Leonid PershinandCursor
5f33130381
Client always merges Exact turbo|raw steps/cfg/sigma before Generate so sparse LLM omissions and leftover SD 20/7 cannot stick; Ollama park/warm skip no-op /api/ps round-trips when the chat model is already unloaded or resident. Co-authored-by: Cursor <cursoragent@cursor.com>
1.6 KiB
1.6 KiB
Mode: fix_params
Goal: adjust generation parameters for Krea 2 Turbo (or RAW if context says so).
Guidelines
- Prefer Exact memory (
profiles.turbo/profiles.raw), liverecommended_params, andsession_exactover invented numbers. Never CFG 0. - Prefer live context field
krea_profile(turbo|raw) when present. On Generate the client also fills Exact turbo|raw when the patch omits steps/cfg/sigma — emit those fields when you are changing them. If session steps/cfg disagree with that profile (leftover 20/7), patch Exact numbers even under a sparse delta. - Aspect: prefer patch field
aspectfrom Exactaspect_table— UI maps to official 1K sizes. Else set width/height near 1024. - Batch:
imagesorbatch(1–4 typical). - Seed:
lock_seed: trueto reuse current;vary: trueorseed: -1for a new roll; set numericseedfor exact reproducibility. - Sampler/scheduler: leave alone unless the user asks (Swarm default is fine; community Turbo often Euler + Simple).
- Init creativity only when
has_init_imageor enabling img2img — seeinpaint_edit. - Do not change the prompt unless needed for the new framing.
- Keep LoRAs unless asked to drop them.
- User’s requested params for this turn beat Exact; do not silently roll them back to Exact defaults.
Deliverable
- Explain the param change.
- JSON patch focusing on
aspect/width/height/steps/cfg/seed/sigma_shift/images/vary/lock_seed(andpromptonly if necessary). actions: ["generate"]if the user wants to re-roll with the new params.