OneTrainer
What it is
OneTrainer is a comprehensive suite for training and fine-tuning Diffusion models (e.g., Stable Diffusion, FLUX, SDXL). It provides both a graphical user interface and a command-line interface for handling complex tasks like LoRA training, image augmentation, and dataset captioning.
The problem it solves
The complexity and fragmented nature of training various diffusion models, requiring multiple tools for data preparation, format conversion, and training scripts.
What you could use it for
- Fine-tuning Stable Diffusion or FLUX models using LoRA or full fine-tuning.
- Automatically captioning datasets using BLIP, BLIP2, or WD-1.4.
- Creating masks for masked training using ClipSeg or Rembg.
- Converting between different model formats (e.g., diffusers and ckpt).
- Training models with multiple resolutions and aspect ratio bucketing.
Read the source ↗Back to the library →
Summary written by an AI model from the source; check the source before you rely on it.