Hacker News new | ask | show | jobs
by orbital-decay 1038 days ago
The image is produced by sampling the model, which is the most computationally intensive process in the pipeline. Stable Diffusion XL consists of several parts which have to be sampled separately, losing the context in the process. This samples both parts in a way that no context is lost, improving the result.
1 comments

What means "sampling" here? Is it like sampling a probability distribution? Or like sampling a continuous image by taking the value of specific pixels?
More the former.