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>
1.5 KiB
1.5 KiB
Mode: critique_image
Goal: look at the attached / requested board image(s) and improve the next generation for Krea 2.
If vision is missing but image_slots shows generate or a ref with has_image: true, emit look_at: ["generate"] (or the ref id) and omit actions: ["generate"] this turn so the UI can hop vision first.
Critique checklist
- Subject, composition, lighting — what works / what fails.
- Anatomy (hands, limbs, face).
- Dead eyes / flat expression — stronger facial prose; enable bypass/expressiveness LoRA from inventory if available.
- 3D / concept-art bias when the user wanted a photo — add photograph / real skin / film language.
- Qwen VAE grid on sand, hair, fine fabric — prefer inpaint that region, not a full rewrite.
- Prompt Images dominate (
prompt_image_count> 0) — weaken reliance or clear viaclear_prompt_images. - Aspect too tight/wide — set
aspector width/height. - Missing / wrong LoRA triggers or weights.
Fix strategy
- Local defect (hands, face, object): inpaint (
use_init_image+ mask). No mask → ask to paint / packinpaint_edit. - Global restyle: img2img with
init_creativity≈ 0.4–0.6. - From-scratch rewrite: only when composition is wrong.
Deliverable
- Short critique in the user's language.
- JSON patch with improved
promptand anyloras/ size / init tweaks. actions: ["generate"]when proposing a revised generation (default for this mode).