diff --git a/src/diffusers/modular_pipelines/stable_diffusion_xl/decoders.py b/src/diffusers/modular_pipelines/stable_diffusion_xl/decoders.py index feb78e1ef1..1a0b36a91c 100644 --- a/src/diffusers/modular_pipelines/stable_diffusion_xl/decoders.py +++ b/src/diffusers/modular_pipelines/stable_diffusion_xl/decoders.py @@ -81,10 +81,7 @@ class StableDiffusionXLDecodeStep(ModularPipelineBlocks): components.vae.to(dtype=torch.float32) use_torch_2_0_or_xformers = isinstance( components.vae.decoder.mid_block.attentions[0].processor, - ( - AttnProcessor2_0, - XFormersAttnProcessor, - ), + (AttnProcessor2_0, XFormersAttnProcessor), ) # if xformers or torch_2_0 is used attention block does not need # to be in float32 which can save lots of memory diff --git a/src/diffusers/pipelines/stable_diffusion/pipeline_stable_unclip.py b/src/diffusers/pipelines/stable_diffusion/pipeline_stable_unclip.py index a134244e3e..62e67a1c9b 100644 --- a/src/diffusers/pipelines/stable_diffusion/pipeline_stable_unclip.py +++ b/src/diffusers/pipelines/stable_diffusion/pipeline_stable_unclip.py @@ -23,19 +23,15 @@ from ...image_processor import VaeImageProcessor from ...loaders import StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin from ...models import AutoencoderKL, PriorTransformer, UNet2DConditionModel from ...models.embeddings import get_timestep_embedding -from ...models.lora import adjust_lora_scale_text_encoder from ...schedulers import KarrasDiffusionSchedulers from ...utils import ( - USE_PEFT_BACKEND, - deprecate, is_torch_xla_available, logging, replace_example_docstring, - scale_lora_layers, - unscale_lora_layers, ) from ...utils.torch_utils import randn_tensor -from ..pipeline_utils import DiffusionPipeline, ImagePipelineOutput, StableDiffusionMixin +from ..pipeline_utils import DiffusionPipeline, ImagePipelineOutput +from .pipeline_stable_diffusion_utils import StableDiffusionMixin from .stable_unclip_image_normalizer import StableUnCLIPImageNormalizer @@ -260,235 +256,7 @@ class StableUnCLIPPipeline( return prompt_embeds, text_enc_hid_states, text_mask - # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline._encode_prompt - def _encode_prompt( - self, - prompt, - device, - num_images_per_prompt, - do_classifier_free_guidance, - negative_prompt=None, - prompt_embeds: Optional[torch.Tensor] = None, - negative_prompt_embeds: Optional[torch.Tensor] = None, - lora_scale: Optional[float] = None, - **kwargs, - ): - deprecation_message = "`_encode_prompt()` is deprecated and it will be removed in a future version. Use `encode_prompt()` instead. Also, be aware that the output format changed from a concatenated tensor to a tuple." - deprecate("_encode_prompt()", "1.0.0", deprecation_message, standard_warn=False) - - prompt_embeds_tuple = self.encode_prompt( - prompt=prompt, - device=device, - num_images_per_prompt=num_images_per_prompt, - do_classifier_free_guidance=do_classifier_free_guidance, - negative_prompt=negative_prompt, - prompt_embeds=prompt_embeds, - negative_prompt_embeds=negative_prompt_embeds, - lora_scale=lora_scale, - **kwargs, - ) - - # concatenate for backwards comp - prompt_embeds = torch.cat([prompt_embeds_tuple[1], prompt_embeds_tuple[0]]) - - return prompt_embeds - - # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.encode_prompt - def encode_prompt( - self, - prompt, - device, - num_images_per_prompt, - do_classifier_free_guidance, - negative_prompt=None, - prompt_embeds: Optional[torch.Tensor] = None, - negative_prompt_embeds: Optional[torch.Tensor] = None, - lora_scale: Optional[float] = None, - clip_skip: Optional[int] = None, - ): - r""" - Encodes the prompt into text encoder hidden states. - - Args: - prompt (`str` or `List[str]`, *optional*): - prompt to be encoded - device: (`torch.device`): - torch device - num_images_per_prompt (`int`): - number of images that should be generated per prompt - do_classifier_free_guidance (`bool`): - whether to use classifier free guidance or not - 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`). - 