MCPcopy Create free account

hub / github.com/TencentARC/StereoCrafter / functions

Functions32 in github.com/TencentARC/StereoCrafter

⨍ Functions 32◇ Types & classes 4
↓ 2 callersFunction_filter2d
(input, kernel)
pipelines/stereo_video_inpainting.py:662
↓ 2 callersFunction_gaussian
(window_size: int, sigma)
pipelines/stereo_video_inpainting.py:685
↓ 2 callersFunction_resize_with_antialiasing
(input, size, interpolation="bicubic", align_corners=True)
pipelines/stereo_video_inpainting.py:611
↓ 2 callersMethoddecode_latents
(self, latents, num_frames, decode_chunk_size=14)
pipelines/stereo_video_inpainting.py:262
↓ 2 callersFunctiontensor2vid
(video: torch.Tensor, processor, output_type="np")
pipelines/stereo_video_inpainting.py:29
↓ 2 callersFunctionwrite_video_opencv
(input_frames, fps, output_video_path)
inpainting_inference.py:123
↓ 1 callersFunctionDepthSplatting
Depth-Based Video Splatting Using the Video Depth. Args: input_video_path: Path to the input video. output_video_path: Path t
depth_splatting_inference.py:199
↓ 1 callersMethod__init__
( self, unet_path: str, pre_trained_path: str, cpu_offload: str = "model",
depth_splatting_inference.py:57
↓ 1 callersFunction_append_dims
Appends dimensions to the end of a tensor until it has target_dims dimensions.
pipelines/stereo_video_inpainting.py:21
↓ 1 callersFunction_compute_padding
Compute padding tuple.
pipelines/stereo_video_inpainting.py:639
↓ 1 callersMethod_encode_image
(self, image, device, num_videos_per_prompt, do_classifier_free_guidance)
pipelines/stereo_video_inpainting.py:103
↓ 1 callersMethod_encode_mask_frames
( self, frames_mask: torch.Tensor, device, num_videos_per_prompt, do_c
pipelines/stereo_video_inpainting.py:214
↓ 1 callersMethod_encode_vae_frames
( self, frames: torch.Tensor, device, num_videos_per_prompt, do_classi
pipelines/stereo_video_inpainting.py:183
↓ 1 callersFunction_gaussian_blur2d
(input, kernel_size, sigma)
pipelines/stereo_video_inpainting.py:701
↓ 1 callersMethod_get_add_time_ids
( self, fps, motion_bucket_id, noise_aug_strength, dtype, batc
pipelines/stereo_video_inpainting.py:234
↓ 1 callersFunctionblend_h
(a: torch.Tensor, b: torch.Tensor, overlap_size: int)
inpainting_inference.py:18
↓ 1 callersFunctionblend_v
(a: torch.Tensor, b: torch.Tensor, overlap_size: int)
inpainting_inference.py:28
↓ 1 callersMethodcheck_inputs
(self, image, height, width)
pipelines/stereo_video_inpainting.py:291
↓ 1 callersMethodinfer
( self, input_video_path: str, output_video_path: str, process_length: int = -
depth_splatting_inference.py:95
↓ 1 callersMethodprepare_latents
( self, batch_size, num_frames, num_channels_latents, height,
pipelines/stereo_video_inpainting.py:305
↓ 1 callersFunctionread_video_frames
(video_path, process_length, target_fps, max_res, dataset="open")
depth_splatting_inference.py:21
↓ 1 callersFunctionspatial_tiled_process
( cond_frames, mask_frames, process_func, tile_num, spatial_n_compress=8, **kargs, )
inpainting_inference.py:38
Method__call__
r""" The call function to the pipeline for generation. Args: frames: (f, c, h, w) in [0, 1], torch.FloatTensor
pipelines/stereo_video_inpainting.py:357
Method__init__
(self, eps=1e-6, occlu_map=False)
depth_splatting_inference.py:161
Method__init__
( self, vae: AutoencoderKLTemporalDecoder, image_encoder: CLIPVisionModelWithProjectio
pipelines/stereo_video_inpainting.py:80
Method_encode_vae_image
( self, image: torch.Tensor, device, num_videos_per_prompt, do_classif
pipelines/stereo_video_inpainting.py:160
Methoddo_classifier_free_guidance
(self)
pipelines/stereo_video_inpainting.py:347
Methodforward
:param im: BCHW :param disp: B1HW :return: BCHW detach will lead to unconverge!!
depth_splatting_inference.py:167
Methodguidance_scale
(self)
pipelines/stereo_video_inpainting.py:340
Functionmain
( pre_trained_path, unet_path, input_video_path, save_dir, frames_chunk=23, overlap=3,
inpainting_inference.py:142
Functionmain
( input_video_path: str, output_video_path: str, unet_path: str, pre_trained_path: str, ma
depth_splatting_inference.py:273
Methodnum_timesteps
(self)
pipelines/stereo_video_inpainting.py:353