diffusers-sdxl-controlnet
/
src
/diffusers
/pipelines
/t2i_adapter
/pipeline_stable_diffusion_adapter.py
# Copyright 2024 TencentARC and The HuggingFace Team. All rights reserved. | |
# | |
# Licensed under the Apache License, Version 2.0 (the "License"); | |
# you may not use this file except in compliance with the License. | |
# You may obtain a copy of the License at | |
# | |
# http://www.apache.org/licenses/LICENSE-2.0 | |
# | |
# Unless required by applicable law or agreed to in writing, software | |
# distributed under the License is distributed on an "AS IS" BASIS, | |
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | |
# See the License for the specific language governing permissions and | |
# limitations under the License. | |
import inspect | |
from dataclasses import dataclass | |
from typing import Any, Callable, Dict, List, Optional, Union | |
import numpy as np | |
import PIL.Image | |
import torch | |
from transformers import CLIPFeatureExtractor, CLIPTextModel, CLIPTokenizer | |
from ...image_processor import VaeImageProcessor | |
from ...loaders import LoraLoaderMixin, TextualInversionLoaderMixin | |
from ...models import AutoencoderKL, MultiAdapter, T2IAdapter, UNet2DConditionModel | |
from ...models.lora import adjust_lora_scale_text_encoder | |
from ...schedulers import KarrasDiffusionSchedulers | |
from ...utils import ( | |
PIL_INTERPOLATION, | |
USE_PEFT_BACKEND, | |
BaseOutput, | |
deprecate, | |
logging, | |
replace_example_docstring, | |
scale_lora_layers, | |
unscale_lora_layers, | |
) | |
from ...utils.torch_utils import randn_tensor | |
from ..pipeline_utils import DiffusionPipeline, StableDiffusionMixin | |
from ..stable_diffusion.safety_checker import StableDiffusionSafetyChecker | |
class StableDiffusionAdapterPipelineOutput(BaseOutput): | |
""" | |
Args: | |
images (`List[PIL.Image.Image]` or `np.ndarray`) | |
List of denoised PIL images of length `batch_size` or numpy array of shape `(batch_size, height, width, | |
num_channels)`. PIL images or numpy array present the denoised images of the diffusion pipeline. | |
nsfw_content_detected (`List[bool]`) | |
List of flags denoting whether the corresponding generated image likely represents "not-safe-for-work" | |
(nsfw) content, or `None` if safety checking could not be performed. | |
""" | |
images: Union[List[PIL.Image.Image], np.ndarray] | |
nsfw_content_detected: Optional[List[bool]] | |
logger = logging.get_logger(__name__) # pylint: disable=invalid-name | |
EXAMPLE_DOC_STRING = """ | |
Examples: | |
```py | |
>>> from PIL import Image | |
>>> from diffusers.utils import load_image | |
>>> import torch | |
>>> from diffusers import StableDiffusionAdapterPipeline, T2IAdapter | |
>>> image = load_image( | |
... "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/color_ref.png" | |
... ) | |
>>> color_palette = image.resize((8, 8)) | |
>>> color_palette = color_palette.resize((512, 512), resample=Image.Resampling.NEAREST) | |
>>> adapter = T2IAdapter.from_pretrained("TencentARC/t2iadapter_color_sd14v1", torch_dtype=torch.float16) | |
>>> pipe = StableDiffusionAdapterPipeline.from_pretrained( | |
... "CompVis/stable-diffusion-v1-4", | |
... adapter=adapter, | |
... torch_dtype=torch.float16, | |
... ) | |
>>> pipe.to("cuda") | |
>>> out_image = pipe( | |
... "At night, glowing cubes in front of the beach", | |
... image=color_palette, | |
... ).images[0] | |
``` | |
""" | |
def _preprocess_adapter_image(image, height, width): | |
if isinstance(image, torch.Tensor): | |
return image | |
elif isinstance(image, PIL.Image.Image): | |
image = [image] | |
if isinstance(image[0], PIL.Image.Image): | |
image = [np.array(i.resize((width, height), resample=PIL_INTERPOLATION["lanczos"])) for i in image] | |
image = [ | |
i[None, ..., None] if i.ndim == 2 else i[None, ...] for i in image | |
] # expand [h, w] or [h, w, c] to [b, h, w, c] | |
image = np.concatenate(image, axis=0) | |
image = np.array(image).astype(np.float32) / 255.0 | |
image = image.transpose(0, 3, 1, 2) | |
image = torch.from_numpy(image) | |
elif isinstance(image[0], torch.Tensor): | |
if image[0].ndim == 3: | |
image = torch.stack(image, dim=0) | |
elif image[0].ndim == 4: | |
image = torch.cat(image, dim=0) | |
else: | |
raise ValueError( | |
