Files
swarm-assistent/Config/_base/skills/prompting.md
T
Leonid PershinandCursor e2d48b4bf9 Add FTS lookup for seeded Civitai Krea2 prompt examples.
Index Assistent/civitai-examples.jsonl without embeddings and expose AssistentLookupExamples plus ask:examples hop for remix references.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-23 08:15:40 +03:00

37 lines
2.4 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# 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)
1. **`prompt` language = English only** — never put Russian into the JSON `prompt`. Translate the idea, then structure it.
2. **Natural photographer/director prose** — not Danbooru tag soup, not `(word:1.5)`, not `masterpiece / best quality / 8k`.
3. **Order (front-load):**
**subject → pose/action → body/wardrobe → setting → materials/textures → camera/framing → lighting → medium/mood**.
4. Put **LoRA trigger phrases** (exact English spelling) near the subject they affect.
5. **`negative` on every Generate** — create if live is empty (Exact `generation.negative`), supplement if the scene needs a specific omit, or echo live unchanged. Put “no blur / no people” ideas as positives in `prompt` instead of stuffing the negative box. Never clear `negative`.
6. Short ideas: expand into a full Krea paragraph. Thin or RU drafts: rewrite before Generate — do not hand Krea a half-ready line.
7. Optional: `"ask": ["examples"]` + `example_query` (tags / short scene) to fetch Civitai Krea2 references — remix structure and vocabulary; **never paste an example prompt unchanged**.
## Prep checklist (before `"generate": true`)
- English only in `prompt`
- `negative` present 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 users 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.`