KJK
RRunPod
•Created by KJK on 2/19/2024 in #⚡｜serverless
Stable Diffusion API Execution Time
I am posting this for a response from runpod support @flash-singh or anyone other than @justin
Is 30+ seconds execution time on a serverless 24GB GPU, via any API Docker 1111, for 768px image acceptable/expected? The exact same model/prompt/settings runs on a pod using the A1111 UI in 3 seconds. Why is serverless so much slower? This is regarding execution time -- not delay, queue, spinup...
2 replies
Stable Diffusion GPU Pod and API
Is there a way to connect a GPU Pod running the stable diffusion template to an API layer that is externally exposed.?
I have a serverless instance running @ashleyk 's docker which is working great and much appreciated, albeit 10x slower than the GPU Pods.
I am attempting to leverage the processing power and number of GPUs on the pod side -- but need an API endpoint that I can expose to my external app...
@flash-singh ?
@justin I appreciate your answers, but I am directing this to the RunPod support or @ashleyk if willing to chip in.
6 replies