【AI彼女】AIでエロが叶うハイパーポルノでAI彼女を作ってみた！

a japanese woman walking in the city, buildings, plants ,smile, mixed korean,blur background, 
focus, cinematic lighting, (((masterpiece))), ((best quality)), ((intricate detailed)), ((Hyperrealistic)),
 absurd res, milf, mature woman, perspective, highly detailed, illustration, 1girl, (big breasts),
 beautiful detailed eyes, short hair, dark hair, purple eyes, (casual outfit:1.2), jacket, turtle neck sweater,
 skirt, black choker, earrings, high heels, detailed background, perfect eyes, seductive eyes, looking at the viewer,
 from front  <lora:odanon-lora-v1-128dim-4ep-novae:0.5>

Negative prompt: easynegative, badhandv4, (low quality, worst quality:1.4), poorly drawn hands, bad anatomy,
 monochrome, { long body }, bad anatomy , liquid body, malformed, mutated, anatomical nonsense ,bad proportions,
 uncoordinated body, unnatural body, disfigured, ugly, gross proportions ,mutation, disfigured, deformed, { mutation},
 {poorlydrawn} , bad hand, mutated hand, bad fingers, mutated fingers,   badhandv4 ,liquid tongue, long neck,
 fused ears, bad ears, poorly drawn ears, extra ears, liquid ears, heavy ears, missing ears, fused animal ears,
 bad animal ears, poorly drawn animal ears, extra animal ears, liquid animal ears, heavy animal ears,
 missing animal ears, bad hairs, poorly drawn hairs, fused hairs, bad face, fused face, poorly drawn face,
 cloned face, big face, long face, bad eyes, fused eyes poorly drawn eyes, extra eyes, bad mouth, fused mouth,
 poorly drawn mouth, bad tongue, big mouth, bad perspective, bad objects placement

Steps: 40, Size: 512x768, Seed: 1168656867, Model: Only Meichi real, Version: v1.3.0, Sampler: DPM++ SDE Karras,
 CFG scale: 7, Clip skip: 2, Model hash: c7f2cae17c, (monochrome: 1.1), Hires steps: 15, (bad-hands-5: 1.1),
 lowres,(Bored pose), static pose, busty bad hands, lowers, long body, disfigured, ugly, cross eyed, squinting,
 grain, Deformed, blurry, bad anatomy, poorly drawn face, mutation, mutated, extra limb, ugly, poorly drawn hands,
 missing limb, floating limbs, disconnected limbs, malformed hands, blur, out of focus, long neck, disgusting,
 poorly drawn, mutilated, ((text)), ((centered shot)), ((symetric pose)), ((symetric)), multiple views,
 multiple panels, blurry, multiple panels, blurry, watermark, letterbox, text, easynegative, asian, loli, ,
 child, childish", "(low quality: 1.4), Hires upscale: 2, (worst quality: 1.4), Hires upscaler: R-ESRGAN 4x+ Anime6B,
 ADetailer model: face_yolov8n.pt, ADetailer prompt: "(((masterpiece))), (((best result))), (((best quality))),
 ultra-detailed, beautiful eyes, beautiful face, smiling, blush, ", Noise multiplier: 0, ADetailer version: 23.7.1,
 Denoising strength: 0.4, ADetailer mask blur: 4, (bad_prompt_version2: 0.8), ADetailer confidence: 0.3,
 ADetailer dilate/erode: 32, ADetailer inpaint padding: 0, ADetailer denoising strength: 0.4,
 ADetailer inpaint only masked: True, odanon-lora-v1-128dim-4ep-novae: dbbcb38d0ce9

!git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui
%cd /content/stable-diffusion-webui

from google.colab import drive
drive.mount('/content/drive')

!cp /content/drive/MyDrive/stablediffusion/xxmix9realisticsdxl_testV20.safetensors /content/stable-diffusion-webui/models/Stable-diffusion/
!cp /content/drive/MyDrive/stablediffusion/chilloutrealistic_v21.safetensors /content/stable-diffusion-webui/models/Stable-diffusion/
!cp /content/drive/MyDrive/stablediffusion/meichidarkMix_meichidarkV45.safetensors /content/stable-diffusion-webui/models/Stable-diffusion/

!cp /content/drive/MyDrive/stablediffusion/embedding/* /content/stable-diffusion-webui/embeddings/

!python launch.py --share --xformers --enable-insecure-extension-access

a japanese woman walking in the city, buildings, plants ,smile, mixed korean,blur background , focus,
 cinematic lighting,(((masterpiece))), ((best quality)), ((intricate detailed)), ((Hyperrealistic)),
 absurd res, milf, mature woman, perspective, highly detailed, illustration, 1girl, (big breasts),
 beautiful detailed eyes, short hair, dark hair, purple eyes, (casual outfit:1.2), jacket, turtle neck sweater,
 skirt, black choker, earrings, high heels, detailed background, perfect eyes, seductive eyes, looking at the viewer,
 from front

badhandv4, (low quality, worst quality:1.4), poorly drawn hands, bad anatomy, monochrome, { long body },
 bad anatomy , liquid body, malformed, mutated, anatomical nonsense ,bad proportions, uncoordinated body,
 unnatural body, disfigured, ugly, gross proportions ,mutation, disfigured, deformed, { mutation}, {poorlydrawn} ,
 bad hand, mutated hand, bad fingers, mutated finger, liquid tongue, long neck, fused ears, bad ears,
 poorly drawn ears, extra ears, liquid ears, heavy ears, missing ears, fused animal ears, bad animal ears,
 poorly drawn animal ears, extra animal ears, liquid animal ears, heavy animal ears, missing animal ears,
 bad hairs, poorly drawn hairs, fused hairs, bad face, fused face, poorly drawn face, cloned face, big face,
 long face, bad eyes, fused eyes poorly drawn eyes, extra eyes, bad mouth, fused mouth, poorly drawn mouth,
 bad tongue, big mouth, bad perspective, bad objects placement

git clone https://github.com/OpenTalker/SadTalker.git
cd SadTalker 
conda create -n sadtalker python=3.8
conda activate sadtalker
pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 torchaudio==0.12.1 --extra-index-url https://download.pytorch.org/whl/cu113
conda install ffmpeg
pip install -r requirements.txt

bash scripts/download_models.sh

python app_sadtalker.py

python3.8 inference.py --driven_audio <audio.wav> \
                    --source_image <video.mp4 or picture.png> \
                    --enhancer gfpgan 

python3.8 inference.py --driven_audio ./examples/driven_audio/RD_Radio31_000.wav \
           --source_image ./examples/source_image/full13.png \
           --result_dir ./results --still --preprocess full --enhancer gfpgan