f"Invalid image tensor! Expecting image tensor with 3 or 4 dimension, but recive: {image[0].ndim}" | |
) | |
return image | |
# Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.retrieve_timesteps | |
def retrieve_timesteps( | |
scheduler, | |
num_inference_steps: Optional[int] = None, | |
device: Optional[Union[str, torch.device]] = None, | |
timesteps: Optional[List[int]] = None, | |
sigmas: Optional[List[float]] = None, | |
**kwargs, | |
): | |
""" | |
Calls the scheduler's `set_timesteps` method and retrieves timesteps from the scheduler after the call. Handles | |
custom timesteps. Any kwargs will be supplied to `scheduler.set_timesteps`. | |
Args: | |
scheduler (`SchedulerMixin`): | |
The scheduler to get timesteps from. | |
num_inference_steps (`int`): | |
The number of diffusion steps used when generating samples with a pre-trained model. If used, `timesteps` | |
must be `None`. | |
device (`str` or `torch.device`, *optional*): | |
The device to which the timesteps should be moved to. If `None`, the timesteps are not moved. | |
timesteps (`List[int]`, *optional*): | |
Custom timesteps used to override the timestep spacing strategy of the scheduler. If `timesteps` is passed, | |
`num_inference_steps` and `sigmas` must be `None`. | |
sigmas (`List[float]`, *optional*): | |
Custom sigmas used to override the timestep spacing strategy of the scheduler. If `sigmas` is passed, | |
`num_inference_steps` and `timesteps` must be `None`. | |
Returns: | |
`Tuple[torch.Tensor, int]`: A tuple where the first element is the timestep schedule from the scheduler and the | |
second element is the number of inference steps. | |
""" | |
if timesteps is not None and sigmas is not None: | |
raise ValueError("Only one of `timesteps` or `sigmas` can be passed. Please choose one to set custom values") | |
if timesteps is not None: | |
accepts_timesteps = "timesteps" in set(inspect.signature(scheduler.set_timesteps).parameters.keys()) | |
if not accepts_timesteps: | |
raise ValueError( | |
f"The current scheduler class {scheduler.__class__}'s `set_timesteps` does not support custom" | |
f" timestep schedules. Please check whether you are using the correct scheduler." | |
) | |
scheduler.set_timesteps(timesteps=timesteps, device=device, **kwargs) | |
timesteps = scheduler.timesteps | |
num_inference_steps = len(timesteps) | |
elif sigmas is not None: | |
accept_sigmas = "sigmas" in set(inspect.signature(scheduler.set_timesteps).parameters.keys()) | |
if not accept_sigmas: | |
raise ValueError( | |
f"The current scheduler class {scheduler.__class__}'s `set_timesteps` does not support custom" | |
f" sigmas schedules. Please check whether you are using the correct scheduler." | |
) | |
scheduler.set_timesteps(sigmas=sigmas, device=device, **kwargs) | |
timesteps = scheduler.timesteps | |
num_inference_steps = len(timesteps) | |
else: | |
scheduler.set_timesteps(num_inference_steps, device=device, **kwargs) | |
timesteps = scheduler.timesteps | |
return timesteps, num_inference_steps | |
class StableDiffusionAdapterPipeline(DiffusionPipeline, StableDiffusionMixin): | |
r""" | |
Pipeline for text-to-image generation using Stable Diffusion augmented with T2I-Adapter | |
https://arxiv.org/abs/2302.08453 | |
This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods the | |
library implements for all the pipelines (such as downloading or saving, running on a particular device, etc.) | |
Args: | |
adapter ([`T2IAdapter`] or [`MultiAdapter`] or `List[T2IAdapter]`): | |
Provides additional conditioning to the unet during the denoising process. If you set multiple Adapter as a | |
list, the outputs from each Adapter are added together to create one combined additional conditioning. | |
adapter_weights (`List[float]`, *optional*, defaults to None): | |
List of floats representing the weight which will be multiply to each adapter's output before adding them | |
together. | |
vae ([`AutoencoderKL`]): | |
Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations. | |
text_encoder ([`CLIPTextModel`]): | |
Frozen text-encoder. Stable Diffusion uses the text portion of | |
[CLIP](https://huggingface.co/docs/transformers/model_doc/clip#transformers.CLIPTextModel), specifically | |
the [clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14) variant. | |
tokenizer (`CLIPTokenizer`): | |
Tokenizer of class | |
