This model is a tad overbaked, so you'll likely want to keep CFG at 5-6 usually. I've tried down-weighting the model, but even a small 5% dilution with SD 1.5 can be awful for a noticeable number of prompts. This is the most fun it gets, folks.
Example images generated in InvokeAI with DDIM, using high res optimization (img2img, 0.47 strength) to upscale from a low resolution. Some prompts may need closer to 40 steps to come out with the cleanest detail if you're using a different method of high res optimization than I am.