sayakpaul/dreambooth-keras
Implementation of DreamBooth in KerasCV and TensorFlow.
Enables fine-tuning of Stable Diffusion's UNet and text encoder using prior-preservation loss to teach new visual concepts from just 3-10 images. Integrates with Weights & Biases for experiment tracking, model checkpointing, and qualitative validation logging during training. Provides end-to-end utilities including class image generation via diffusion models and inference support through both notebook and bulk processing scripts.
No commits in the last 6 months.
Stars
88
Forks
15
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Feb 16, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/sayakpaul/dreambooth-keras"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Acly/krita-ai-diffusion
Streamlined interface for generating images with AI in Krita. Inpaint and outpaint with optional...
deep-diver/LoRA-deployment
LoRA fine-tuned Stable Diffusion Deployment
charrywhite/LanPaint-diffusers
LanPaint diffusers version code
aws-samples/amazon-sagemaker-personalized-generative-ai
This project simplifies personalized Gen-AI SaaS apps. We fine-tune pre-trained models for...
aws-samples/generative-ai-demo-using-amazon-sagemaker-jumpstart-kr
This project shows the demos about how to generate stable diffusion images using AWS SageMaker Jumpstat.