Method build_mask

diffsynth/models/stepvideo_vae.py:1040–1050

(self, data, is_bound, border_width)

        return x
    
    def build_mask(self, data, is_bound, border_width):
        _, _, _, H, W = data.shape
        h = self.build_1d_mask(H, is_bound[0], is_bound[1], border_width[0])
        w = self.build_1d_mask(W, is_bound[2], is_bound[3], border_width[1])

        h = repeat(h, "H -> H W", H=H, W=W)
        w = repeat(w, "W -> H W", H=H, W=W)

        mask = torch.stack([h, w]).min(dim=0).values
        mask = rearrange(mask, "H W -> 1 1 1 H W")
        return mask
    
    def tiled_decode(self, hidden_states, device, tile_size=(34, 34), tile_stride=(16, 16)):
        B, T, C, H, W = hidden_states.shape