Wow guys, you have to try this for yourself! 😲😲
Super fast generations at "normal" XL resolutions with much better quality than the (freshly released) SDXL Turbo!
Suggested settings for best output
Sampler: DPM++ SDE Karras
Steps: 3 - 5
CFG: 1 - 2.25
You can run this model in Automatic1111 like a normal XL model, however not all samplers work with it. I've found DPM++ SDE Karras works best, and the LCM sampler (added by AnimateDiff in A1111 if you didn't know) works pretty well with it too.
LoRAs work fine, I've tested multiple LoRAs and they appear to still produce expected results, tho YMMV of course.
I will say, this model has some issues with coherence currently. When it's spitting out handfuls of images every few seconds you may not care, but I will be actively working on improving the coherence of the output with future versions.
NOTE ON LICENSING - This model is based on the SDXL Turbo model released by Stability AI. They have flagged the model as being released under a non-commercial research license and permits personal, non-commercial use only. Be aware this model cannot be used for image generation services at this time. If you have questions, please reach out to me on Discord.
Like the work I do and want to say thanks? Buy me a coffee or Support me on Patreon for exclusive early access to my models and more!