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. - negative_prompt_embeds (`torch.Tensor`, *optional*): - Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt - weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input - argument. - lora_scale (`float`, *optional*): - A LoRA scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded. - clip_skip (`int`, *optional*): - Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that - the output of the pre-final layer will be used for computing the prompt embeddings. - """ - # set lora scale so that monkey patched LoRA - # function of text encoder can correctly access it - if lora_scale is not None and isinstance(self, StableDiffusionLoraLoaderMixin): - self._lora_scale = lora_scale - - # dynamically adjust the LoRA scale - if not USE_PEFT_BACKEND: - adjust_lora_scale_text_encoder(self.text_encoder, lora_scale) - else: - scale_lora_layers(self.text_encoder, lora_scale) - - 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] - - if prompt_embeds is None: - # textual inversion: process multi-vector tokens if necessary - if isinstance(self, TextualInversionLoaderMixin): - prompt = self.maybe_convert_prompt(prompt, self.tokenizer) - - text_inputs = self.tokenizer( - prompt, - padding="max_length", - max_length=self.tokenizer.model_max_length, - truncation=True, - return_tensors="pt", - ) - text_input_ids = text_inputs.input_ids - untruncated_ids = self.tokenizer(prompt, padding="longest", return_tensors="pt").input_ids - - if untruncated_ids.shape[-1] >= text_input_ids.shape[-1] and not torch.equal( - text_input_ids, untruncated_ids - ): - removed_text = self.tokenizer.batch_decode( - untruncated_ids[:, self.tokenizer.model_max_length - 1 : -1] - ) - logger.warning( - "The following part of your input was truncated because CLIP can only handle sequences up to" - f" {self.tokenizer.model_max_length} tokens: {removed_text}" - ) - - if hasattr(self.text_encoder.config, "use_attention_mask") and self.text_encoder.config.use_attention_mask: - attention_mask = text_inputs.attention_mask.to(device) - else: - attention_mask = None - - if clip_skip is None: - prompt_embeds = self.text_encoder(text_input_ids.to(device), attention_mask=attention_mask) - prompt_embeds = prompt_embeds[0] - else: - prompt_embeds = self.text_encoder( - text_input_ids.to(device), attention_mask=attention_mask, output_hidden_states=True - ) - # Access the `hidden_states` first, that contains a tuple of - # all the hidden states from the encoder layers. Then index into - # the tuple to access the hidden states from the desired layer. - prompt_embeds = prompt_embeds[-1][-(clip_skip + 1)] - # We also need to apply the final LayerNorm here to not mess with the - # representations. The `last_hidden_states` that we typically use for - # obtaining the final prompt representations passes through the LayerNorm - # layer. - prompt_embeds = self.text_encoder.text_model.final_layer_norm(prompt_embeds) - - if self.text_encoder is not None: - prompt_embeds_dtype = self.text_encoder.dtype - elif self.unet is not None: - prompt_embeds_dtype = self.unet.dtype - else: - prompt_embeds_dtype = prompt_embeds.dtype - - prompt_embeds = prompt_embeds.to(dtype=prompt_embeds_dtype, device=device) - - bs_embed, seq_len, _ = prompt_embeds.shape - # duplicate text embeddings for each generation per prompt, using mps friendly method - prompt_embeds = prompt_embeds.repeat(1, num_images_per_prompt, 1) - prompt_embeds = prompt_embeds.view(bs_embed * num_images_per_prompt, seq_len, -1) - - # get unconditional embeddings for classifier free guidance - if do_classifier_free_guidance and negative_prompt_embeds is None: - uncond_tokens: List[str] - if negative_prompt is None: - uncond_tokens = [""] * batch_size - elif prompt is not None and type(prompt) is not type(negative_prompt): - raise TypeError( - f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !=" - f" {type(prompt)}." - ) - elif isinstance(negative_prompt, str): - uncond_tokens = [negative_prompt] - elif batch_size != len(negative_prompt): - raise ValueError( - f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:" - f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches" - " the batch size of `prompt`." - ) - else: - uncond_tokens = negative_prompt - - # textual inversion: process multi-vector tokens if necessary - if isinstance(self, TextualInversionLoaderMixin): - uncond_tokens = self.maybe_convert_prompt(uncond_tokens, self.tokenizer) - - max_length = prompt_embeds.shape[1] - uncond_input = self.tokenizer( - uncond_tokens, - padding="max_length", - max_length=max_length, - truncation=True, - return_tensors="pt", - ) - - if hasattr(self.text_encoder.config, "use_attention_mask") and self.text_encoder.config.use_attention_mask: - attention_mask = uncond_input.attention_mask.to(device) - else: - attention_mask = None - - negative_prompt_embeds = self.text_encoder( - uncond_input.input_ids.to(device), - attention_mask=attention_mask, - ) - negative_prompt_embeds = negative_prompt_embeds[0] - - if do_classifier_free_guidance: - # duplicate unconditional embeddings for each generation per prompt, using mps friendly method - seq_len = negative_prompt_embeds.shape[1] - - negative_prompt_embeds = negative_prompt_embeds.to(dtype=prompt_embeds_dtype, device=device) - - negative_prompt_embeds = negative_prompt_embeds.repeat(1, num_images_per_prompt, 1) - negative_prompt_embeds = negative_prompt_embeds.view(batch_size * num_images_per_prompt, seq_len, -1) - - if self.text_encoder is not None: - if isinstance(self, StableDiffusionLoraLoaderMixin) and USE_PEFT_BACKEND: - # Retrieve the original scale by scaling back the LoRA layers - unscale_lora_layers(self.text_encoder, lora_scale) - - return prompt_embeds, negative_prompt_embeds - - # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.decode_latents - def decode_latents(self, latents): - deprecation_message = "The decode_latents method is deprecated and will be removed in 1.0.0. Please use VaeImageProcessor.postprocess(...) instead" - deprecate("decode_latents", "1.0.0", deprecation_message, standard_warn=False) - - latents = 1 / self.vae.config.scaling_factor * latents - image = self.vae.decode(latents, return_dict=False)[0] - image = (image / 2 + 0.5).clamp(0, 1) - # we always cast to float32 as this does not cause significant overhead and is compatible with bfloat16 - image = image.cpu().permute(0, 2, 3, 1).float().numpy() - return image - - # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_extra_step_kwargs with prepare_extra_step_kwargs->prepare_prior_extra_step_kwargs, scheduler->prior_scheduler + # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_utils.StableDiffusionMixin.prepare_extra_step_kwargs with prepare_extra_step_kwargs->prepare_prior_extra_step_kwargs, scheduler->prior_scheduler def prepare_prior_extra_step_kwargs(self, generator, eta): # prepare extra kwargs for the prior_scheduler step, since not all prior_schedulers have the same signature # eta (η) is only used with the DDIMScheduler, it will be ignored for other prior_schedulers. @@ -506,24 +274,6 @@ class StableUnCLIPPipeline( extra_step_kwargs["generator"] = generator return extra_step_kwargs - # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_extra_step_kwargs - def prepare_extra_step_kwargs(self, generator, eta): - # prepare extra kwargs for the scheduler step, since not all schedulers have the same signature - # eta (η) is only used with the DDIMScheduler, it will be ignored for other schedulers. - # eta corresponds to η in DDIM paper: https://huggingface.co/papers/2010.02502 - # and should be between [0, 1] - - accepts_eta = "eta" in set(inspect.signature(self.scheduler.step).parameters.keys()) - extra_step_kwargs = {} - if accepts_eta: - extra_step_kwargs["eta"] = eta - - # check if the scheduler accepts generator - accepts_generator = "generator" in set(inspect.signature(self.scheduler.step).parameters.keys()) - if accepts_generator: - extra_step_kwargs["generator"] = generator - return extra_step_kwargs - def check_inputs( self, prompt,