threestudio/models/guidance/stable_zero123_guidance.py [102:137]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        self.config = OmegaConf.load(self.cfg.pretrained_config)
        # TODO: seems it cannot load into fp16...
        self.weights_dtype = torch.float32
        self.model = load_model_from_config(
            self.config,
            self.cfg.pretrained_model_name_or_path,
            device=self.device,
            vram_O=self.cfg.vram_O,
        )

        for p in self.model.parameters():
            p.requires_grad_(False)

        # timesteps: use diffuser for convenience... hope it's alright.
        self.num_train_timesteps = self.config.model.params.timesteps

        self.scheduler = DDIMScheduler(
            self.num_train_timesteps,
            self.config.model.params.linear_start,
            self.config.model.params.linear_end,
            beta_schedule="scaled_linear",
            clip_sample=False,
            set_alpha_to_one=False,
            steps_offset=1,
        )

        self.num_train_timesteps = self.scheduler.config.num_train_timesteps
        self.set_min_max_steps()  # set to default value

        self.alphas: Float[Tensor, "..."] = self.scheduler.alphas_cumprod.to(
            self.device
        )

        self.grad_clip_val: Optional[float] = None

        self.prepare_embeddings(self.cfg.cond_image_path)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



threestudio/models/guidance/zero123_guidance.py [105:140]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        self.config = OmegaConf.load(self.cfg.pretrained_config)
        # TODO: seems it cannot load into fp16...
        self.weights_dtype = torch.float32
        self.model = load_model_from_config(
            self.config,
            self.cfg.pretrained_model_name_or_path,
            device=self.device,
            vram_O=self.cfg.vram_O,
        )

        for p in self.model.parameters():
            p.requires_grad_(False)

        # timesteps: use diffuser for convenience... hope it's alright.
        self.num_train_timesteps = self.config.model.params.timesteps

        self.scheduler = DDIMScheduler(
            self.num_train_timesteps,
            self.config.model.params.linear_start,
            self.config.model.params.linear_end,
            beta_schedule="scaled_linear",
            clip_sample=False,
            set_alpha_to_one=False,
            steps_offset=1,
        )

        self.num_train_timesteps = self.scheduler.config.num_train_timesteps
        self.set_min_max_steps()  # set to default value

        self.alphas: Float[Tensor, "..."] = self.scheduler.alphas_cumprod.to(
            self.device
        )

        self.grad_clip_val: Optional[float] = None

        self.prepare_embeddings(self.cfg.cond_image_path)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -