From 3be4b01cda20f3600007bd007f96fc6432ab0a7a Mon Sep 17 00:00:00 2001 From: sayakpaul Date: Thu, 4 Dec 2025 09:43:17 +0800 Subject: [PATCH] remove methods again --- .../pipeline_stable_diffusion_xl.py | 92 ------------------- .../pipeline_stable_diffusion_xl_utils.py | 19 ++-- 2 files changed, 6 insertions(+), 105 deletions(-) diff --git a/src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl.py b/src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl.py index 6e9245d697..2e52c9b06c 100644 --- a/src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl.py +++ b/src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl.py @@ -309,98 +309,6 @@ class StableDiffusionXLPipeline( latents = latents * self.scheduler.init_noise_sigma return latents - def _get_add_time_ids( - self, original_size, crops_coords_top_left, target_size, dtype, text_encoder_projection_dim=None - ): - add_time_ids = list(original_size + crops_coords_top_left + target_size) - - passed_add_embed_dim = ( - self.unet.config.addition_time_embed_dim * len(add_time_ids) + text_encoder_projection_dim - ) - expected_add_embed_dim = self.unet.add_embedding.linear_1.in_features - - if expected_add_embed_dim != passed_add_embed_dim: - raise ValueError( - f"Model expects an added time embedding vector of length {expected_add_embed_dim}, but a vector of {passed_add_embed_dim} was created. The model has an incorrect config. Please check `unet.config.time_embedding_type` and `text_encoder_2.config.projection_dim`." - ) - - add_time_ids = torch.tensor([add_time_ids], dtype=dtype) - return add_time_ids - - def upcast_vae(self): - deprecate( - "upcast_vae", - "1.0.0", - "`upcast_vae` is deprecated. Please use `pipe.vae.to(torch.float32)`. For more details, please refer to: https://github.com/huggingface/diffusers/pull/12619#issue-3606633695.", - ) - self.vae.to(dtype=torch.float32) - - # Copied from diffusers.pipelines.latent_consistency_models.pipeline_latent_consistency_text2img.LatentConsistencyModelPipeline.get_guidance_scale_embedding - def get_guidance_scale_embedding( - self, w: torch.Tensor, embedding_dim: int = 512, dtype: torch.dtype = torch.float32 - ) -> torch.Tensor: - """ - See https://github.com/google-research/vdm/blob/dc27b98a554f65cdc654b800da5aa1846545d41b/model_vdm.py#L298 - - Args: - w (`torch.Tensor`): - Generate embedding vectors with a specified guidance scale to subsequently enrich timestep embeddings. - embedding_dim (`int`, *optional*, defaults to 512): - Dimension of the embeddings to generate. - dtype (`torch.dtype`, *optional*, defaults to `torch.float32`): - Data type of the generated embeddings. - - Returns: - `torch.Tensor`: Embedding vectors with shape `(len(w), embedding_dim)`. - """ - assert len(w.shape) == 1 - w = w * 1000.0 - - half_dim = embedding_dim // 2 - emb = torch.log(torch.tensor(10000.0)) / (half_dim - 1) - emb = torch.exp(torch.arange(half_dim, dtype=dtype) * -emb) - emb = w.to(dtype)[:, None] * emb[None, :] - emb = torch.cat([torch.sin(emb), torch.cos(emb)], dim=1) - if embedding_dim % 2 == 1: # zero pad - emb = torch.nn.functional.pad(emb, (0, 1)) - assert emb.shape == (w.shape[0], embedding_dim) - return emb - - @property - def guidance_scale(self): - return self._guidance_scale - - @property - def guidance_rescale(self): - return self._guidance_rescale - - @property - def clip_skip(self): - return self._clip_skip - - # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2) - # of the Imagen paper: https://huggingface.co/papers/2205.11487 . `guidance_scale = 1` - # corresponds to doing no classifier free guidance. - @property - def do_classifier_free_guidance(self): - return self._guidance_scale > 1 and self.unet.config.time_cond_proj_dim is None - - @property - def cross_attention_kwargs(self): - return self._cross_attention_kwargs - - @property - def denoising_end(self): - return self._denoising_end - - @property - def num_timesteps(self): - return self._num_timesteps - - @property - def interrupt(self): - return self._interrupt - @torch.no_grad() @replace_example_docstring(EXAMPLE_DOC_STRING) def __call__( diff --git a/src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_utils.py b/src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_utils.py index c491b8d0bb..8412235325 100644 --- a/src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_utils.py +++ b/src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_utils.py @@ -19,9 +19,8 @@ import torch from ...loaders import StableDiffusionXLLoraLoaderMixin, TextualInversionLoaderMixin from ...models import ImageProjection -from ...models.attention_processor import AttnProcessor2_0, FusedAttnProcessor2_0, XFormersAttnProcessor from ...models.lora import adjust_lora_scale_text_encoder -from ...utils import USE_PEFT_BACKEND, logging, scale_lora_layers, unscale_lora_layers +from ...utils import USE_PEFT_BACKEND, deprecate, logging, scale_lora_layers, unscale_lora_layers logger = logging.get_logger(__name__) # pylint: disable=invalid-name @@ -393,18 +392,12 @@ class StableDiffusionXLMixin: return image_embeds, uncond_image_embeds def upcast_vae(self): - dtype = self.vae.dtype - self.vae.to(dtype=torch.float32) - use_torch_2_0_or_xformers = isinstance( - self.vae.decoder.mid_block.attentions[0].processor, - (AttnProcessor2_0, XFormersAttnProcessor, FusedAttnProcessor2_0), + deprecate( + "upcast_vae", + "1.0.0", + "`upcast_vae` is deprecated. Please use `pipe.vae.to(torch.float32)`. For more details, please refer to: https://github.com/huggingface/diffusers/pull/12619#issue-3606633695.", ) - # if xformers or torch_2_0 is used attention block does not need - # to be in float32 which can save lots of memory - if use_torch_2_0_or_xformers: - self.vae.post_quant_conv.to(dtype) - self.vae.decoder.conv_in.to(dtype) - self.vae.decoder.mid_block.to(dtype) + self.vae.to(dtype=torch.float32) # Copied from diffusers.pipelines.latent_consistency_models.pipeline_latent_consistency_text2img.LatentConsistencyModelPipeline.get_guidance_scale_embedding def get_guidance_scale_embedding(