This is a SDXL version of <a target="_blank" rel="ugc" href="https://civarchive.com/models/144449">my previous Giantess LoRA</a>.It was trained using <a rel="ugc" href="https://civarchive.com/models/43977?modelVersionId=338512">LEOSAM's XL 5.0 GPT4V</a> as the base model. Using this model when generating images produces good results, but you can try using the LoRA with different models.The example images where upscaled x2 with SUPIR and after that I used inpainting with partial denoising strength to improve the faces.

Files with SHA256: 44db9899943f6e76a63529e13e8ec29a4d86f5ecd1db7d7596661f0554b53119