ZChao97 / Roop-new
此作者的其他模型
拍摄一段视频或一张照片，并将其中的人脸替换成您选择的人脸。您只需要一张所需人脸的图像。无需数据集，无需训练。
用户应遵守当地法律并负责任地使用该软件。如果使用真实面孔，请征得用户同意，并在分享时清晰标注深度伪造内容。开发者对用户行为不承担任何责任。
200
Service Inference
Usage Instructions
Examples
Model Details
Version List
Input
Form
JSON
Generated Result
Form
JSON
Preview
Generation Time：18.01 s
source: /tmp/tmp5_sqwrtkswap img.jpg
source1: None
target: /tmp/tmpk5qxsmayinput.jpg
keep_fps: True
keep_frames: True
/root/.pyenv/versions/3.10.18/lib/python3.10/site-packages/insightface/utils/transform.py:68: FutureWarning: `rcond` parameter will change to the default of machine precision times ``max(M, N)`` where M and N are the input matrix dimensions.
To use the future default and silence this warning we advise to pass `rcond=None`, to keep using the old, explicitly pass `rcond=-1`.
P = np.linalg.lstsq(X_homo, Y)[0].T # Affine matrix. 3 x 4
source_img: /tmp/tmp5_sqwrtkswap img.jpg
target_path: /tmp/tmpk5qxsmayinput.jpg
./output.png
Status: 换脸成功1!
Billing Information
When this model performs inference to generate content, in addition to charging computing power fees, it will also charge additional usage fees. Therefore, the total cost of this model consists of two parts: usage fees and computing power fees.
Usage Fee:
The usage fee amount is set by the model uploader and authorized by the platform to collect it on their behalf from users.
Computing Power Fee:
This model is billed based on the amount of computing power used.