Free local LoRA training studio: build character, style and concept datasets from one photo or a big image folder, caption them (JoyCaption, prose or booru tags), train LoRAs with ai-toolkit for Krea 2, FLUX.1, FLUX.2 Klein, Qwen-Image 2.1, Z-Image, SDXL and Anima, then compare checkpoints side by side. ComfyUI-powered, self-hosted.
flux self-hosted image-captioning lora text-to-image fine-tuning ai-toolkit diffusion-models dataset-preparation stable-diffusion generative-ai comfyui sdxl lora-training joycaption krea qwen-image character-consistency z-image lora-dataset
-
Updated
Nov 16, 2026 - Python