-
diffusers
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.
-
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.
-
custom-diffusion
Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)
You might find a method called LoRA interesting for reducing size. Can be applied to approximate a full Dreambooth-style training. See this discussion for more details: https://github.com/cloneofsimo/lora/discussions/37
Hi, I want to finetune Stable diffusion using the diffusers' dreambooth example for multiple subjects (each subject with its own model).
Adobe Research also has "Custom Diffusion" out: https://github.com/adobe-research/custom-diffusion. It's got a similar goal of ~megabytes sized outputs. Warning that it's got a proprietary license.