Our great sponsors
-
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)
-
Dreambooth-SD-optimized
Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion
-
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.
-
stable-diffusion-webui
Discontinued Stable Diffusion web UI [Moved to: https://github.com/Sygil-Dev/sygil-webui] (by sd-webui)
There's also this https://github.com/gammagec/Dreambooth-SD-optimized
There are two GitHub issues for DreamBooth: #914, #1010
https://github.com/TheLastBen/fast-stable-diffusion and it's 25% faster
We implemented textual inversion recently on the streamlit version of our WebUI, it is still a work in progress but you can train it with any image and directly from the UI and it will create an embedding (.bin file) which then you can place on the concepts library folder (models/custom/sd-concepts-library) and use it on any prompt using the token you generated during training. If you need help or just want to chat you can join our discord server, I'm always there and the community is also always active and ready to help with any problem or doutb.
Well, we have users doing 1408x1408 in 8GB of VRAM on our WebUI, both the streamlit version and gradio version. You might want to check it out.