An few obstacles I keep running across with training I’m hoping someone can please help.

• dreambooth-tokens

  3 118 10.0

First, you probably should NOT use parker. It's a bit too common a word. Try dprk as it's a single token and low in "the list." And then you should have as your instance prompt "photo of dprk woman" and for your class prompt: "photo of woman." Then when you want to invoke the token, use it with "woman", for example, "an oil painting of dprk woman in the style of ..."

• Dreambooth-Stable-Diffusion

  100 3,168 6.8 Jupyter Notebook

  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)

This has been the most used source for information about training people with dreambooth: https://github.com/JoePenna/Dreambooth-Stable-Diffusion.

• InfluxDB

  www.influxdata.com featured

  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.

  

Suggest a related project