[Other][LORA]onimai-characters-lora v0.1
<p>For some reason people seem to prefer loras over full checkpoint, so as an experiment I decide to make a lora based on the same dataset that I used for the model <a target="_blank" rel="ugc" href="https://civitai.com/models/7848/onimai-characters">https://civitai.com/models/7848/onimai-characters</a><br />Civitai does not allow me to mark the repository as both full checkpoint and lora so I can only create a new one for this.<br />Naturally I am able to get the characters trained but not the styles. Unlike the full checkpoint, the outfits are not learned either.<br />For more details please see <a target="_blank" rel="ugc" href="https://huggingface.co/alea31415/onimai-characters">https://huggingface.co/alea31415/onimai-characters</a><br />I would still suggest using the full model if you want more characters, or more fidelity to the styles and outfits. Remember that you can always alter the style by merging models. </p>
页:
[1]