Add personas and model Cards (0.5.1): tone presets, stem.assistent.json, wanted queue.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
Leonid Pershin
2026-08-21 21:25:01 +03:00
co-authored by Cursor
parent b8145c6455
commit 0b429542b5
10 changed files with 1573 additions and 84 deletions
+6 -1
View File
@@ -72,8 +72,13 @@ Restart / rebuild SwarmUI after clone.
| `fix_params` | Aspect / steps / CFG / seed / batch |
| `inpaint_edit` | Init Image img2img + Mask inpaint |
| `describe_ref` | Vision → Krea prompt (no generate by default) |
| `catalog_card` | Recommendation card JSON for a checkpoint/LoRA |
Live context (checkpoint, server inventory LoRAs + triggers, wildcards, current params) is injected every request.
**Persona** (tone) is a separate dropdown from pack — `base_krea2` → persona → pack. Overlay: `/mnt/swarm_data/Assistent/personas.json` (seeded from gpu-rent `assistent-personas.yaml`).
**Cards** subtab: edit/save `{stem}.assistent.json` next to weights; live chat gets cards for the current checkpoint + enabled LoRAs only. Uninstalled models can enqueue `.gpu-rent-wanted-models.yaml` for the next `up`.
Live context (checkpoint, server inventory LoRAs + triggers, `model_cards`, wildcards, current params, persona) is injected every request.
**Cloud-only Krea.ai features** (moodboards UI, Generative Sliders, Creativity Raw/Low/Medium/High) are **not** in Swarm. The assistant emulates them with prompt language + board refs. Optional patch fields `creativity` / `intensity` / `complexity` / `movement` guide the LLM only.