I trained this LoRa by mixing a failed unpublished Pony version of this LoRa Tizi and this Thicc helper. The results were somewhat good. Then I tried to train a Pony version only to fail. Then I totally forgot about these images. I was cleaning my PC from useless files when I came across these training images. I decided to give them a try once more but this time with the IL training method. This is the result. Let me know what you think.

Activation Prompt: ChunkyL1n3s, wide hips, mature woman, long eyelashes

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.

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:ChunkyLines_IL_Style_epoch_2:1> ChunkyL1n3s, wide hips, mature woman, long eyelashes

*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.

Weight: 1

Sampler: Euler a - Automatic

Recommended Base Models: WAI-NSFW-illustrious-SDXL V13

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