Method prepare_input

inference/ace_plus_diffusers.py:41–66

(self,
                      image,
                      mask,
                      batch_size=1,
                      dtype = torch.bfloat16,
                      num_images_per_prompt=1,
                      height=512,
                      width=512,
                      generator=None)

        self.load_default(cfg.DEFAULT_PARAS)

    def prepare_input(self,
                      image,
                      mask,
                      batch_size=1,
                      dtype = torch.bfloat16,
                      num_images_per_prompt=1,
                      height=512,
                      width=512,
                      generator=None):
        num_channels_latents = self.pipe.vae.config.latent_channels
        # import pdb;pdb.set_trace()
        mask, masked_image_latents = self.pipe.prepare_mask_latents(
            mask.unsqueeze(0),
            image.unsqueeze(0).to(we.device_id, dtype = dtype),
            batch_size,
            num_channels_latents,
            num_images_per_prompt,
            height,
            width,
            dtype,
            we.device_id,
            generator,
        )
        # import pdb;pdb.set_trace()
        masked_image_latents = torch.cat((masked_image_latents, mask), dim=-1)
        return masked_image_latents

    @torch.no_grad()
    def __call__(self,