Hugging Face's logo

Diffusers documentation

DeepFloyd IF

You are viewing v0.19.3 version. A newer version v0.31.0 is available.
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

DeepFloyd IF

Overview

DeepFloyd IF is a novel state-of-the-art open-source text-to-image model with a high degree of photorealism and language understanding. The model is a modular composed of a frozen text encoder and three cascaded pixel diffusion modules:

  • Stage 1: a base model that generates 64x64 px image based on text prompt,
  • Stage 2: a 64x64 px => 256x256 px super-resolution model, and a
  • Stage 3: a 256x256 px => 1024x1024 px super-resolution model Stage 1 and Stage 2 utilize a frozen text encoder based on the T5 transformer to extract text embeddings, which are then fed into a UNet architecture enhanced with cross-attention and attention pooling. Stage 3 is Stability’s x4 Upscaling model. The result is a highly efficient model that outperforms current state-of-the-art models, achieving a zero-shot FID score of 6.66 on the COCO dataset. Our work underscores the potential of larger UNet architectures in the first stage of cascaded diffusion models and depicts a promising future for text-to-image synthesis.

Usage

Before you can use IF, you need to accept its usage conditions. To do so:

  1. Make sure to have a Hugging Face account and be logged in
  2. Accept the license on the model card of DeepFloyd/IF-I-XL-v1.0. Accepting the license on the stage I model card will auto accept for the other IF models.
  3. Make sure to login locally. Install huggingface_hub
pip install huggingface_hub --upgrade

run the login function in a Python shell

from huggingface_hub import login

login()

and enter your Hugging Face Hub access token.

Next we install diffusers and dependencies:

pip install diffusers accelerate transformers safetensors

The following sections give more in-detail examples of how to use IF. Specifically:

Available checkpoints

Demo Hugging Face Spaces

Google Colab Open In Colab

Text-to-Image Generation

By default diffusers makes use of model cpu offloading to run the whole IF pipeline with as little as 14 GB of VRAM.

from diffusers import DiffusionPipeline
from diffusers.utils import pt_to_pil
import torch

# stage 1
stage_1 = DiffusionPipeline.from_pretrained("DeepFloyd/IF-I-XL-v1.0", variant="fp16", torch_dtype=torch.float16)
stage_1.enable_model_cpu_offload()

# stage 2
stage_2 = DiffusionPipeline.from_pretrained(
    "DeepFloyd/IF-II-L-v1.0", text_encoder=None, variant="fp16", torch_dtype=torch.float16
)
stage_2.enable_model_cpu_offload()

# stage 3
safety_modules = {
    "feature_extractor": stage_1.feature_extractor,
    "safety_checker": stage_1.safety_checker,
    "watermarker": stage_1.watermarker,
}
stage_3 = DiffusionPipeline.from_pretrained(
    "stabilityai/stable-diffusion-x4-upscaler", **safety_modules, torch_dtype=torch.float16
)
stage_3.enable_model_cpu_offload()

prompt = 'a photo of a kangaroo wearing an orange hoodie and blue sunglasses standing in front of the eiffel tower holding a sign that says "very deep learning"'
generator = torch.manual_seed(1)

# text embeds
prompt_embeds, negative_embeds = stage_1.encode_prompt(prompt)

# stage 1
image = stage_1(
    prompt_embeds=prompt_embeds, negative_prompt_embeds=negative_embeds, generator=generator, output_type="pt"
).images
pt_to_pil(image)[0].save("./if_stage_I.png")

# stage 2
image = stage_2(
    image=image,
    prompt_embeds=prompt_embeds,
    negative_prompt_embeds=negative_embeds,
    generator=generator,
    output_type="pt",
).images
pt_to_pil(image)[0].save("./if_stage_II.png")

# stage 3
image = stage_3(prompt=prompt, image=image, noise_level=100, generator=generator).images
image[0].save("./if_stage_III.png")

Text Guided Image-to-Image Generation

The same IF model weights can be used for text-guided image-to-image translation or image variation. In this case just make sure to load the weights using the IFInpaintingPipeline and IFInpaintingSuperResolutionPipeline pipelines.

