Realistic BodyWriting (RBW) is for inpainting.The model does a poor job of generating the correct text during txt2img.The sample image was generated with URPM1.3, and then inpainted with URPM1.3-inpainting and RBW.Recommend values when inpainting with URPM1.3-inpainting,<ul><li>.7-.8 for LORA weight</li><li>prompt weight of 1-1.3</li><li>CFG scale of 5</li><li>denoising strength of .7-.85</li></ul>Other values were tested but these were found to be the best ranges.InpaintingWhen inpainting, it is recommend to add one word at a time. The success rate depends on the text being inpainted.RBW is partially case-sensitive, ie T vs t may change the case of the letters used in the image.The size of the inpainting area and the resolution of the picture being inpainted are both very important.The LORA is prompted with,<ul><li>text "ADDTEXT" on bodypart</li><li>emoji "EMOJI" on bodypart</li></ul>Common bodyparts are,<ul><li>upper chest</li><li>breast</li><li>upper abdomen</li><li>stomach</li><li>navel</li><li>pubic mound</li><li>leg</li><li>ass</li></ul>Notes<ol><li>Text contained in the training data generates better than text that isn't.</li><li>Non-training text is still possible but has a lower success rate.</li><li>For text in the training data the success rate is (1-10%).</li><li>For text not in the training data the success rate is lower and strongly depends on the word.</li><li>The full list of texted used for training is in the LORA info (I icon in the LORA menu for auto1111).</li><li>Adding a basic description of the subject in the prompt helps. i.e. women standing naked</li></ol>Source MaterialThe images were gathered online and the heads were removed to anonymize the images.If anyone feels the model depicts them too accurately, I am willing to retrain the model with their images removed.Conversely, is anyone is interested in providing custom images please contact me.Version 2The model was retrained many times with different parameters and tested with different epochs.After determining the optimal parameters the dataset was expanded.Ultimately, the version released is the best so far.If the LORA can be improved a version 2 will be released.

Files with SHA256: 3f32119560b1d39916e9cd532ce3919360611ba303409a2cd8d99c65855cb394