nuwandda/sdxl-lora-training
Stable Diffusion XL LoRa Training
This project helps anyone working with generative AI to create highly customized image generation models. It takes your unique set of 5-20 customer images and automatically labels them using advanced AI like Claude or ChatGPT-4. The outcome is a finely tuned Stable Diffusion XL model capable of generating new images that perfectly match the specific style or concepts in your original dataset, without needing extensive manual annotation or heavy computing resources. This is ideal for marketers, designers, or product teams who need custom image generation for unique brand assets or specific visual themes.
No commits in the last 6 months.
Use this if you need to quickly and efficiently create a personalized Stable Diffusion XL image generation model based on a small set of your own specific images or visual concepts.
Not ideal if you're looking for a broad, general-purpose image generation model or if you prefer to manually control every aspect of the data annotation process.
Stars
29
Forks
3
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Oct 07, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/nuwandda/sdxl-lora-training"
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.