p1atdev/LECO
Low-rank adaptation for Erasing COncepts from diffusion models.
This tool helps AI artists and content creators refine their image generation by precisely controlling specific visual styles or elements. You provide an existing AI image generation model and define concepts you want to reduce, emphasize, or swap. The output is a modified version of your original model, allowing you to generate images with greater stylistic control, like removing a particular artist's style or adding features like cat ears.
324 stars. No commits in the last 6 months.
Use this if you need to fine-tune a Stable Diffusion model to either eliminate unwanted stylistic traits from generated images or to consistently incorporate specific visual elements into your prompts.
Not ideal if you're looking for a simple, no-code image editing tool or if you want to make broad, non-specific changes to your image generation model.
Stars
324
Forks
27
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Jan 20, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/p1atdev/LECO"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
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.