DEX-1101/kohya-trainer
Legacy LoRA Trainer that work on T4 GPU Colab for SDXL Model
This tool helps artists and creators generate unique images with specific styles or subjects using Stable Diffusion XL (SDXL) models, even with more limited computing resources. You provide existing images of a desired style or subject, and it trains a specialized model (LoRA) that can then be used to create new images incorporating those unique elements. It's designed for digital artists, illustrators, and anyone looking to customize AI image generation outputs.
Use this if you want to train a custom Stable Diffusion XL model (LoRA) to generate images with a specific character, object, or artistic style using accessible cloud resources like Google Colab.
Not ideal if you need a general-purpose image editing tool or if you're not working with Stable Diffusion XL models for custom image generation.
Stars
23
Forks
6
Language
Jupyter Notebook
License
—
Category
Last pushed
Oct 18, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/DEX-1101/kohya-trainer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
KohakuBlueleaf/LyCORIS
Lora beYond Conventional methods, Other Rank adaptation Implementations for Stable diffusion.
tsiendragon/qwen-image-finetune
Repo for Qwen Image Finetune
Akegarasu/lora-scripts
SD-Trainer. LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion model.
PRITHIVSAKTHIUR/Qwen-Image-Edit-2511-LoRAs-Fast-Lazy-Load
Demonstration for the Qwen-Image-Edit-2511 model with lazy-loaded LoRA adapters for advanced...
cloneofsimo/lora
Using Low-rank adaptation to quickly fine-tune diffusion models.