其實安裝步驟,見該項目Github的安裝主頁。 GitHub - Gourieff/sd-webui-reactor: Fast and Simple Face Swap Extension for StableDiffusion WebUI (A1111 SD WebUI, SD WebUI Forge, SD.Next, Cagliostro)github.com/Gourieff/sd-webui-reactor 安裝完後,在文生圖、圖生圖、後期處理這三個頁面都會有ReAc...
Build Blended Face Model 和 ReActor-Fast Face Swap,一个是用来训练混合的节点,一个是主节点。 从版本 0.4.0 开始,我们可以将面部模型保存为safetensors文件(存储在ComfyUI\models\reactor\faces)并将其加载到 ReActor 中,实现不同的场景并保留您使用的面部的超轻量级面部模型。 face_model_name:这个mix_face_...
swap_model: 作用:指定用于面部交换的模型。 推荐值:通常使用inswapper_128.onnx,这是一个预训练的面部交换模型。 示例: json "swap_model": "models/insightface/inswapper_128.onnx" facedetection: 作用:选择用于人脸检测的模型。 推荐值:可以选择如retinaface_resnet50等高性能模型。 示例: json "face...
然后,就是主节点了,使用Fast Face Swap节点来进行换脸,主要参数如下: input image:需要换脸的图片 source image:需要参考的脸部图像(和face model二选一即可) face model:需要参考的脸部模型(和source image二选一即可) swap model:仅用默认的即可。 facedetection:侦测脸的方法,默认即可。 face restore model:选择...
Nice, but is it possible to faceswap directly with multiple source faces without creating a model first so that reactor can be directly used in the workflows with multiple face images like FaceID portrait? 👍1Gourieff reacted with thumbs up emoji ...
"face_swapper = getFaceSwapModel(model)" ], [ "C:\stable diffusion\stable-diffusion-webui\extensions\sd-webui-reactor\scripts\reactor_swapper.py, line 103, getFaceSwapModel", "FS_MODEL = insightface.model_zoo.get_model(model_path, providers=PROVIDERS)" ...
File "F:\SD\sd-webui-aki-v4.6.1\extensions\sd-webui-reactor\scripts\reactor_faceswap.py", line 318, in postprocessresult, output, swapped = swap_face(File "F:\SD\sd-webui-aki-v4.6.1\extensions\sd-webui-reactor\scripts\reactor_swapper.py", line 516, in swap_facesource_faces = ...
FaceSwapScript, get_models, get_current_faces_model, analyze_faces, half_det_size, providers ) from scripts.reactor_logger import logger from reactor_utils import ( batch_tensor_to_pil, batched_pil_to_tensor, tensor_to_pil, img2tensor, tensor2img, save_face_model, ...
FaceSwapScript, get_models, get_current_faces_model, analyze_faces, half_det_size, providers ) from scripts.reactor_logger import logger from reactor_utils import ( batch_tensor_to_pil, batched_pil_to_tensor, tensor_to_pil, img2tensor, tensor2img, save_face_model, ...
Error occurred when executing ReActorFaceSwap: 'reactor' object has no attribute 'boost_model' File "F:\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "F:\ComfyUI\execution.py", line 81, in get_output_data ret...