diffusers-version/tora/i2v_pipeline.py [734:780]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        )
        self._guidance_scale = guidance_scale
        self._attention_kwargs = attention_kwargs
        self._interrupt = False

        # 2. Default call parameters
        if prompt is not None and isinstance(prompt, str):
            batch_size = 1
        elif prompt is not None and isinstance(prompt, list):
            batch_size = len(prompt)
        else:
            batch_size = prompt_embeds.shape[0]

        device = self._execution_device

        # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
        # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
        # corresponds to doing no classifier free guidance.
        do_classifier_free_guidance = guidance_scale > 1.0

        # 3. Encode input prompt
        prompt_embeds, negative_prompt_embeds = self.encode_prompt(
            prompt=prompt,
            negative_prompt=negative_prompt,
            do_classifier_free_guidance=do_classifier_free_guidance,
            num_videos_per_prompt=num_videos_per_prompt,
            prompt_embeds=prompt_embeds,
            negative_prompt_embeds=negative_prompt_embeds,
            max_sequence_length=max_sequence_length,
            device=device,
        )
        if do_classifier_free_guidance:
            prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds], dim=0)

        # 4. Prepare timesteps
        timesteps, num_inference_steps = retrieve_timesteps(self.scheduler, num_inference_steps, device, timesteps)
        self._num_timesteps = len(timesteps)

        # 5. Prepare latents
        latent_frames = (num_frames - 1) // self.vae_scale_factor_temporal + 1

        # For CogVideoX 1.5, the latent frames should be padded to make it divisible by patch_size_t
        patch_size_t = self.transformer.config.patch_size_t
        additional_frames = 0
        if patch_size_t is not None and latent_frames % patch_size_t != 0:
            additional_frames = patch_size_t - latent_frames % patch_size_t
            num_frames += additional_frames * self.vae_scale_factor_temporal
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



diffusers-version/tora/t2v_pipeline.py [661:707]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        )
        self._guidance_scale = guidance_scale
        self._attention_kwargs = attention_kwargs
        self._interrupt = False

        # 2. Default call parameters
        if prompt is not None and isinstance(prompt, str):
            batch_size = 1
        elif prompt is not None and isinstance(prompt, list):
            batch_size = len(prompt)
        else:
            batch_size = prompt_embeds.shape[0]

        device = self._execution_device

        # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
        # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
        # corresponds to doing no classifier free guidance.
        do_classifier_free_guidance = guidance_scale > 1.0

        # 3. Encode input prompt
        prompt_embeds, negative_prompt_embeds = self.encode_prompt(
            prompt=prompt,
            negative_prompt=negative_prompt,
            do_classifier_free_guidance=do_classifier_free_guidance,
            num_videos_per_prompt=num_videos_per_prompt,
            prompt_embeds=prompt_embeds,
            negative_prompt_embeds=negative_prompt_embeds,
            max_sequence_length=max_sequence_length,
            device=device,
        )
        if do_classifier_free_guidance:
            prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds], dim=0)

        # 4. Prepare timesteps
        timesteps, num_inference_steps = retrieve_timesteps(self.scheduler, num_inference_steps, device, timesteps)
        self._num_timesteps = len(timesteps)

        # 5. Prepare latents
        latent_frames = (num_frames - 1) // self.vae_scale_factor_temporal + 1

        # For CogVideoX 1.5, the latent frames should be padded to make it divisible by patch_size_t
        patch_size_t = self.transformer.config.patch_size_t
        additional_frames = 0
        if patch_size_t is not None and latent_frames % patch_size_t != 0:
            additional_frames = patch_size_t - latent_frames % patch_size_t
            num_frames += additional_frames * self.vae_scale_factor_temporal
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -