Cyber Beauty

Cyber Beauty. All images are generated with A1111 on PC. SD Work better with simple negative prompt (3 embeddings) and detailed positive prompt. SD and ILL Tested with my checkpoint available on TA.

All my work is based on your buzz donations. If you like my models, please donate some buzz and vote for videos and models. Only in this way will I be able to continue and create more loras and videos. I hope for your understanding and support.

SD Weight 0.6 - 0.8 (0.6 more flexible) - CFG 3.5 to 5.5

ILL Weight 0.7 - 0.9 - CFG 5

If you like the model, always leave a rating and a picture, and if you give some buzz you will allow me to train other LORAs or other models. Downloading only is not useful. For model visibility, remember to rate the images in my gallery and the LORA. Thank you.

SD Negative prompt : (CyberRealistic_Negative-neg), (worst quality:2), (low quality:2), (bad-hands-5, lowres, bad anatomy, deformed, missing fingers, extra digit, fewer digits, cropped,watermark,username),(blurry:1.4) ,easynegative, unreal engine

SD Positive prompt : LORA, realistic, masterpiece, realistic, detailed, 8k, beautiful photography of girl, in a futuristic city, cyber tecnology, robot joints, massive cleavage, outdoor, (upper body shot), hourglass body shape, big breasts, skindentation, slim body, big thighs...

You can change suit (see trigger words), color of dress and hair.

ILL v1 Positive prompt : LORA, realistic, masterpiece, detailed, 8k, beautiful photography of a cyborg girl, joint, color and color bodysuit, pose in a futuristic city, cyber tecnology, robot joints, outdoor, slender body...

Choose two color for her bodysuit, standard is white and black.

ILL v2 Positive prompt : LORA, realistic, masterpiece, detailed, 8k, beautiful photography of a cyborg girl, ....... , large breasts, robot joints, outdoor, slender body

Add in prompt at ......

cyborg suit,

cyborg suit, transparent part,

cyborg implant, underwear,

cyborg implant, cleavage, nude,

You can try to add "ass" or "butt" or "big thighs, large hips" or "cleavage" in a positive prompt at the end, for different body visual effect.

V1 and V2 are different outfit, not a new version.

Settings For Illustrious version:

IMPORTANT, PLEASE READ : If you get different results, the prompt was probably not followed and an unsuitable checkpoint was used. All my LoRAs have been trained on realistic models. The videos I post represent what you can achieve; even though the video is animated, it reflects the quality and what the LoRA can do. The first frame of the video is the image I created using the LoRA and then animated, using the parameters I recommended. To achieve a realistic result, a realistic ILLustrious non-merged checkpoint should be used. If you use merged models with anime models, the result may be very different from mine. Do not use corrective loras in addition to the main lora because they often only ruin the result. If possible, do not exceed 150 tokens in prompts. Too many words in prompts do not improve the result. The parameters I use are the following :

Steps: 35, Sampler: Euler a, Schedule type: Automatic, CFG scale: 4.5, Size: 512x768, Denoising strength: 0.35, ADetailer model: face_yolov9c.pt, ADetailer confidence: 0.5, ADetailer dilate erode: 4, ADetailer mask blur: 8, ADetailer denoising strength: 0.25, ADetailer inpaint only masked: True, ADetailer inpaint padding: 32, ADetailer use separate CFG scale: True, ADetailer CFG scale: 4.5

For Adetailer face, you can choose the better: face_yolov10x_face.pt

On SD For perfect results, use only suggested embedding in negative prompt and suggested upscaler. Don't use with other loras and ng_deepnegative_v1_75t embedding (use only for anime or semirealistic) in negative prompt. In this way you have realistic body and skin detail.

SD Recommended for a better result: ADETAILER mediapipe face mesh with impaint 0.55

Setting : Sampling DPM Karras, HiresFix on, ITF-skinDiffDetail-Lite at 2x, Denoising 0.35/0.40, Upscale 2x, Sampling steps 35+, Resolution 512x768, Upscale 2x ITF-skinDiffDetail-Lite next passage. CFG 3,5 to 5,5.

It is strictly prohibited to distribute outside civitai this model or hosting services in third-party image generation services, or sell my images on other site. You can use this model for personal use on Civitai or A1111 on your pc. Not for sell.

If you appreciate the lora, please consider leaving us a review and sharing the images generated using this model. Your feedback is valuable to both us and the AI community. Thanks.