Note: You can also directly move the weights of the text-to-image pipelines to the image-to-image pipelines without loading them twice by making use of the ~DiffusionPipeline.components() function as explained here.

from diffusers import IFImg2ImgPipeline, IFImg2ImgSuperResolutionPipeline, DiffusionPipeline
from diffusers.utils import pt_to_pil

import torch

from PIL import Image
import requests
from io import BytesIO

# download image
url = "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"
response = requests.get(url)
original_image = Image.open(BytesIO(response.content)).convert("RGB")
original_image = original_image.resize((768, 512))

# stage 1
stage_1 = IFImg2ImgPipeline.from_pretrained("DeepFloyd/IF-I-XL-v1.0", variant="fp16", torch_dtype=torch.float16)
stage_1.enable_model_cpu_offload()

# stage 2
stage_2 = IFImg2ImgSuperResolutionPipeline.from_pretrained(
    "DeepFloyd/IF-II-L-v1.0", text_encoder=None, variant="fp16", torch_dtype=torch.float16
)
stage_2.enable_model_cpu_offload()

# stage 3
safety_modules = {
    "feature_extractor": stage_1.feature_extractor,
    "safety_checker": stage_1.safety_checker,
    "watermarker": stage_1.watermarker,
}
stage_3 = DiffusionPipeline.from_pretrained(
    "stabilityai/stable-diffusion-x4-upscaler", **safety_modules, torch_dtype=torch.float16
)
stage_3.enable_model_cpu_offload()

prompt = "A fantasy landscape in style minecraft"
generator = torch.manual_seed(1)

# text embeds
prompt_embeds, negative_embeds = stage_1.encode_prompt(prompt)

# stage 1
image = stage_1(
    image=original_image,
    prompt_embeds=prompt_embeds,
    negative_prompt_embeds=negative_embeds,
    generator=generator,
    output_type="pt",
).images
pt_to_pil(image)[0].save("./if_stage_I.png")

# stage 2
image = stage_2(
    image=image,
    original_image=original_image,
    prompt_embeds=prompt_embeds,
    negative_prompt_embeds=negative_embeds,
    generator=generator,
    output_type="pt",
).images
pt_to_pil(image)[0].save("./if_stage_II.png")

# stage 3
image = stage_3(prompt=prompt, image=image, generator=generator, noise_level=100).images
image[0].save("./if_stage_III.png")

Text Guided Inpainting Generation

The same IF model weights can be used for text-guided image-to-image translation or image variation. In this case just make sure to load the weights using the IFInpaintingPipeline and IFInpaintingSuperResolutionPipeline pipelines.

Note: You can also directly move the weights of the text-to-image pipelines to the image-to-image pipelines without loading them twice by making use of the ~DiffusionPipeline.components() function as explained here.

from diffusers import IFInpaintingPipeline, IFInpaintingSuperResolutionPipeline, DiffusionPipeline
from diffusers.utils import pt_to_pil
import torch

from PIL import Image
import requests
from io import BytesIO

# download image
url = "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/if/person.png"
response = requests.get(url)
original_image = Image.open(BytesIO(response.content)).convert("RGB")
original_image = original_image

# download mask
url = "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/if/glasses_mask.png"
response = requests.get(url)
mask_image = Image.open(BytesIO(response.content))
mask_image = mask_image

# stage 1
stage_1 = IFInpaintingPipeline.from_pretrained("DeepFloyd/IF-I-XL-v1.0", variant="fp16", torch_dtype=torch.float16)
stage_1.enable_model_cpu_offload()

# stage 2
stage_2 = IFInpaintingSuperResolutionPipeline.from_pretrained(
    "DeepFloyd/IF-II-L-v1.0", text_encoder=None, variant="fp16", torch_dtype=torch.float16
)
stage_2.enable_model_cpu_offload()

# stage 3
safety_modules = {
    "feature_extractor": stage_1.feature_extractor,
    "safety_checker": stage_1.safety_checker,
    "watermarker": stage_1.watermarker,
}
stage_3 = DiffusionPipeline.from_pretrained(
    "stabilityai/stable-diffusion-x4-upscaler", **safety_modules, torch_dtype=torch.float16
)
stage_3.enable_model_cpu_offload()

prompt = "blue sunglasses"
generator = torch.manual_seed(1)

# text embeds
prompt_embeds, negative_embeds = stage_1.encode_prompt(prompt)

# stage 1
image = stage_1(
    image=original_image,
    mask_image=mask_image,
    prompt_embeds=prompt_embeds,
    negative_prompt_embeds=negative_embeds,
    generator=generator,
    output_type="pt",
).images
pt_to_pil(image)[0].save("./if_stage_I.png")

