File size: 21,851 Bytes
43b7e92 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 |
import inspect
from typing import Callable, List, Optional, Union
import PIL.Image
import torch
from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer, CLIPVisionModel
from ....models import AutoencoderKL, UNet2DConditionModel
from ....schedulers import KarrasDiffusionSchedulers
from ....utils import logging
from ...pipeline_utils import DiffusionPipeline
from .pipeline_versatile_diffusion_dual_guided import VersatileDiffusionDualGuidedPipeline
from .pipeline_versatile_diffusion_image_variation import VersatileDiffusionImageVariationPipeline
from .pipeline_versatile_diffusion_text_to_image import VersatileDiffusionTextToImagePipeline
logger = logging.get_logger(__name__) # pylint: disable=invalid-name
class VersatileDiffusionPipeline(DiffusionPipeline):
r"""
Pipeline for text-to-image generation using Stable Diffusion.
This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods
implemented for all pipelines (downloading, saving, running on a particular device, etc.).
Args:
vae ([`AutoencoderKL`]):
Variational Auto-Encoder (VAE) model to encode and decode images to and from latent representations.
text_encoder ([`~transformers.CLIPTextModel`]):
Frozen text-encoder ([clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14)).
tokenizer ([`~transformers.CLIPTokenizer`]):
A `CLIPTokenizer` to tokenize text.
unet ([`UNet2DConditionModel`]):
A `UNet2DConditionModel` 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 more details
about a model's potential harms.
feature_extractor ([`~transformers.CLIPImageProcessor`]):
A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
"""
tokenizer: CLIPTokenizer
image_feature_extractor: CLIPImageProcessor
text_encoder: CLIPTextModel
image_encoder: CLIPVisionModel
image_unet: UNet2DConditionModel
text_unet: UNet2DConditionModel
vae: AutoencoderKL
scheduler: KarrasDiffusionSchedulers
def __init__(
self,
tokenizer: CLIPTokenizer,
image_feature_extractor: CLIPImageProcessor,
text_encoder: CLIPTextModel,
image_encoder: CLIPVisionModel,
image_unet: UNet2DConditionModel,
text_unet: UNet2DConditionModel,
vae: AutoencoderKL,
scheduler: KarrasDiffusionSchedulers,
):
super().__init__()
self.register_modules(
tokenizer=tokenizer,
image_feature_extractor=image_feature_extractor,
text_encoder=text_encoder,
image_encoder=image_encoder,
image_unet=image_unet,
text_unet=text_unet,
vae=vae,
scheduler=scheduler,
)
self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
@torch.no_grad()
def image_variation(
self,
image: Union[torch.Tensor, PIL.Image.Image],
height: Optional[int] = None,
width: Optional[int] = None,
num_inference_steps: int = 50,
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,
output_type: Optional[str] = "pil",
return_dict: bool = True,
callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
callback_steps: int = 1,
):
r"""
The call function to the pipeline for generation.
Args:
image (`PIL.Image.Image`, `List[PIL.Image.Image]` or `torch.Tensor`):
The image prompt or prompts to guide the image generation.
height (`int`, *optional*, defaults to `self.image_unet.config.sample_size * self.vae_scale_factor`):
The height in pixels of the generated image.
width (`int`, *optional*, defaults to `self.image_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.
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`.
negative_prompt (`str` or `List[str]`, *optional*):
The prompt or prompts to guide what to not include in image generation. If not defined, you need to
pass `negative_prompt_embeds` instead. Ignored when not using guidance (`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`, *optional*):
A [`torch.Generator`](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 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.Tensor)`.
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.
Examples:
```py
>>> from diffusers import VersatileDiffusionPipeline
>>> import torch
>>> import requests
>>> from io import BytesIO
>>> from PIL import Image
>>> # let's download an initial image
>>> url = "https://huggingface.co/datasets/diffusers/images/resolve/main/benz.jpg"
>>> response = requests.get(url)
>>> image = Image.open(BytesIO(response.content)).convert("RGB")
>>> pipe = VersatileDiffusionPipeline.from_pretrained(
... "shi-labs/versatile-diffusion", torch_dtype=torch.float16
... )
>>> pipe = pipe.to("cuda")
>>> generator = torch.Generator(device="cuda").manual_seed(0)
>>> image = pipe.image_variation(image, generator=generator).images[0]
>>> image.save("./car_variation.png")
```
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.
"""
expected_components = inspect.signature(VersatileDiffusionImageVariationPipeline.__init__).parameters.keys()
components = {name: component for name, component in self.components.items() if name in expected_components}
return VersatileDiffusionImageVariationPipeline(**components)(
image=image,
height=height,
width=width,
num_inference_steps=num_inference_steps,
guidance_scale=guidance_scale,
negative_prompt=negative_prompt,
num_images_per_prompt=num_images_per_prompt,
eta=eta,
generator=generator,
latents=latents,
output_type=output_type,
return_dict=return_dict,
callback=callback,
callback_steps=callback_steps,
)
@torch.no_grad()
def text_to_image(
self,
prompt: Union[str, List[str]],
height: Optional[int] = None,
width: Optional[int] = None,
num_inference_steps: int = 50,
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,
output_type: Optional[str] = "pil",
return_dict: bool = True,
callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
callback_steps: int = 1,
):
r"""
The call function to the pipeline for generation.
