threestudio/models/guidance/stable_diffusion_bsd_guidance.py [1016:1077]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def get_latents(
        self, rgb_BCHW: Float[Tensor, "B C H W"], rgb_as_latents=False
    ) -> Float[Tensor, "B 4 64 64"]:
        if rgb_as_latents:
            latents = F.interpolate(
                rgb_BCHW, (64, 64), mode="bilinear", align_corners=False
            )
        else:
            rgb_BCHW_512 = F.interpolate(
                rgb_BCHW, (512, 512), mode="bilinear", align_corners=False
            )
            # encode image into latents with vae
            latents = self.encode_images(rgb_BCHW_512)
        return latents

    def forward(
        self,
        rgb: Float[Tensor, "B H W C"],
        prompt_utils: PromptProcessorOutput,
        elevation: Float[Tensor, "B"],
        azimuth: Float[Tensor, "B"],
        camera_distances: Float[Tensor, "B"],
        mvp_mtx: Float[Tensor, "B 4 4"],
        c2w: Float[Tensor, "B 4 4"],
        rgb_as_latents=False,
        mask: Float[Tensor, "B H W 1"] = None,
        lora_prompt_utils = None,
        **kwargs,
    ):
        batch_size = rgb.shape[0]

        rgb_BCHW = rgb.permute(0, 3, 1, 2)
        latents = self.get_latents(rgb_BCHW, rgb_as_latents=rgb_as_latents)

        if mask is not None: mask = mask.permute(0, 3, 1, 2)

        # view-dependent text embeddings
        text_embeddings_vd = prompt_utils.get_text_embeddings(
            elevation,
            azimuth,
            camera_distances,
            view_dependent_prompting=self.cfg.view_dependent_prompting,
        )
        if lora_prompt_utils is not None:
            # input text embeddings, view-independent
            text_embeddings = lora_prompt_utils.get_text_embeddings(
                elevation, azimuth, camera_distances, view_dependent_prompting=False
            )
        else:
            # input text embeddings, view-independent
            text_embeddings = prompt_utils.get_text_embeddings(
                elevation, azimuth, camera_distances, view_dependent_prompting=False
            )   

        if self.cfg.camera_condition_type == "extrinsics":
            camera_condition = c2w
        elif self.cfg.camera_condition_type == "mvp":
            camera_condition = mvp_mtx
        else:
            raise ValueError(
                f"Unknown camera_condition_type {self.cfg.camera_condition_type}"
            )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



threestudio/models/guidance/stable_diffusion_vsd_guidance.py [900:961]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def get_latents(
        self, rgb_BCHW: Float[Tensor, "B C H W"], rgb_as_latents=False
    ) -> Float[Tensor, "B 4 64 64"]:
        if rgb_as_latents:
            latents = F.interpolate(
                rgb_BCHW, (64, 64), mode="bilinear", align_corners=False
            )
        else:
            rgb_BCHW_512 = F.interpolate(
                rgb_BCHW, (512, 512), mode="bilinear", align_corners=False
            )
            # encode image into latents with vae
            latents = self.encode_images(rgb_BCHW_512)
        return latents

    def forward(
        self,
        rgb: Float[Tensor, "B H W C"],
        prompt_utils: PromptProcessorOutput,
        elevation: Float[Tensor, "B"],
        azimuth: Float[Tensor, "B"],
        camera_distances: Float[Tensor, "B"],
        mvp_mtx: Float[Tensor, "B 4 4"],
        c2w: Float[Tensor, "B 4 4"],
        rgb_as_latents=False,
        mask: Float[Tensor, "B H W 1"] = None,
        lora_prompt_utils = None,
        **kwargs,
    ):
        batch_size = rgb.shape[0]

        rgb_BCHW = rgb.permute(0, 3, 1, 2)
        latents = self.get_latents(rgb_BCHW, rgb_as_latents=rgb_as_latents)

        if mask is not None: mask = mask.permute(0, 3, 1, 2)

        # view-dependent text embeddings
        text_embeddings_vd = prompt_utils.get_text_embeddings(
            elevation,
            azimuth,
            camera_distances,
            view_dependent_prompting=self.cfg.view_dependent_prompting,
        )
        if lora_prompt_utils is not None:
            # input text embeddings, view-independent
            text_embeddings = lora_prompt_utils.get_text_embeddings(
                elevation, azimuth, camera_distances, view_dependent_prompting=False
            )
        else:
            # input text embeddings, view-independent
            text_embeddings = prompt_utils.get_text_embeddings(
                elevation, azimuth, camera_distances, view_dependent_prompting=False
            )   

        if self.cfg.camera_condition_type == "extrinsics":
            camera_condition = c2w
        elif self.cfg.camera_condition_type == "mvp":
            camera_condition = mvp_mtx
        else:
            raise ValueError(
                f"Unknown camera_condition_type {self.cfg.camera_condition_type}"
            )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -