mirror of
https://github.com/THUDM/CogVideo.git
synced 2025-12-02 10:32:09 +08:00
957a210a72
- Integrated progress tracking with upscale model loading. - Implemented conditional latent upscaling using the upscale model. - Processed batch video frames using PyTorch and converted them to PIL images. - load_torch_file for params_ema convert weights
23 lines
1.0 KiB
Python
23 lines
1.0 KiB
Python
import torch
|
|
import torch.nn as nn
|
|
|
|
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
|
backwarp_tenGrid = {}
|
|
|
|
|
|
def warp(tenInput, tenFlow):
|
|
k = (str(tenFlow.device), str(tenFlow.size()))
|
|
if k not in backwarp_tenGrid:
|
|
tenHorizontal = torch.linspace(-1.0, 1.0, tenFlow.shape[3], device=device).view(
|
|
1, 1, 1, tenFlow.shape[3]).expand(tenFlow.shape[0], -1, tenFlow.shape[2], -1)
|
|
tenVertical = torch.linspace(-1.0, 1.0, tenFlow.shape[2], device=device).view(
|
|
1, 1, tenFlow.shape[2], 1).expand(tenFlow.shape[0], -1, -1, tenFlow.shape[3])
|
|
backwarp_tenGrid[k] = torch.cat(
|
|
[tenHorizontal, tenVertical], 1).to(device)
|
|
|
|
tenFlow = torch.cat([tenFlow[:, 0:1, :, :] / ((tenInput.shape[3] - 1.0) / 2.0),
|
|
tenFlow[:, 1:2, :, :] / ((tenInput.shape[2] - 1.0) / 2.0)], 1)
|
|
|
|
g = (backwarp_tenGrid[k] + tenFlow).permute(0, 2, 3, 1)
|
|
return torch.nn.functional.grid_sample(input=tenInput, grid=g, mode='bilinear', padding_mode='border', align_corners=True)
|