This is my third and final attempt at training this LoRa. I have used the same training images as the other 2 versions but this time I removed any and all images that were of low quality or weirdly cropped. So far this version's (V3) generated images look the closest to that of the training images.

You may like V1 more but V3 is its intended look. I hope you like it and I can't wait to see your generations.

✨✨Tizi V3✨✨

Activation Prompt: T1z1v3

Negative Prompt: keychain, lowres, worst aesthetic, (worst quality, bad quality, low quality:1.2), bad anatomy, old, signature, watermark, artist name, 3d

*This ^^^ negative prompt works best.

Weight: 1

Sampler: Euler a - Automatic

Recommended Base Models: WAI-NSFW-illustrious-SDXL V14

To get the same results like the sample images follow this prompting formula: Your Prompt + BREAK Prompt + LoRa

Break Prompt: BREAK character_concept, cowboy_shot, (dutch_angle:1.25), masterpiece, best quality, amazing quality, very aesthetic, absurdres, modern, recent, newest

Prompt Example: 1girl, solo, virgin ribbed sweater, destroyer sweater, dark violet green sweater, navel, thighhighs, smile, looking at viewer, library, thick thighs, wide hips, large breasts, curvy, BREAK character_concept, cowboy_shot, (dutch_angle:1.25), masterpiece, best quality, amazing quality, very aesthetic, absurdres, modern, recent, newest, <lora:TiziV3_IL_Style-000013:1> T1z1v3

*This prompt formula works best if you are using reForge or StableDiffusion locally. Based on my tests it does not work as good if you generate them here on the site.

Make sure to post your favorite generations on the Gallery by simply clicking +Add Post button.