x: [B, L, C].

x: [B, L, C].

imgs: [B, 3, H, W] of torch.float32. - mean: [0.48145466, 0.4578275, 0.40821073] - std: [0.26862954, 0.2613025

Fix bfloat16 support for nearest neighbor interpolation.

Merge the video and audio into a new video, with the duration set to the shorter of the two, and overwrite the original video file. Para

Draw result boxes Copy from nanodet/util/visualization.py

Modified from https://github.com/hehao13/CameraCtrl/blob/main/inference.py

Modified from https://github.com/hehao13/CameraCtrl/blob/main/inference.py

将 PIL 图像缩放到接近指定像素面积（target_area），保持原始宽高比， 并确保新宽度和高度均为 32 的整数倍。 参数: img (PIL.Image.Image): 输入图像 target_area (int): 目标像素总面

Scale model input.

Ensures interchangeability with schedulers that need to scale the denoising model input depending on the current timestep. A

Sets the begin index for the scheduler. This function should be run from pipeline before the inference. Args: begin_index

Sets the begin index for the scheduler. This function should be run from pipeline before the inference. Args: begin_inde

Set timesteps - routes to distill or original scheduler.

Sets the discrete timesteps used for the diffusion chain (to be run before inference). Args: num_inference_steps (`int`):

Perform scheduler step.

The current step index.