Self-hosted, one-tab workbench for the whole training lifecycle: build Character/Concept/Style datasets (generate, scrape, or triage a big dump in the Image Bank), curate, caption, clean watermarks, then train LoRAs on five model families or a full Krea 2 model on a rented GPU, and rank checkpoints in a Test Studio. Free & local.
Windows desktop workspace for local LoRA training. Integrates kohya, musubi-tuner, AI Toolkit and Fizgig with guided setup, dataset tools, sample comparison and local MCP access.
