threestudio/models/guidance/stable_zero123_guidance.py [222:261]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            ],
            dim=-1,
        )[:, None, :].to(self.device)
        cond = {}
        clip_emb = self.model.cc_projection(
            torch.cat(
                [
                    (self.c_crossattn if c_crossattn is None else c_crossattn).repeat(
                        len(T), 1, 1
                    ),
                    T,
                ],
                dim=-1,
            )
        )
        cond["c_crossattn"] = [
            torch.cat([torch.zeros_like(clip_emb).to(self.device), clip_emb], dim=0)
        ]
        cond["c_concat"] = [
            torch.cat(
                [
                    torch.zeros_like(self.c_concat)
                    .repeat(len(T), 1, 1, 1)
                    .to(self.device),
                    (self.c_concat if c_concat is None else c_concat).repeat(
                        len(T), 1, 1, 1
                    ),
                ],
                dim=0,
            )
        ]
        return cond

    def __call__(
        self,
        rgb: Float[Tensor, "B H W C"],
        elevation: Float[Tensor, "B"],
        azimuth: Float[Tensor, "B"],
        camera_distances: Float[Tensor, "B"],
        rgb_as_latents=False,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



threestudio/models/guidance/zero123_guidance.py [223:262]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            ],
            dim=-1,
        )[:, None, :].to(self.device)
        cond = {}
        clip_emb = self.model.cc_projection(
            torch.cat(
                [
                    (self.c_crossattn if c_crossattn is None else c_crossattn).repeat(
                        len(T), 1, 1
                    ),
                    T,
                ],
                dim=-1,
            )
        )
        cond["c_crossattn"] = [
            torch.cat([torch.zeros_like(clip_emb).to(self.device), clip_emb], dim=0)
        ]
        cond["c_concat"] = [
            torch.cat(
                [
                    torch.zeros_like(self.c_concat)
                    .repeat(len(T), 1, 1, 1)
                    .to(self.device),
                    (self.c_concat if c_concat is None else c_concat).repeat(
                        len(T), 1, 1, 1
                    ),
                ],
                dim=0,
            )
        ]
        return cond

    def __call__(
        self,
        rgb: Float[Tensor, "B H W C"],
        elevation: Float[Tensor, "B"],
        azimuth: Float[Tensor, "B"],
        camera_distances: Float[Tensor, "B"],
        rgb_as_latents=False,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -