy red fox sitting alert in fresh powder snow, ears forward, breath faintly visible in the cold air, soft morning light from the left catching orange fur and casting long blue shadows, shot on an 85mm lens at f/2.8 with creamy bokeh, calm winter atmosphere, sharp eyes and whiskers.