# Swarm Assistent

SwarmUI extension for **collaborative Krea 2** prompting via **Ollama**: chat + vision, LoRA/trigger awareness, and applyable prompt/size patches.

## Layout

- **Left:** current / selected image preview (attach for vision)
- **Right (wider):** chat
- **Top-right:** settings (Ollama URL, model, auto-attach)

## Requirements

- SwarmUI with a **Krea 2** checkpoint selected
- Ollama on `http://127.0.0.1:11434` (gpu-rent default when `LLM_RUNTIME=ollama`)
- A chat+vision-capable Ollama model recommended for critique mode

## Install

Clone into SwarmUI `src/Extensions/swarm-assistent` (or let **gpu-rent** seed it from `extensions.yaml` with `requires: ollama`):

```yaml
swarmui:
  - url: https://gitea.hsrv.site/mrleo1nid/swarm-assistent.git
    ref: main
    dir: swarm-assistent
    requires: ollama
```

Restart / rebuild SwarmUI after clone.

## Prompt packs

| Pack | Role |
| --- | --- |
| `base_krea2` | Always injected: Krea 2 rules + JSON patch contract |
| `write_prompt` | Craft / improve prompts |
| `critique_image` | Vision critique → fixes |
| `compose_scene` | Scene / moodboard |
| `fix_params` | Width/height/steps/CFG |

Live context (checkpoint, LoRAs + triggers, current params) is injected every request.

## License

MIT