File size: 14,606 Bytes
37aeb5b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 |
# Copyright 2023 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.
# modified by Wuvin
from typing import Any, Callable, Dict, List, Optional, Tuple, Union
import numpy as np
import torch
from diffusers import AutoencoderKL, UNet2DConditionModel, StableDiffusionImageVariationPipeline
from diffusers.schedulers import KarrasDiffusionSchedulers
from diffusers.pipelines.stable_diffusion import StableDiffusionSafetyChecker, StableDiffusionPipelineOutput
from diffusers.models.unets.unet_2d_condition import UNet2DConditionModel
from PIL import Image
from transformers import CLIPImageProcessor, CLIPVisionModelWithProjection
class StableDiffusionImageCustomPipeline(
StableDiffusionImageVariationPipeline
):
def __init__(
self,
vae: AutoencoderKL,
image_encoder: CLIPVisionModelWithProjection,
unet: UNet2DConditionModel,
scheduler: KarrasDiffusionSchedulers,
safety_checker: StableDiffusionSafetyChecker,
feature_extractor: CLIPImageProcessor,
requires_safety_checker: bool = True,
latents_offset=None,
noisy_cond_latents=False,
):
super().__init__(
vae=vae,
image_encoder=image_encoder,
unet=unet,
scheduler=scheduler,
safety_checker=safety_checker,
feature_extractor=feature_extractor,
requires_safety_checker=requires_safety_checker
)
latents_offset = tuple(latents_offset) if latents_offset is not None else None
self.latents_offset = latents_offset
if latents_offset is not None:
self.register_to_config(latents_offset=latents_offset)
self.noisy_cond_latents = noisy_cond_latents
self.register_to_config(noisy_cond_latents=noisy_cond_latents)
def encode_latents(self, image, device, dtype, height, width):
# support batchsize > 1
if isinstance(image, Image.Image):
image = [image]
image = [img.convert("RGB") for img in image]
images = self.image_processor.preprocess(image, height=height, width=width).to(device, dtype=dtype)
latents = self.vae.encode(images).latent_dist.mode() * self.vae.config.scaling_factor
if self.latents_offset is not None:
return latents - torch.tensor(self.latents_offset).to(latents.device)[None, :, None, None]
else:
return latents
def _encode_image(self, image, device, num_images_per_prompt, do_classifier_free_guidance):
dtype = next(self.image_encoder.parameters()).dtype
if not isinstance(image, torch.Tensor):
image = self.feature_extractor(images=image, return_tensors="pt").pixel_values
image = image.to(device=device, dtype=dtype)
image_embeddings = self.image_encoder(image).image_embeds
image_embeddings = image_embeddings.unsqueeze(1)
# duplicate image embeddings for each generation per prompt, using mps friendly method
bs_embed, seq_len, _ = image_embeddings.shape
image_embeddings = image_embeddings.repeat(1, num_images_per_prompt, 1)
image_embeddings = image_embeddings.view(bs_embed * num_images_per_prompt, seq_len, -1)
if do_classifier_free_guidance:
# NOTE: the same as original code
negative_prompt_embeds = torch.zeros_like(image_embeddings)
# 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
image_embeddings = torch.cat([negative_prompt_embeds, image_embeddings])
return image_embeddings
@torch.no_grad()
def __call__(
self,
image: Union[Image.Image, List[Image.Image], torch.FloatTensor],
height: Optional[int] = 1024,
width: Optional[int] = 1024,
height_cond: Optional[int] = 512,
width_cond: Optional[int] = 512,
num_inference_steps: int = 50,
guidance_scale: float = 7.5,
num_images_per_prompt: Optional[int] = 1,
eta: float = 0.0,
generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
latents: Optional[torch.FloatTensor] = None,
output_type: Optional[str] = "pil",
return_dict: bool = True,
callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
callback_steps: int = 1,
upper_left_feature: bool = False,
):
r"""
The call function to the pipeline for generation.
Args:
image (`Image.Image` or `List[Image.Image]` or `torch.FloatTensor`):
Image or images to guide image generation. If you provide a tensor, it needs to be compatible with
[`CLIPImageProcessor`](https://huggingface.co/lambdalabs/sd-image-variations-diffusers/blob/main/feature_extractor/preprocessor_config.json).
