.ipynb_checkpoints/pipeline_waifu-checkpoint.py

import torch
from diffusers import DiffusionPipeline

# waifu
# tokenizer
from transformers import XLMRobertaTokenizerFast
# text_encoder
from transformers import XLMRobertaModel
# scheduler
from diffusers import FlowMatchEulerDiscreteScheduler
# VAE
from diffusers.models import AutoencoderKL
# Transformer
from diffusers import SanaTransformer2DModel


class WaifuPipeline(DiffusionPipeline):
    r"""
    Pipeline for text-to-image generation using [waifu](https://github.com/recoilme/waifu).
    """

    model_cpu_offload_seq = "text_encoder->transformer->vae"
    _callback_tensor_inputs = ["latents", "prompt_embeds", "negative_prompt_embeds"]

    def __init__(
        self,
        tokenizer: XLMRobertaTokenizerFast,
        text_encoder: XLMRobertaModel,
        vae: AutoencoderKL,
        transformer: SanaTransformer2DModel,
        scheduler: FlowMatchEulerDiscreteScheduler,
    ):
        super().__init__()

        self.register_modules(
            tokenizer=tokenizer, text_encoder=text_encoder, vae=vae, transformer=transformer, scheduler=scheduler
        )

        self.vae_scale_factor = 8
        self.image_processor = PixArtImageProcessor(vae_scale_factor=self.vae_scale_factor)

    @torch.no_grad()
    @replace_example_docstring(EXAMPLE_DOC_STRING)
    def __call__(
        self,
        prompt: Union[str, List[str]] = None,
        negative_prompt: str = "",
        num_inference_steps: int = 20,
        timesteps: List[int] = None,
        sigmas: List[float] = None,
        guidance_scale: float = 4.5,
        num_images_per_prompt: Optional[int] = 1,
        height: int = 512,
        width: int = 512,
        eta: float = 0.0,
        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
        latents: Optional[torch.Tensor] = None,
        prompt_embeds: Optional[torch.Tensor] = None,
        prompt_attention_mask: Optional[torch.Tensor] = None,
        negative_prompt_embeds: Optional[torch.Tensor] = None,
        negative_prompt_attention_mask: Optional[torch.Tensor] = None,
        output_type: Optional[str] = "pil",
        return_dict: bool = True,
        callback_on_step_end: Optional[Callable[[int, int, Dict], None]] = None,
        callback_on_step_end_tensor_inputs: List[str] = ["latents"],
        max_sequence_length: int = 512,
    ) -> Union[SanaPipelineOutput, Tuple]:
        """
        Function invoked when calling the pipeline for generation.

        Args:
            prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts to guide the image generation. If not defined, one has to pass `prompt_embeds`.
                instead.
            negative_prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts not to guide the image generation. If not defined, one has to pass
                `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
                less than `1`).
            num_inference_steps (`int`, *optional*, defaults to 20):
                The number of denoising steps. More denoising steps usually lead to a higher quality image at the
                expense of slower inference.
            timesteps (`List[int]`, *optional*):
                Custom timesteps to use for the denoising process with schedulers which support a `timesteps` argument
                in their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is
                passed will be used. Must be in descending order.
            sigmas (`List[float]`, *optional*):
                Custom sigmas to use for the denoising process with schedulers which support a `sigmas` argument in
                their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is passed
                will be used.
            guidance_scale (`float`, *optional*, defaults to 4.5):
                Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
                `guidance_scale` is defined as `w` of equation 2. of [Imagen
                Paper](https://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
                1`. Higher guidance scale encourages to generate images that are closely linked to the text `prompt`,
                usually at the expense of lower image quality.
            num_images_per_prompt (`int`, *optional*, defaults to 1):
                The number of images to generate per prompt.
            height (`int`, *optional*, defaults to self.unet.config.sample_size):
                The height in pixels of the generated image.
            width (`int`, *optional*, defaults to self.unet.config.sample_size):
                The width in pixels of the generated image.
            eta (`float`, *optional*, defaults to 0.0):
                Corresponds to parameter eta (η) in the DDIM paper: https://arxiv.org/abs/2010.02502. Only applies to
                [`schedulers.DDIMScheduler`], will be ignored for others.
            generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
                One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
                to make generation deterministic.
            latents (`torch.Tensor`, *optional*):
                Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
                generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
                tensor will ge generated by sampling using the supplied random `generator`.
            prompt_embeds (`torch.Tensor`, *optional*):
                Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                provided, text embeddings will be generated from `prompt` input argument.
            prompt_attention_mask (`torch.Tensor`, *optional*): Pre-generated attention mask for text embeddings.
            negative_prompt_embeds (`torch.Tensor`, *optional*):
                Pre-generated negative text embeddings. For PixArt-Sigma this negative prompt should be "". If not
                provided, negative_prompt_embeds will be generated from `negative_prompt` input argument.
            negative_prompt_attention_mask (`torch.Tensor`, *optional*):
                Pre-generated attention mask for negative text embeddings.
            output_type (`str`, *optional*, defaults to `"pil"`):
                The output format of the generate image. Choose between
                [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
            return_dict (`bool`, *optional*, defaults to `True`):
                Whether or not to return a [`~pipelines.stable_diffusion.IFPipelineOutput`] instead of a plain tuple.
            callback_on_step_end (`Callable`, *optional*):
                A function that calls at the end of each denoising steps during the inference. The function is called
                with the following arguments: `callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int,
                callback_kwargs: Dict)`. `callback_kwargs` will include a list of all tensors as specified by
                `callback_on_step_end_tensor_inputs`.
            callback_on_step_end_tensor_inputs (`List`, *optional*):
                The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list
                will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
                `._callback_tensor_inputs` attribute of your pipeline class.
            max_sequence_length (`int` defaults to `512`):
                Maximum sequence length to use with the `prompt`.

