Anima LoRA Trainer for ComfyUI

A ComfyUI custom node pack for training LoRA / LoKR / LoHA models on the Anima architecture using kohya-ss/sd-scripts. Train Anima LoRAs directly from ComfyUI with zero command-line knowledge required.

Installation

Download and extract the zip into your ComfyUI/custom_nodes/ folder, then restart ComfyUI. The nodes will appear under the "Anima Training" category.

Features

• One-click model downloading from HuggingFace (always fetches the latest Anima base model)

• Two workflow modes: Wizard (questionnaire-driven auto-config) and Manual (full control over all parameters)

• Automatic sd-scripts installation and dependency management

• TOML config generation with inline annotations explaining every setting

• Smart VRAM presets (12GB, 16GB, 24GB) with automatic memory optimization

• Live config preview inside ComfyUI before launching training

• Cross-platform support (Windows, Linux, macOS)

• Zero pip dependencies — pure Python stdlib

Included Nodes

• Model Downloader — Downloads Anima models from HuggingFace

• SD-Scripts Manager — Installs/updates kohya-ss/sd-scripts

• Model Selector — Finds and validates model files

• Training Wizard — Questionnaire-driven auto-configuration

• Basic/Advanced/Memory Params — Manual parameter control

• Training Launcher — Generates config and launches training

• Config Preview — Shows annotated TOML config inline

Requirements

• ComfyUI (any recent version)

• Python 3.10+

• kohya-ss/sd-scripts (auto-installed by the SD-Scripts Manager node)

• Anima base model files (auto-downloaded by the Model Downloader node)

Dataset Preparation

Your training images should follow the sd-scripts convention: place images in a folder named <repeats>_<concept> inside your train_data_dir, with matching .txt caption files for each image.