edenartlab/sd-lora-trainer
LoRa trainer for SDXL and SD15
This tool helps digital artists and content creators teach Stable Diffusion new styles, faces, or objects. You provide a set of images depicting a specific aesthetic, person, or item, and it generates a specialized LoRa file. This file can then be used in image generation tools like ComfyUI or AUTO1111 to produce new images featuring your custom learned elements.
No commits in the last 6 months.
Use this if you want to personalize Stable Diffusion models to consistently generate images in a specific visual style, or with a particular face or object.
Not ideal if you are looking for a tool to perform pure textual inversion for SD1.5, as this feature has known issues.
Stars
66
Forks
12
Language
Python
License
—
Category
Last pushed
Aug 04, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/edenartlab/sd-lora-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.