[CLIPTokenizer](https://huggingface.co/docs/transformers/v4.21.0/en/model_doc/clip#transformers.CLIPTokenizer). | |
unet ([`UNet2DConditionModel`]): Conditional U-Net architecture to denoise the encoded image latents. | |
scheduler ([`SchedulerMixin`]): | |
A scheduler to be used in combination with `unet` to denoise the encoded image latents. Can be one of | |
[`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`]. | |
safety_checker ([`StableDiffusionSafetyChecker`]): | |
Classification module that estimates whether generated images could be considered offensive or harmful. | |
Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details. | |
feature_extractor ([`CLIPFeatureExtractor`]): | |
Model that extracts features from generated images to be used as inputs for the `safety_checker`. | |
""" | |
model_cpu_offload_seq = "text_encoder->adapter->unet->vae" | |
_optional_components = ["safety_checker", "feature_extractor"] | |
def __init__( | |
self, | |
vae: AutoencoderKL, | |
text_encoder: CLIPTextModel, | |
tokenizer: CLIPTokenizer, | |
unet: UNet2DConditionModel, | |
adapter: Union[T2IAdapter, MultiAdapter, List[T2IAdapter]], | |
scheduler: KarrasDiffusionSchedulers, | |
safety_checker: StableDiffusionSafetyChecker, | |
feature_extractor: CLIPFeatureExtractor, | |
requires_safety_checker: bool = True, | |
): | |
super().__init__() | |
if safety_checker is None and requires_safety_checker: | |
logger.warning( | |
f"You have disabled the safety checker for {self.__class__} by passing `safety_checker=None`. Ensure" | |
" that you abide to the conditions of the Stable Diffusion license and do not expose unfiltered" | |
" results in services or applications open to the public. Both the diffusers team and Hugging Face" | |
" strongly recommend to keep the safety filter enabled in all public facing circumstances, disabling" | |
" it only for use-cases that involve analyzing network behavior or auditing its results. For more" | |
" information, please have a look at https://github.com/huggingface/diffusers/pull/254 ." | |
) | |
if safety_checker is not None and feature_extractor is None: | |
raise ValueError( | |
"Make sure to define a feature extractor when loading {self.__class__} if you want to use the safety" | |
" checker. If you do not want to use the safety checker, you can pass `'safety_checker=None'` instead." | |
) | |
if isinstance(adapter, (list, tuple)): | |
adapter = MultiAdapter(adapter) | |
self.register_modules( | |
vae=vae, | |
text_encoder=text_encoder, | |
tokenizer=tokenizer, | |
unet=unet, | |
adapter=adapter, | |
scheduler=scheduler, | |
safety_checker=safety_checker, | |
feature_extractor=feature_extractor, | |
) | |
self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1) | |
self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor) | |
self.register_to_config(requires_safety_checker=requires_safety_checker) | |
# 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, LoraLoaderMixin): | |
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, LoraLoaderMixin) 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.run_safety_checker | |
def run_safety_checker(self, image, device, dtype): | |
if self.safety_checker is None: | |
has_nsfw_concept = None | |
else: | |
if torch.is_tensor(image): | |
feature_extractor_input = self.image_processor.postprocess(image, output_type="pil") | |
else: | |
feature_extractor_input = self.image_processor.numpy_to_pil(image) | |
safety_checker_input = self.feature_extractor(feature_extractor_input, return_tensors="pt").to(device) | |
image, has_nsfw_concept = self.safety_checker( | |
images=image, clip_input=safety_checker_input.pixel_values.to(dtype) | |
) | |
return image, has_nsfw_concept | |
# 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 | |
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://arxiv.org/abs/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, | |
height, | |
width, | |
callback_steps, | |
image, | |
negative_prompt=None, | |
prompt_embeds=None, | |
negative_prompt_embeds=None, | |
): | |
if height % 8 != 0 or width % 8 != 0: | |
raise ValueError(f"`height` and `width` have to be divisible by 8 but are {height} and {width}.") | |
if (callback_steps is None) or ( | |
callback_steps is not None and (not isinstance(callback_steps, int) or callback_steps <= 0) | |
