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.
Description
Added LoKR & LoHA parameters
FAQ
Comments (1)
I keep on getting this error:
Traceback (most recent call last): File "_mt19937.pyx", line 180, in numpy.random._mt19937.MT19937._legacy_seedingTypeError: 'str' object cannot be interpreted as an integerDuring handling of the above exception, another exception occurred:Traceback (most recent call last): File "my_training_directory\model\_train_wrapper.py", line 7, in <module> runpy.run_path(r"G:\SwarmUI\Models\sd-scripts\anima_train_network.py", run_name="__main__") File "<frozen runpy>", line 291, in run_path File "<frozen runpy>", line 98, in runmodule_code File "<frozen runpy>", line 88, in runcode File "G:\SwarmUI\Models\sd-scripts\anima_train_network.py", line 451, in <module> trainer.train(args) File "G:\SwarmUI\Models\sd-scripts\train_network.py", line 488, in train set_seed(args.seed) File "G:\SwarmUI\dlbackend\comfy\python_embeded\Lib\site-packages\accelerate\utils\random.py", line 54, in set_seed np.random.seed(seed) File "numpy\\random\\mtrand.pyx", line 4806, in numpy.random.mtrand.seed File "numpy\\random\\mtrand.pyx", line 250, in numpy.random.mtrand.RandomState.seed File "_mt19937.pyx", line 168, in numpy.random._mt19937.MT19937._legacy_seeding File "_mt19937.pyx", line 188, in numpy.random._mt19937.MT19937._legacy_seedingTypeError: Cannot cast scalar from dtype('<U4') to dtype('int64') according to the rule 'safe'