For business inquires, commercial licensing, custom models, and consultation contact me under <a target="_blank" rel="ugc" href="mailto:joachim@rundiffusion.com">joachim@rundiffusion.com</a>. This is Aether FIRE - a fire texture based subject and object oriented LoRA trained on animals, people and some other stuff. Play with weights but 1 is a good base. Higher and you seem to get more engulfing results on tough subjects - lower and you get more distinct features. Works well with no negative prompting for basic things. Make sure to check out prompt examples with the images in this gallery.Activate by using either fire that looks like X or X made of fire.Thanks to <a target="_blank" rel="ugc" href="https://rundiffusion.com/">RunDiffusion</a> who sponsored the finetuning of this LoRA. It was made on Lastben’s SDXL LoRA trainer through RunDiffusion which will soon be made public for everyone. Aether Fire is of course available on their platform to try it out.Also thanks to Masslevel for contributing with awesome images.It's not cool, it's FIRE!

Aether Fire - LoRA for SDXL

Aether_Fire_v1_SDXL_LoRA.safetensors

v1.0

This is Aether FIRE - a fire texture based subject and object oriented LoRA trained on animals, people and some other stuff. Play with weights but 1 is a good base. Higher and you seem to get more engulfing results on tough subjects - lower and you get more distinct features. Works well with no negative prompting for basic things. Make sure to check out prompt examples with the images in this gallery.Activate by using either fire that looks like X or X made of fire.Thanks to <a target="_blank" rel="noopener noreferrer nofollow" href="http://rundiffusion.com">RunDiffusion</a> who sponsored the finetuning of this LoRA. It was made on Lastben’s SDXL LoRA trainer through RunDiffusion which will soon be made public for everyone. Aether Fire is of course available on their platform to try it out.Also thanks to Masslevel for contributing with awesome images.It's not cool, it's FIRE!

Files with SHA256: 004bbcf0ce2bd29195ebdd5456f001ebbf7fbf9fd48f338dc2b58e6074bebde5