): | |
raise ValueError( | |
f"`callback_steps` has to be a positive integer but is {callback_steps} of type" | |
f" {type(callback_steps)}." | |
) | |
if prompt is not None and prompt_embeds is not None: | |
raise ValueError( | |
f"Cannot forward both `prompt`: {prompt} and `prompt_embeds`: {prompt_embeds}. Please make sure to" | |
" only forward one of the two." | |
) | |
elif prompt is None and prompt_embeds is None: | |
raise ValueError( | |
"Provide either `prompt` or `prompt_embeds`. Cannot leave both `prompt` and `prompt_embeds` undefined." | |
) | |
elif prompt is not None and (not isinstance(prompt, str) and not isinstance(prompt, list)): | |
raise ValueError(f"`prompt` has to be of type `str` or `list` but is {type(prompt)}") | |
if negative_prompt is not None and negative_prompt_embeds is not None: | |
raise ValueError( | |
f"Cannot forward both `negative_prompt`: {negative_prompt} and `negative_prompt_embeds`:" | |
f" {negative_prompt_embeds}. Please make sure to only forward one of the two." | |
) | |
if prompt_embeds is not None and negative_prompt_embeds is not None: | |
if prompt_embeds.shape != negative_prompt_embeds.shape: | |
raise ValueError( | |
"`prompt_embeds` and `negative_prompt_embeds` must have the same shape when passed directly, but" | |
f" got: `prompt_embeds` {prompt_embeds.shape} != `negative_prompt_embeds`" | |
f" {negative_prompt_embeds.shape}." | |
) | |
if isinstance(self.adapter, MultiAdapter): | |
if not isinstance(image, list): | |
raise ValueError( | |
"MultiAdapter is enabled, but `image` is not a list. Please pass a list of images to `image`." | |
) | |
if len(image) != len(self.adapter.adapters): | |
raise ValueError( | |
f"MultiAdapter requires passing the same number of images as adapters. Given {len(image)} images and {len(self.adapter.adapters)} adapters." | |
) | |
# Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_latents | |
def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None): | |
shape = ( | |
batch_size, | |
num_channels_latents, | |
int(height) // self.vae_scale_factor, | |
int(width) // self.vae_scale_factor, | |
) | |
if isinstance(generator, list) and len(generator) != batch_size: | |
raise ValueError( | |
f"You have passed a list of generators of length {len(generator)}, but requested an effective batch" | |
f" size of {batch_size}. Make sure the batch size matches the length of the generators." | |
) | |
if latents is None: | |
latents = randn_tensor(shape, generator=generator, device=device, dtype=dtype) | |
else: | |
latents = latents.to(device) | |
# scale the initial noise by the standard deviation required by the scheduler | |
latents = latents * self.scheduler.init_noise_sigma | |
return latents | |
def _default_height_width(self, height, width, image): | |
# NOTE: It is possible that a list of images have different | |
# dimensions for each image, so just checking the first image | |
# is not _exactly_ correct, but it is simple. | |
while isinstance(image, list): | |
image = image[0] | |
if height is None: | |
if isinstance(image, PIL.Image.Image): | |
height = image.height | |
elif isinstance(image, torch.Tensor): | |
height = image.shape[-2] | |
# round down to nearest multiple of `self.adapter.downscale_factor` | |
height = (height // self.adapter.downscale_factor) * self.adapter.downscale_factor | |
if width is None: | |
if isinstance(image, PIL.Image.Image): | |
width = image.width | |
elif isinstance(image, torch.Tensor): | |
width = image.shape[-1] | |
# round down to nearest multiple of `self.adapter.downscale_factor` | |
width = (width // self.adapter.downscale_factor) * self.adapter.downscale_factor | |
return height, width | |
# 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 | |
def guidance_scale(self): | |
return self._guidance_scale | |
# 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. | |
def do_classifier_free_guidance(self): | |
return self._guidance_scale > 1 and self.unet.config.time_cond_proj_dim is None | |
def __call__( | |
self, | |
prompt: Union[str, List[str]] = None, | |
image: Union[torch.Tensor, PIL.Image.Image, List[PIL.Image.Image]] = None, | |
height: Optional[int] = None, | |
width: Optional[int] = None, | |
num_inference_steps: int = 50, | |
timesteps: List[int] = None, | |
