Our great sponsors
-
WorkOS
The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.
-
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.
RTX 3070 here
Keep in mind to have the batch-size low (equal to 1, probably), that was my main issue when I first installed this.
Then, there's lot's of great forks already which add an interactive repl or web ui [0][1]. They also run with half-precision which saves a few bytes. Additionally, they integrate with upscaling neural networks, which means you can generate 512x512 images with stable diffusion and then scale them up to 1024x1024 easily. Moreover, they integrate with face-fixing neural networks, which can also drastically improve the quality of images.
There's also this ultra-optimized repo, but it's a fair bit slower [2].
[0]: https://github.com/lstein/stable-diffusion
[1]: https://github.com/hlky/stable-diffusion
[2]: https://github.com/basujindal/stable-diffusion
RTX 3070 here
Keep in mind to have the batch-size low (equal to 1, probably), that was my main issue when I first installed this.
Then, there's lot's of great forks already which add an interactive repl or web ui [0][1]. They also run with half-precision which saves a few bytes. Additionally, they integrate with upscaling neural networks, which means you can generate 512x512 images with stable diffusion and then scale them up to 1024x1024 easily. Moreover, they integrate with face-fixing neural networks, which can also drastically improve the quality of images.
There's also this ultra-optimized repo, but it's a fair bit slower [2].
[0]: https://github.com/lstein/stable-diffusion
[1]: https://github.com/hlky/stable-diffusion
[2]: https://github.com/basujindal/stable-diffusion
RTX 3070 here
Keep in mind to have the batch-size low (equal to 1, probably), that was my main issue when I first installed this.
Then, there's lot's of great forks already which add an interactive repl or web ui [0][1]. They also run with half-precision which saves a few bytes. Additionally, they integrate with upscaling neural networks, which means you can generate 512x512 images with stable diffusion and then scale them up to 1024x1024 easily. Moreover, they integrate with face-fixing neural networks, which can also drastically improve the quality of images.
There's also this ultra-optimized repo, but it's a fair bit slower [2].
[0]: https://github.com/lstein/stable-diffusion
[1]: https://github.com/hlky/stable-diffusion
[2]: https://github.com/basujindal/stable-diffusion
Openvivo (CPU version of Stable Diffusion) is a easy setup on Linux within a venv. Be sure to update Pip first.
https://github.com/bes-dev/stable_diffusion.openvino
Basically stuff a 32 bit value into an 8 bit value (and lose precision).
Apparently it doesn't affect the results significantly.
More info:
https://github.com/huggingface/transformers/pull/17901