[esjeon]

I saw a person using this. The system had 4090, which can pull about 20-30 iter/sec. This roughly translates to 4 image/sec with 8 iter/image. This allows interactive AI drawing (thou a bit quirky). Once the desired image is reached, the user can re-run w/ 30-50 iterations to finalize the image. This is really cool.

[pedrovhb]

Latent consistency models are a pretty radical game changer that came up recently. There are LoRAs [0] that you can just use alongside any SD or SDXL that just cut the number of inference steps you need to 2-8, rather than the usual ~25+. It's as close to magic as one could expect, and on ComfyUI my modest RX 5700XT spits out 512x512 images in probably around a second each, or a couple of seconds for a 4x batch. A more beefy GPU could certainly enable high res, very low latency interactive use.

For even better latency perception, you could hook into the generation steps and have TAESD [1] decoding intermediate latents.

[0] https://huggingface.co/collections/latent-consistency/latent... [1] https://github.com/madebyollin/taesd