# stage 2
image = stage_2(
    image=image,
    original_image=original_image,
    mask_image=mask_image,
    prompt_embeds=prompt_embeds,
    negative_prompt_embeds=negative_embeds,
    generator=generator,
    output_type="pt",
).images
pt_to_pil(image)[0].save("./if_stage_II.png")

# stage 3
image = stage_3(prompt=prompt, image=image, generator=generator, noise_level=100).images
image[0].save("./if_stage_III.png")

Converting between different pipelines

In addition to being loaded with from_pretrained, Pipelines can also be loaded directly from each other.

from diffusers import IFPipeline, IFSuperResolutionPipeline

pipe_1 = IFPipeline.from_pretrained("DeepFloyd/IF-I-XL-v1.0")
pipe_2 = IFSuperResolutionPipeline.from_pretrained("DeepFloyd/IF-II-L-v1.0")


from diffusers import IFImg2ImgPipeline, IFImg2ImgSuperResolutionPipeline

pipe_1 = IFImg2ImgPipeline(**pipe_1.components)
pipe_2 = IFImg2ImgSuperResolutionPipeline(**pipe_2.components)


from diffusers import IFInpaintingPipeline, IFInpaintingSuperResolutionPipeline

pipe_1 = IFInpaintingPipeline(**pipe_1.components)
pipe_2 = IFInpaintingSuperResolutionPipeline(**pipe_2.components)

Optimizing for speed

The simplest optimization to run IF faster is to move all model components to the GPU.

pipe = DiffusionPipeline.from_pretrained("DeepFloyd/IF-I-XL-v1.0", variant="fp16", torch_dtype=torch.float16)
pipe.to("cuda")

You can also run the diffusion process for a shorter number of timesteps.

This can either be done with the num_inference_steps argument

pipe("<prompt>", num_inference_steps=30)

Or with the timesteps argument

from diffusers.pipelines.deepfloyd_if import fast27_timesteps

pipe("<prompt>", timesteps=fast27_timesteps)

When doing image variation or inpainting, you can also decrease the number of timesteps with the strength argument. The strength argument is the amount of noise to add to the input image which also determines how many steps to run in the denoising process. A smaller number will vary the image less but run faster.

pipe = IFImg2ImgPipeline.from_pretrained("DeepFloyd/IF-I-XL-v1.0", variant="fp16", torch_dtype=torch.float16)
pipe.to("cuda")

image = pipe(image=image, prompt="<prompt>", strength=0.3).images

You can also use torch.compile. Note that we have not exhaustively tested torch.compile with IF and it might not give expected results.

import torch

pipe = DiffusionPipeline.from_pretrained("DeepFloyd/IF-I-XL-v1.0", variant="fp16", torch_dtype=torch.float16)
pipe.to("cuda")

pipe.text_encoder = torch.compile(pipe.text_encoder)
pipe.unet = torch.compile(pipe.unet)

Optimizing for memory

When optimizing for GPU memory, we can use the standard diffusers cpu offloading APIs.

Either the model based CPU offloading,

pipe = DiffusionPipeline.from_pretrained("DeepFloyd/IF-I-XL-v1.0", variant="fp16", torch_dtype=torch.float16)
pipe.enable_model_cpu_offload()

or the more aggressive layer based CPU offloading.

pipe = DiffusionPipeline.from_pretrained("DeepFloyd/IF-I-XL-v1.0", variant="fp16", torch_dtype=torch.float16)
pipe.enable_sequential_cpu_offload()

Additionally, T5 can be loaded in 8bit precision

from transformers import T5EncoderModel

text_encoder = T5EncoderModel.from_pretrained(
    "DeepFloyd/IF-I-XL-v1.0", subfolder="text_encoder", device_map="auto", load_in_8bit=True, variant="8bit"
)

from diffusers import DiffusionPipeline

pipe = DiffusionPipeline.from_pretrained(
    "DeepFloyd/IF-I-XL-v1.0",
    text_encoder=text_encoder,  # pass the previously instantiated 8bit text encoder
    unet=None,
    device_map="auto",
)

prompt_embeds, negative_embeds = pipe.encode_prompt("<prompt>")

For CPU RAM constrained machines like google colab free tier where we can’t load all model components to the CPU at once, we can manually only load the pipeline with the text encoder or unet when the respective model components are needed.

from diffusers import IFPipeline, IFSuperResolutionPipeline
import torch
import gc
from transformers import T5EncoderModel
from diffusers.utils import pt_to_pil

text_encoder = T5EncoderModel.from_pretrained(
    "DeepFloyd/IF-I-XL-v1.0", subfolder="text_encoder", device_map="auto", load_in_8bit=True, variant="8bit"
)

