Please read through the entire description (might need to be expanded) and the version change notes as they cover a lot of information about basic use cases and limitations. The description is always focused on the latest version. Thank you!This is an SD 1.5 LoRA for the character Nessa / Rurina from Pokemon. It works for models based on SD 1.x only, it will not work for models based on SD 2.x or SDXL!Example images were picked from base resolution txt2img results + the FreeU extension (<a target="_blank" rel="ugc" href="https://github.com/ljleb/sd-webui-freeu">https://github.com/ljleb/sd-webui-freeu</a>) enabled with default settings to further improve results (see last example images for a comparison of FreeU disabled vs enabled). They were then re-created at 2x resolutions using txt2img with moderate Hi-res Fix settings (upscaler Lanczos, denoising strength 0.4). This improves faces and other details that are almost impossible to get correctly and consistently at base resolutions (limitation of the technology) while still giving a realistic impression of what it looks like. Base resolution results will have more distorted faces and less detail.Please see the version change notes for the training and example image generation models as well as the used weights as they might change between versions. Remember that you might need to adjust weights to best suit your use case!Remember to add the tag nessa \(pokemon\) (with backslashes intact) to your positive prompt.The training set contained multiple variations of Nessa's signature look (though very heavily weighted towards the signature bikini outfit as there aren't many others) so you might need to put combinations of the following tags in your positive or negative prompts to get the desired results:<ul><li>armlet</li><li>armband</li><li>belly chain</li><li>bikini</li><li>dynamax band</li><li>ear piercing</li><li>hair bun</li><li>hair ornament</li><li>hoop earrings</li><li>necklace</li><li>sandals</li><li>single glove</li></ul>As the training set contained a few images with floating hair, you might need to add floating hair to the negative prompts if not desired.Known Limitations / Problems:<ul><li>The skin tone sadly is quite a bit too light on average but I don't know how to fix that at the moment. It is very much NOT intentional! I might need to change the training data to include some better images with dark skin tones but I already have quite a few of those. You may have some success prompting for dark skin or very dark skin but it does not seem to help too much.</li><li>The sandals and ear piercings were not present in a lot of images and not a focus for the training so they sadly will not be consistent at all.</li><li>Same goes for the positioning of the asymmetrical arm bands and glove since they are not bound to a consistent arm. They might even merge together or disappear. No idea how to fix this yet.</li><li>Sometimes, double hair buns might get generated instead of a single one. Try single hair bun in the positive prompts and / or double bun in the negative prompts if that happens. I might change the tag in the future to prevent this from happening.</li><li>Good luck getting the necklace to look as it should (don't think this can be fixed as it is an awkward shape to train).</li></ul>

[SD 1.5] Pokemon - Nessa / Rurina

There are detailed changes below the next paragraph, you might need to expand this version changes box!I'm uploading this "WIP version" of v7 as I'm not sure when / if I'll have the time / motivation to properly finish it up. It is roughly equivalent to v6 with the changes to the training process from v7 of my Dawn LoRA. It already fixes quite a few issues with v6 and should usually perform better. But it is not at the same level of improvement yet. If I'm not doing a "proper" v7 with major dataset changes, I might simply rename this version in the future.Most of the changes (look at LoRA metadata for more details):<ul><li>Updated to much newer Kohya scripts version (&gt;3 months newer)</li><li>Updated training images<ul><li>Switched to keep original-ish aspect ratios (slightly cropped and resized to compatible SD 1.5 resolutions) where it makes sense instead of forcing squares</li><li>Added regularization images to actually make trigger tag work correctly<ul><li>1 regularization image per training image</li><li>Generated by the base model at the same resolution, with the same tags (minus the activation tag)</li><li>Currently at half loss during training as they had a bit too much influence otherwise</li><li>With this, the LoRA now reverts back much closer to base model knowledge without the activation tag (which is correct!)</li><li>Might care a bit more about the positioning of the activation tag now as it was trained with "keep tokens" to keep the activation token at the front when shuffling</li></ul></li></ul></li><li>Normalized repeats to 1 (only using different values if ever in need of balancing datasets) and learning rates back to defaults<ul><li>Compensated with different epoch settings</li></ul></li><li>Reverted back to training at 128 dims and a resize down to 32<ul><li>Results were better across the board and the resizing also removes a bit of noise as a bonus</li><li>Used NO dynamic resize method as results for sv_fro@0.99 and sv_ratio@20 did not seem too different from or better than a simple resizing</li></ul></li><li>Added training warmup of 10%<ul><li>Not sure if this had much impact, might remove again in the future</li></ul></li><li>Added "scale weight norms" with value 1 during training<ul><li>Supposedly helps against overfitting and might make LoRAs more compatible with others</li></ul></li><li>Used FreeU extension for example image generation to further improve results</li></ul>Recommended weight: 1Training model: <a target="_blank" rel="ugc" href="https://civitai.com/models/66/anything-v3">Anything V3</a>Example image generation model: <a target="_blank" rel="ugc" href="https://civitai.com/models/4451/abyssorangemix2-hardcore">AbyssOrangeMix2 - Hardcore</a>

Files with SHA256: 4dee3c68b25098103caa5302d5c8431c45c5af34f4db713e31e6783c47415eb4