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. This parameter is modulated by `strength`.
guidance_scale (`float`, *optional*, defaults to 7.5):
A higher guidance scale value encourages the model to generate images closely linked to the text
`prompt` at the expense of lower image quality. Guidance scale is enabled when `guidance_scale > 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) from the [DDIM](https://arxiv.org/abs/2010.02502) paper. Only applies
to the [`~schedulers.DDIMScheduler`], and is ignored in other schedulers.
generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
A [`torch.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make
generation deterministic.
latents (`torch.FloatTensor`, *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 is generated by sampling using the supplied random `generator`.
output_type (`str`, *optional*, defaults to `"pil"`):
The output format of the generated image. Choose between `PIL.Image` or `np.array`.
return_dict (`bool`, *optional*, defaults to `True`):
Whether or not to return a [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] instead of a
plain tuple.
callback (`Callable`, *optional*):
A function that calls every `callback_steps` steps during inference. The function is called with the
following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
callback_steps (`int`, *optional*, defaults to 1):
The frequency at which the `callback` function is called. If not specified, the callback is called at
every step.
Returns:
[`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] or `tuple`:
If `return_dict` is `True`, [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] is returned,
otherwise a `tuple` is returned where the first element is a list with the generated images and the
second element is a list of `bool`s indicating whether the corresponding generated image contains
"not-safe-for-work" (nsfw) content.
Examples:
```py
from diffusers import StableDiffusionImageVariationPipeline
from PIL import Image
from io import BytesIO
import requests
pipe = StableDiffusionImageVariationPipeline.from_pretrained(
"lambdalabs/sd-image-variations-diffusers", revision="v2.0"
)
pipe = pipe.to("cuda")
url = "https://lh3.googleusercontent.com/y-iFOHfLTwkuQSUegpwDdgKmOjRSTvPxat63dQLB25xkTs4lhIbRUFeNBWZzYf370g=s1200"
response = requests.get(url)
image = Image.open(BytesIO(response.content)).convert("RGB")
out = pipe(image, num_images_per_prompt=3, guidance_scale=15)
out["images"][0].save("result.jpg")
```
"""
# 0. Default height and width to unet
height = height or self.unet.config.sample_size * self.vae_scale_factor
width = width or self.unet.config.sample_size * self.vae_scale_factor
# 1. Check inputs. Raise error if not correct
self.check_inputs(image, height, width, callback_steps)
# 2. Define call parameters
if isinstance(image, Image.Image):
batch_size = 1
elif isinstance(image, list):
batch_size = len(image)
else:
batch_size = image.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 image
if isinstance(image, Image.Image) and upper_left_feature:
# only use the first one of four images
emb_image = image.crop((0, 0, image.size[0] // 2, image.size[1] // 2))
else:
emb_image = image
image_embeddings = self._encode_image(emb_image, device, num_images_per_prompt, do_classifier_free_guidance)
cond_latents = self.encode_latents(image, image_embeddings.device, image_embeddings.dtype, height_cond, width_cond)
# 4. Prepare timesteps
self.scheduler.set_timesteps(num_inference_steps, device=device)
timesteps = self.scheduler.timesteps
# 5. Prepare latent variables
num_channels_latents = self.unet.config.out_channels
latents = self.prepare_latents(
batch_size * num_images_per_prompt,
num_channels_latents,
height,
width,
image_embeddings.dtype,
device,
generator,
latents,
)
# 6. Prepare extra step kwargs.
extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)
# 7. Denoising loop
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):
if self.noisy_cond_latents:
raise ValueError("Noisy condition latents is not recommended.")
else:
noisy_cond_latents = cond_latents
noisy_cond_latents = torch.cat([torch.zeros_like(noisy_cond_latents), noisy_cond_latents]) if do_classifier_free_guidance else noisy_cond_latents
# expand the latents if we are doing classifier free guidance
latent_model_input = torch.cat([latents] * 2) if 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=image_embeddings, condition_latents=noisy_cond_latents).sample
# perform guidance
if 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)
self.maybe_free_model_hooks()
if self.latents_offset is not None:
latents = latents + torch.tensor(self.latents_offset).to(latents.device)[None, :, None, None]
if not output_type == "latent":
image = self.vae.decode(latents / self.vae.config.scaling_factor, return_dict=False)[0]
image, has_nsfw_concept = self.run_safety_checker(image, device, image_embeddings.dtype)
else:
image = latents
has_nsfw_concept = None
if has_nsfw_concept is None:
do_denormalize = [True] * image.shape[0]
else:
do_denormalize = [not has_nsfw for has_nsfw in has_nsfw_concept]
image = self.image_processor.postprocess(image, output_type=output_type, do_denormalize=do_denormalize)
self.maybe_free_model_hooks()
if not return_dict:
return (image, has_nsfw_concept)
return StableDiffusionPipelineOutput(images=image, nsfw_content_detected=has_nsfw_concept)
if __name__ == "__main__":
pass
|