Fizgig — LoRA & Fine-tune Studio for Klein 9B, Krea 2, MiniMax H3, Qwen Image 2.1, Anima & Z-Image Turbo: train, fine-tune, profile, repair and extract LoRAs & LoKRs
-
Updated
Oct 7, 2026 - Python
Fizgig — LoRA & Fine-tune Studio for Klein 9B, Krea 2, MiniMax H3, Qwen Image 2.1, Anima & Z-Image Turbo: train, fine-tune, profile, repair and extract LoRAs & LoKRs
Extract a LoRA from the difference between two MODEL objects in ComfyUI. Capture chained edits (LoRAs, layer scaling, merges, IP-Adapter, patches) as a single distributable .safetensors file.
Train, fine-tune, and manage LoRA (SFT) models on your own GPU via an intuitive web UI — select hardware, datasets, and configs effortlessly.
To associate your repository with the lora-extraction topic, visit your repo's landing page and select "manage topics."