sigmas: List[float] = None, | |
guidance_scale: float = 7.5, | |
negative_prompt: Optional[Union[str, List[str]]] = None, | |
num_images_per_prompt: Optional[int] = 1, | |
eta: float = 0.0, | |
generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None, | |
latents: Optional[torch.Tensor] = None, | |
prompt_embeds: Optional[torch.Tensor] = None, | |
negative_prompt_embeds: Optional[torch.Tensor] = None, | |
output_type: Optional[str] = "pil", | |
return_dict: bool = True, | |
callback: Optional[Callable[[int, int, torch.Tensor], None]] = None, | |
callback_steps: int = 1, | |
cross_attention_kwargs: Optional[Dict[str, Any]] = None, | |
adapter_conditioning_scale: Union[float, List[float]] = 1.0, | |
clip_skip: Optional[int] = None, | |
): | |
r""" | |
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. | |
image (`torch.Tensor`, `PIL.Image.Image`, `List[torch.Tensor]` or `List[PIL.Image.Image]` or `List[List[PIL.Image.Image]]`): | |
The Adapter input condition. Adapter uses this input condition to generate guidance to Unet. If the | |
type is specified as `torch.Tensor`, it is passed to Adapter as is. PIL.Image.Image` can also be | |
accepted as an image. The control image is automatically resized to fit the output image. | |
height (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor): | |
The height in pixels of the generated image. | |
width (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor): | |
The width in pixels of the generated image. | |
num_inference_steps (`int`, *optional*, defaults to 50): | |
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 7.5): | |
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. | |
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. 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_images_per_prompt (`int`, *optional*, defaults to 1): | |
The number of images to generate per prompt. | |
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. | |
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. | |
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.StableDiffusionAdapterPipelineOutput`] instead | |
of a plain tuple. | |
callback (`Callable`, *optional*): | |
A function that will be called every `callback_steps` steps during inference. The function will be | |
called with the following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`. | |
callback_steps (`int`, *optional*, defaults to 1): | |
The frequency at which the `callback` function will be called. If not specified, the callback will be | |
called at every step. | |
cross_attention_kwargs (`dict`, *optional*): | |
A kwargs dictionary that if specified is passed along to the `AttnProcessor` as defined under | |
`self.processor` in | |
[diffusers.models.attention_processor](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py). | |
adapter_conditioning_scale (`float` or `List[float]`, *optional*, defaults to 1.0): | |
The outputs of the adapter are multiplied by `adapter_conditioning_scale` before they are added to the | |
residual in the original unet. If multiple adapters are specified in init, you can set the | |
corresponding scale as a list. | |
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. | |
Examples: | |
Returns: | |
[`~pipelines.stable_diffusion.StableDiffusionAdapterPipelineOutput`] or `tuple`: | |
[`~pipelines.stable_diffusion.StableDiffusionAdapterPipelineOutput`] if `return_dict` is True, otherwise a | |
`tuple. When returning a tuple, the first element is a list with the generated images, and the second | |
element is a list of `bool`s denoting whether the corresponding generated image likely represents | |
"not-safe-for-work" (nsfw) content, according to the `safety_checker`. | |
""" | |
# 0. Default height and width to unet | |
height, width = self._default_height_width(height, width, image) | |
device = self._execution_device | |
# 1. Check inputs. Raise error if not correct | |
self.check_inputs( | |
prompt, height, width, callback_steps, image, negative_prompt, prompt_embeds, negative_prompt_embeds | |
) | |
self._guidance_scale = guidance_scale | |
if isinstance(self.adapter, MultiAdapter): | |
adapter_input = [] | |
for one_image in image: | |
one_image = _preprocess_adapter_image(one_image, height, width) | |
one_image = one_image.to(device=device, dtype=self.adapter.dtype) | |
