git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git
,將專案clone到本地pip install virtualenv
pip install gfpgan
即可安裝成功,如果還是不行,可以多試幾次,或者切換一下梯子的伺服器,選擇歐洲國家最好,如果梯子不支援,建議選擇日本、新加坡等,別選香港、臺灣(我自己試的不行,可能和我的梯子有關係,各位自行嘗試)git clone https://github.com/Mikubill/sd-webui-controlnet.git
命令clone專案到本地,並將資料夾移動到 E:\Projects\AI\stable-diffusion-webui\extensions
資料夾下,路徑各位按照自己的安裝路徑設定,我的在E槽下1.介面開啟後,在左上角可以選擇我們剛剛匯入的模型,
photorealistic, long_hair, realistic, solo, long_hair, (photorealistic:1.4), best quality, ultra high res, teeth, Long sleeve,Blue dress, Big mouth,full body, 3girls, Grin, graffiti (medium), ok sign, smile, stand, 1girl,full body, beautiful, masterpiece, best quality, extremely detailed face, perfect lighting, 1girl, solo, best quality, ultra high res, (photorealistic:1.4), parted lips lipstick, ultra detailed, Peach buttock, looking at viewer, masterpiece, best quality,
(worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, age spot, glans,extra fingers,fewer fingers,strange fingers,bad hand (low quality, worst quality:1.4), (bad_prompt:0.8), (monochrome), (greyscale)
調整相關的引數,如下圖所示,點選生成,等待即可,在專案啟動的cmd介面可以看到生成的進度條
等待片刻後,圖片就能生成。
其他模型下載和相關引數可以在這個網站上查詢,記得開著梯子嗷。
模型*.safetensors檔案放在E:\Projects\AI\stable-diffusion-webui\models\Stable-diffusion這個路徑下,這裡可能在視訊裡講錯了,,見諒