Hi! Did you consider to implement LORA into your API?

LoRAs are files that alter the results of existing Stable Diffusion models based a particular concept. This could be an art-style, a character, a real-life person, an object, or a theme.
https://aituts.com/stable-diffusion-lora/

I’ve noticed right now lots of people uses it their renders, but i couldn’t find it in any API for stable diffusion.

In replicate you just need to provide:
lora_urls: The URL or URLs of your trained LoRA concept(s) you copied in the previous step. You can pass a single URL, or a list of URLs separated by a pipe character |. Passing multiple URLs allows you to combine multiple concepts into a single image.

Replicate documentation describing it:
https://replicate.com/blog/lora-faster-fine-tuning-of-stable-diffusion

Please consider this, that’s such a cool feature i miss everywhere

Thank’s in advance and have a great day! 😄