adapter_input.append(one_image) | |
else: | |
adapter_input = _preprocess_adapter_image(image, height, width) | |
adapter_input = adapter_input.to(device=device, dtype=self.adapter.dtype) | |
# 2. Define 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] | |
# 3. Encode input prompt | |
prompt_embeds, negative_prompt_embeds = self.encode_prompt( | |
prompt, | |
device, | |
num_images_per_prompt, | |
self.do_classifier_free_guidance, | |
negative_prompt, | |
prompt_embeds=prompt_embeds, | |
negative_prompt_embeds=negative_prompt_embeds, | |
clip_skip=clip_skip, | |
) | |
# For classifier free guidance, we need to do two forward passes. | |
# Here we concatenate the unconditional and text embeddings into a single batch | |
# to avoid doing two forward passes | |
if self.do_classifier_free_guidance: | |
prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds]) | |
# 4. Prepare timesteps | |
timesteps, num_inference_steps = retrieve_timesteps( | |
self.scheduler, num_inference_steps, device, timesteps, sigmas | |
) | |
# 5. Prepare latent variables | |
num_channels_latents = self.unet.config.in_channels | |
latents = self.prepare_latents( | |
batch_size * num_images_per_prompt, | |
num_channels_latents, | |
height, | |
width, | |
prompt_embeds.dtype, | |
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) | |
# 6.5 Optionally get Guidance Scale Embedding | |
timestep_cond = None | |
if self.unet.config.time_cond_proj_dim is not None: | |
guidance_scale_tensor = torch.tensor(self.guidance_scale - 1).repeat(batch_size * num_images_per_prompt) | |
timestep_cond = self.get_guidance_scale_embedding( | |
guidance_scale_tensor, embedding_dim=self.unet.config.time_cond_proj_dim | |
).to(device=device, dtype=latents.dtype) | |
# 7. Denoising loop | |
if isinstance(self.adapter, MultiAdapter): | |
adapter_state = self.adapter(adapter_input, adapter_conditioning_scale) | |
for k, v in enumerate(adapter_state): | |
adapter_state[k] = v | |
else: | |
adapter_state = self.adapter(adapter_input) | |
for k, v in enumerate(adapter_state): | |
adapter_state[k] = v * adapter_conditioning_scale | |
if num_images_per_prompt > 1: | |
for k, v in enumerate(adapter_state): | |
adapter_state[k] = v.repeat(num_images_per_prompt, 1, 1, 1) | |
if self.do_classifier_free_guidance: | |
for k, v in enumerate(adapter_state): | |
adapter_state[k] = torch.cat([v] * 2, dim=0) | |
num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order | |
with self.progress_bar(total=num_inference_steps) as progress_bar: | |
for i, t in enumerate(timesteps): | |
# expand the latents if we are doing classifier free guidance | |
latent_model_input = torch.cat([latents] * 2) if self.do_classifier_free_guidance else latents | |
latent_model_input = self.scheduler.scale_model_input(latent_model_input, t) | |
# predict the noise residual | |
noise_pred = self.unet( | |
latent_model_input, | |
t, | |
encoder_hidden_states=prompt_embeds, | |
timestep_cond=timestep_cond, | |
cross_attention_kwargs=cross_attention_kwargs, | |
down_intrablock_additional_residuals=[state.clone() for state in adapter_state], | |
return_dict=False, | |
)[0] | |
# 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) | |
# compute the previous noisy sample x_t -> x_t-1 | |
latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs).prev_sample | |
# 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 callback is not None and i % callback_steps == 0: | |
step_idx = i // getattr(self.scheduler, "order", 1) | |
callback(step_idx, t, latents) | |
if output_type == "latent": | |
image = latents | |
has_nsfw_concept = None | |
elif output_type == "pil": | |
# 8. Post-processing | |
image = self.decode_latents(latents) | |
# 9. Run safety checker | |
image, has_nsfw_concept = self.run_safety_checker(image, device, prompt_embeds.dtype) | |
# 10. Convert to PIL | |
image = self.numpy_to_pil(image) | |
else: | |
# 8. Post-processing | |
image = self.decode_latents(latents) | |
# 9. Run safety checker | |
image, has_nsfw_concept = self.run_safety_checker(image, device, prompt_embeds.dtype) | |
# Offload all models | |
self.maybe_free_model_hooks() | |
if not return_dict: | |
return (image, has_nsfw_concept) | |
return StableDiffusionAdapterPipelineOutput(images=image, nsfw_content_detected=has_nsfw_concept) | |