Args:
prompt (`str` or `List[str]`):
The prompt or prompts to guide image generation.
height (`int`, *optional*, defaults to `self.image_unet.config.sample_size * self.vae_scale_factor`):
The height in pixels of the generated image.
width (`int`, *optional*, defaults to `self.image_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.
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`.
negative_prompt (`str` or `List[str]`, *optional*):
The prompt or prompts to guide what to not include in image generation. If not defined, you need to
pass `negative_prompt_embeds` instead. Ignored when not using guidance (`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`, *optional*):
A [`torch.Generator`](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 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.Tensor)`.
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.
Examples:
```py
>>> from diffusers import VersatileDiffusionPipeline
>>> import torch
>>> pipe = VersatileDiffusionPipeline.from_pretrained(
... "shi-labs/versatile-diffusion", torch_dtype=torch.float16
... )
>>> pipe = pipe.to("cuda")
>>> generator = torch.Generator(device="cuda").manual_seed(0)
>>> image = pipe.text_to_image("an astronaut riding on a horse on mars", generator=generator).images[0]
>>> image.save("./astronaut.png")
```
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.
"""
expected_components = inspect.signature(VersatileDiffusionTextToImagePipeline.__init__).parameters.keys()
components = {name: component for name, component in self.components.items() if name in expected_components}
temp_pipeline = VersatileDiffusionTextToImagePipeline(**components)
output = temp_pipeline(
prompt=prompt,
height=height,
width=width,
num_inference_steps=num_inference_steps,
guidance_scale=guidance_scale,
negative_prompt=negative_prompt,
num_images_per_prompt=num_images_per_prompt,
eta=eta,
generator=generator,
latents=latents,
output_type=output_type,
return_dict=return_dict,
callback=callback,
callback_steps=callback_steps,
)
# swap the attention blocks back to the original state
temp_pipeline._swap_unet_attention_blocks()
return output
@torch.no_grad()
def dual_guided(
self,
prompt: Union[PIL.Image.Image, List[PIL.Image.Image]],
image: Union[str, List[str]],
text_to_image_strength: float = 0.5,
height: Optional[int] = None,
width: Optional[int] = None,
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.Tensor] = None,
output_type: Optional[str] = "pil",
return_dict: bool = True,
callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
callback_steps: int = 1,
):
r"""
The call function to the pipeline for generation.
Args:
prompt (`str` or `List[str]`):
The prompt or prompts to guide image generation.
height (`int`, *optional*, defaults to `self.image_unet.config.sample_size * self.vae_scale_factor`):
The height in pixels of the generated image.
width (`int`, *optional*, defaults to `self.image_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.
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`.
negative_prompt (`str` or `List[str]`, *optional*):
The prompt or prompts to guide what to not include in image generation. If not defined, you need to
pass `negative_prompt_embeds` instead. Ignored when not using guidance (`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.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 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.Tensor)`.
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.
Examples:
```py
>>> from diffusers import VersatileDiffusionPipeline
>>> import torch
>>> import requests
>>> from io import BytesIO
>>> from PIL import Image
>>> # let's download an initial image
>>> url = "https://huggingface.co/datasets/diffusers/images/resolve/main/benz.jpg"
>>> response = requests.get(url)
>>> image = Image.open(BytesIO(response.content)).convert("RGB")
>>> text = "a red car in the sun"
>>> pipe = VersatileDiffusionPipeline.from_pretrained(
... "shi-labs/versatile-diffusion", torch_dtype=torch.float16
... )
>>> pipe = pipe.to("cuda")
>>> generator = torch.Generator(device="cuda").manual_seed(0)
>>> text_to_image_strength = 0.75
>>> image = pipe.dual_guided(
... prompt=text, image=image, text_to_image_strength=text_to_image_strength, generator=generator
... ).images[0]
>>> image.save("./car_variation.png")
```
Returns:
[`~pipelines.ImagePipelineOutput`] or `tuple`:
If `return_dict` is `True`, [`~pipelines.ImagePipelineOutput`] is returned, otherwise a `tuple` is
returned where the first element is a list with the generated images.
"""
expected_components = inspect.signature(VersatileDiffusionDualGuidedPipeline.__init__).parameters.keys()
components = {name: component for name, component in self.components.items() if name in expected_components}
temp_pipeline = VersatileDiffusionDualGuidedPipeline(**components)
output = temp_pipeline(
prompt=prompt,
image=image,
text_to_image_strength=text_to_image_strength,
height=height,
width=width,
num_inference_steps=num_inference_steps,
guidance_scale=guidance_scale,
num_images_per_prompt=num_images_per_prompt,
eta=eta,
generator=generator,
latents=latents,
output_type=output_type,
return_dict=return_dict,
callback=callback,
callback_steps=callback_steps,
)
temp_pipeline._revert_dual_attention()
return output
|