Our great sponsors
-
stable-diffusion
Discontinued This version of CompVis/stable-diffusion features an interactive command-line script that combines text2img and img2img functionality in a "dream bot" style interface, a WebGUI, and multiple features and other enhancements. [Moved to: https://github.com/invoke-ai/InvokeAI] (by lstein)
-
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.
The GitHub repository is at https://github.com/lstein/stable-diffusion, and has detailed installation instructions. You will need a system with an appropriate GPU, python3 installed, and, of course, the model weights, which should be released soon. If you don't have the weights and want to play with an earlier low-quality model, the repository has instructions on how to get and install it.
Thanks for taking the time to do this for people, I have a question although I'm more or less sure I already know the answer I just need to check first before I spend too much time this weekend on this. I've been using this one here for the last two days and it's been updated frequently and works well on my card. https://github.com/basujindal/stable-diffusion
Are you planning on adding the k_lms sampling (https://github.com/crowsonkb/k-diffusion) that is default sampler for the discord bot? I noticed on the current official Stable Diffusion repo it doesn't have it and defaults to plms.