        Examples:

        Returns:
            [`~pipelines.sana.pipeline_output.SanaPipelineOutput`] or `tuple`:
                If `return_dict` is `True`, [`~pipelines.sana.pipeline_output.SanaPipelineOutput`] is returned,
                otherwise a `tuple` is returned where the first element is a list with the generated images
        """

        if isinstance(callback_on_step_end, (PipelineCallback, MultiPipelineCallbacks)):
            callback_on_step_end_tensor_inputs = callback_on_step_end.tensor_inputs

        # 1. Check inputs. Raise error if not correct
        self.check_inputs(
            prompt,
            height,
            width,
            callback_on_step_end_tensor_inputs,
            negative_prompt,
            prompt_embeds,
            negative_prompt_embeds,
            prompt_attention_mask,
            negative_prompt_attention_mask,
        )

        self._guidance_scale = guidance_scale
        self._interrupt = False

        # 2. Default height and width to transformer
        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

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

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

        # 5. Prepare latents.
        latent_channels = self.transformer.config.in_channels
        latents = self.prepare_latents(
            batch_size * num_images_per_prompt,
            latent_channels,
            height,
            width,
            torch.float32,
            device,
            generator,
            latents,
        )

        # 6. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline
        extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)

        # 7. Denoising loop
        num_warmup_steps = max(len(timesteps) - num_inference_steps * self.scheduler.order, 0)
        self._num_timesteps = len(timesteps)

        with self.progress_bar(total=num_inference_steps) as progress_bar:
            for i, t in enumerate(timesteps):
                if self.interrupt:
                    continue

                latent_model_input = torch.cat([latents] * 2) if self.do_classifier_free_guidance else latents
                latent_model_input = latent_model_input.to(prompt_embeds.dtype)

                # broadcast to batch dimension in a way that's compatible with ONNX/Core ML
                timestep = t.expand(latent_model_input.shape[0]).to(latents.dtype)

                # predict noise model_output
                noise_pred = self.transformer(
                    latent_model_input,
                    encoder_hidden_states=prompt_embeds,
                    encoder_attention_mask=prompt_attention_mask,
                    timestep=timestep,
                    return_dict=False,
                )[0]
                noise_pred = noise_pred.float()

                # perform guidance
                if self.do_classifier_free_guidance:
                    noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
                    noise_pred = noise_pred_uncond + guidance_scale * (noise_pred_text - noise_pred_uncond)

                # learned sigma
                if self.transformer.config.out_channels // 2 == latent_channels:
                    noise_pred = noise_pred.chunk(2, dim=1)[0]
                else:
                    noise_pred = noise_pred

                # compute previous image: x_t -> x_t-1
                latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs, return_dict=False)[0]

                if callback_on_step_end is not None:
                    callback_kwargs = {}
                    for k in callback_on_step_end_tensor_inputs:
                        callback_kwargs[k] = locals()[k]
                    callback_outputs = callback_on_step_end(self, i, t, callback_kwargs)

                    latents = callback_outputs.pop("latents", latents)
                    prompt_embeds = callback_outputs.pop("prompt_embeds", prompt_embeds)
                    negative_prompt_embeds = callback_outputs.pop("negative_prompt_embeds", negative_prompt_embeds)

                # call the callback, if provided
                if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0):
                    progress_bar.update()

        if output_type == "latent":
            image = latents
        else:
            latents = latents.to(self.vae.dtype)
            image = self.vae.decode(latents / self.vae.config.scaling_factor, return_dict=False)[0]
            if use_resolution_binning:
                image = self.image_processor.resize_and_crop_tensor(image, orig_width, orig_height)

        if not output_type == "latent":
            image = self.image_processor.postprocess(image, output_type=output_type)

        # Offload all models
        self.maybe_free_model_hooks()

        if not return_dict:
            return (image,)

        return SanaPipelineOutput(images=image)