-
Dreambooth-Stable-Diffusion
Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) by way of Textual Inversion (https://arxiv.org/abs/2208.01618) for Stable Diffusion (https://arxiv.org/abs/2112.10752). Tweaks focused on training faces, objects, and styles. (by JoePenna)
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
Yep, it looks like you don't have to even retrain - you can train multiple faces, multiple objects, and multiple styles at one time - supposedly using tweaked versions of dreambooth like JoePenna/Dreambooth-Stable-Diffusion (github.com) by Joe Penna.
I'm the author of Dreambooth training UI and spend a lot of time with the Dreambooth community. I recently see a lot of post about paid dreambooth training and worried when I see the price they charge.
https://github.com/nitrosocke/dreambooth-training-guide for help on what prep to do, and settings to use.
Related posts
-
Finetune a GPT Model for Spam Detection on Your Laptop in Just 5 Minutes
-
AI Agent Notebooks Using LangChain, LlamaIndex, Milvus, and More
-
Mastering Dataset Acquisition: A Comprehensive Guide
-
Simple GitHub Issue Handled(?) By Copilot Workspace
-
Show HN: Hamilton's UI – observability, lineage, and catalog for data pipelines