I'm using the fork at https://github.com/basujindal/stable-diffusion which is optimized for lower VRAM usage. My RTX 2070 (8 GB) takes about 90 seconds to generate a batch of 4 images.
I quickly threw together a folder structure where I have a md5'd prompt as a folder name, into that goes _promp.txt with the actual text of the prompt and the images i generate in a loop with the seed used and iteration number in the image's file name. That way I can generate like 20 seed-based images for a prompt and if the model bites I let it run with a much higher number of seed-based images. When you have a 1000 to pick from, some of the results are freaking amazing.