Please share what you generate with this, feedback is helpful so I can iterate on this LoRA!With Lora (euler/beta/27/1.0 strength) vs Withouta woman standing in a field wearing spandex, back to the camera, editorial photo<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/0d1681fa-b75f-4b16-bef3-74e81b051e28/width=525/0d1681fa-b75f-4b16-bef3-74e81b051e28.jpeg" />Left With Lora (and Keyword) vs Without a woman standing in a field wearing spandex, editorial photo, psxmastyle<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/0d3e1f63-2702-4715-91b9-c134be0eb703/width=525/0d3e1f63-2702-4715-91b9-c134be0eb703.jpeg" /> What Is It?This LoRA is trained to stylize images of women for erotic soft-modeling photos. Photos that mimic erotic art poses (SFW). This brings in more candid lighting, more varied faces and natural playful poses. How ToAll generations in the samples are used with this LoRA applied only, and a face detail node. Samples are generated using euler/beta @ 27 steps. You may notice at strengths near 1.0 and higher the model can cause some issues with hands, and distorted people in backgrounds. I've left these in the examples.Suggested Weight: 0.4-0.9 produces very natural results, strengths above can produce great results inconsistently. Use the trigger word to force the style. Training NotesTrained with 15 uncaptioned images at 768. No effort was made to train NSFW concepts.

Files with SHA256: 9dc55f847d9b5273eb14fe24112f5d83255970e798f10ff12c25a83b3c383a92