cloneofsimo / lora

Using Low-rank adaptation to quickly fine-tune diffusion models.
https://arxiv.org/abs/2106.09685
Apache License 2.0
7.08k stars 481 forks source link

Training a lora_model with inpainting is giving conversion failed: . the model may not be trained by `sd-scripts`. #246

Open Pavankunchala opened 1 year ago

Pavankunchala commented 1 year ago

The model may is trained on sd.1.5 inpainting but when I am trying to use it in automatic1111 I am getting this following error

   assert cv_name is not None, f"conversion failed: {du_name}. the model may not be trained by `sd-scripts`."
AssertionError: conversion failed: <cake_table>. the model may not be trained by `sd-scripts`.
oliverban commented 1 year ago

I'm getting the same. Trained two LORAs now and I get this error as well in A1111

BXuan694 commented 1 year ago

same for me, even on WowifierXL of civitai....With so many expetiences, there must be some little tricks that I missed.