StreamDiffusion

This account was spamming Python repositories with the same type of low value obvious backdoor spam.[1] Full list of attempted pull requests (all deleted seemingly by GitHub): 1 https://www.github.com/KurtBestor/Hitomi-Downloader/pull/7638 2 https://www.github.com/home-assistant/core/pull/130423 3 https://www.github.com/celery/celery/pull/9407 4 https://www.github.com/chriskiehl/Gooey/pull/921 5 https://www.github.com/crewAIInc/crewAI/pull/1582 6 https://www.github.com/cumulo-autumn/StreamDiffusion/pull/177 7 https://www.github.com/AUTOMATIC1111/stable-diffusion-webui/pull/16646 8 https://www.github.com/Aider-AI/aider/pull/2343 9 https://www.github.com/aboul3la/Sublist3r/pull/383 10 https://www.github.com/plotly/dash/pull/3073 11 https://www.github.com/soimort/you-get/pull/3034 12 https://www.github.com/streamlink/

Nice! I peeked at the code and thought I’d share a few tips for improving the low frame rate: Base64 encoding the JPEG bytes will increase payload size up to ~30% and burns CPU cycles on both client and server. This is unnecessary, as Websocket protocol can send binary payloads (doesn’t need to be text). Consider removing lossy jpg compression as well, ie just send the raw RGB bytes over the network. Then on the server side you can simply call Image.frombuffer(…). StreamDiffusion can achieve high frame rates because of extensive batching in the pipeline. You’re not benefiting from that here as the client is only sending one frame at a time and then waiting for a response. See this example for an idea of how to queue input frames and consume them in batches https://github.com/cumulo-autumn/StreamDiffusion/blob/main/e... . Alternatively you

Everyone does warmup before you measure. But measuring isn't always done right because we actually measure the GPU time only but some people naively use CPU time which is problematic because the process is asynchrenous. They have a few timing scripts though and I'm away from my GPU. There are some interesting things but they look like they know how to time. But it can also get confusing because is it considering batches or not. Some works do batch some do single. Only problem is when it isn't communicated correctly or left ambiguous. Their paper is ambiguous unfortunately. Abstract, intro, and conclusion suggests single image by motivating with sequential generation (specifically mentioning metaverse). Experiment section says > We note that we evaluate the throughput mainly via the average inference time per image through processing 100 i