The title says pretty much everything. Can i use external/train lora in text-to-image generator? If yes, then how? If no, will this happen in the future? AI simply refuses to draw some things properly no matter how much you write the prompt, lora trained on your own photos with examples of what you need to draw easily solves this problem. Also interested if i can use Stable Diffusion(No, I haven’t checked the posts, sorry if someone asked all this before, I’m writing this post in a hurry while I have a minute)
You must log in or register to comment.
No. There’s a set back-end that we have access to in our generator pages, that’s all. It uses a somewhat older Stable Diffusion model. (Or perhaps three models: one for photos, anime, and the “furry” character style.)
The dev has mentioned that they’re planning on an image generator update to the back-end soon. Perhaps including image-to-image or other features. But nothing about LoRA or using our own models or however you’d put it, so I doubt those will come to Perchance for now.
If you want those things, I’d recommend using other sites dedicated to AI image generation. This is just an added feature to Perchance, not the focus of the platform, so the dev is not focused on expanding those features.