Autoencoder3d adapted from Stable Diffusion 1.x, 2.x and XL.
(pretrained_path=None, z_dim=None, device='cpu', **kwargs)
| 46 | |
| 47 | |
| 48 | def _video_vae(pretrained_path=None, z_dim=None, device='cpu', **kwargs): |
| 49 | """ |
| 50 | Autoencoder3d adapted from Stable Diffusion 1.x, 2.x and XL. |
| 51 | """ |
| 52 | # params |
| 53 | cfg = dict( |
| 54 | dim=96, |
| 55 | z_dim=z_dim, |
| 56 | dim_mult=[1, 2, 4, 4], |
| 57 | num_res_blocks=2, |
| 58 | attn_scales=[], |
| 59 | temperal_downsample=[False, True, True], |
| 60 | dropout=0.0) |
| 61 | cfg.update(**kwargs) |
| 62 | |
| 63 | # init model |
| 64 | with torch.device('meta'): |
| 65 | model = WanVAE_(**cfg) |
| 66 | |
| 67 | # load checkpoint |
| 68 | model.load_state_dict( |
| 69 | load_state_dict(pretrained_path), assign=True) |
| 70 | |
| 71 | return model |
| 72 | |
| 73 | |
| 74 | class WanVAE: |
no test coverage detected