gazingstars123/Anima-Standalone-Trainer

Standalone Anima Lora trainer with GUI

What it solves

This project provides a lightweight, decoupled training environment specifically for the Anima model, allowing users to fine-tune the model using Low-Rank Adaptation (LoRA) without needing a complex setup process.

How it works

Built upon the sd-scripts implementation, the tool provides a Web UI for managing training jobs. Users configure global settings for the DiT model, VAE, and text encoder paths, and then launch the training process through a browser-based interface at http://localhost:3000.

Who it’s for

It is designed for developers and AI artists who want to fine-tune the Anima model on Windows or Linux systems using their own datasets.

Highlights

  • Support for Anima 2.9B LoRA training.
  • Web-based user interface for easier configuration.
  • Support for both Windows and Linux operating systems.
  • Multi-GPU inference capabilities.

Related

  • Project
    shootthesound/comfyUI-Realtime-Lora

    A comprehensive ComfyUI toolkit for training, analyzing, and selectively loading LoRAs across multiple model architectures, featuring granular block-level and sub-component control.

  • Dispatch
    Using LoRA for Efficient Stable Diffusion Fine-Tuning

    Hugging Face has integrated Low-Rank Adaptation (LoRA) into the diffusers library, enabling faster Stable Diffusion fine-tuning with significantly lower VRAM requirements and model weights as small as 3 MB.

  • Project
    Akegarasu/lora-scripts

    A GUI and script preset collection for training Stable Diffusion LoRA and Dreambooth models, providing an integrated environment for dataset tagging and training.

  • Project
    unslothai/unsloth

    A desktop and code-based platform for running and fine-tuning AI models locally, offering significantly faster training speeds and lower VRAM requirements.

  • Project
    DashAISoftware/dashAI

    A graphical toolbox for training, evaluating, and deploying state-of-the-art AI models with support for various hardware accelerators.