# text to image

pipe = DiffusionPipeline.from_pretrained(
    "DeepFloyd/IF-I-XL-v1.0",
    text_encoder=text_encoder,  # pass the previously instantiated 8bit text encoder
    unet=None,
    device_map="auto",
)

prompt = 'a photo of a kangaroo wearing an orange hoodie and blue sunglasses standing in front of the eiffel tower holding a sign that says "very deep learning"'
prompt_embeds, negative_embeds = pipe.encode_prompt(prompt)

# Remove the pipeline so we can re-load the pipeline with the unet
del text_encoder
del pipe
gc.collect()
torch.cuda.empty_cache()

pipe = IFPipeline.from_pretrained(
    "DeepFloyd/IF-I-XL-v1.0", text_encoder=None, variant="fp16", torch_dtype=torch.float16, device_map="auto"
)

generator = torch.Generator().manual_seed(0)
image = pipe(
    prompt_embeds=prompt_embeds,
    negative_prompt_embeds=negative_embeds,
    output_type="pt",
    generator=generator,
).images

pt_to_pil(image)[0].save("./if_stage_I.png")

# Remove the pipeline so we can load the super-resolution pipeline
del pipe
gc.collect()
torch.cuda.empty_cache()

# First super resolution

pipe = IFSuperResolutionPipeline.from_pretrained(
    "DeepFloyd/IF-II-L-v1.0", text_encoder=None, variant="fp16", torch_dtype=torch.float16, device_map="auto"
)

generator = torch.Generator().manual_seed(0)
image = pipe(
    image=image,
    prompt_embeds=prompt_embeds,
    negative_prompt_embeds=negative_embeds,
    output_type="pt",
    generator=generator,
).images

pt_to_pil(image)[0].save("./if_stage_II.png")

Available Pipelines:

Pipeline Tasks Colab
pipeline_if.py Text-to-Image Generation -
pipeline_if_superresolution.py Text-to-Image Generation -
pipeline_if_img2img.py Image-to-Image Generation -
pipeline_if_img2img_superresolution.py Image-to-Image Generation -
pipeline_if_inpainting.py Image-to-Image Generation -
pipeline_if_inpainting_superresolution.py Image-to-Image Generation -

IFPipeline

class diffusers.IFPipeline

< >

( tokenizer: T5Tokenizer text_encoder: T5EncoderModel unet: UNet2DConditionModel scheduler: DDPMScheduler safety_checker: typing.Optional[diffusers.pipelines.deepfloyd_if.safety_checker.IFSafetyChecker] feature_extractor: typing.Optional[transformers.models.clip.image_processing_clip.CLIPImageProcessor] watermarker: typing.Optional[diffusers.pipelines.deepfloyd_if.watermark.IFWatermarker] requires_safety_checker: bool = True )

__call__

< >

( prompt: typing.Union[str, typing.List[str]] = None num_inference_steps: int = 100 timesteps: typing.List[int] = None guidance_scale: float = 7.0 negative_prompt: typing.Union[str, typing.List[str], NoneType] = None num_images_per_prompt: typing.Optional[int] = 1 height: typing.Optional[int] = None width: typing.Optional[int] = None eta: float = 0.0 generator: typing.Union[torch._C.Generator, typing.List[torch._C.Generator], NoneType] = None prompt_embeds: typing.Optional[torch.FloatTensor] = None negative_prompt_embeds: typing.Optional[torch.FloatTensor] = None output_type: typing.Optional[str] = 'pil' return_dict: bool = True callback: typing.Union[typing.Callable[[int, int, torch.FloatTensor], NoneType], NoneType] = None callback_steps: int = 1 clean_caption: bool = True cross_attention_kwargs: typing.Union[typing.Dict[str, typing.Any], NoneType] = None ) → ~pipelines.stable_diffusion.IFPipelineOutput or tuple

Parameters

  • 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.
  • 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. If not defined, equal spaced num_inference_steps timesteps are used. Must be in descending order.
  • guidance_scale (float, optional, defaults to 7.5) — Guidance scale as defined in Classifier-Free Diffusion Guidance. guidance_scale is defined as w of equation 2. of Imagen Paper. 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. 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.
  • height (int, optional, defaults to self.unet.config.sample_size) — The height in pixels of the generated image.
  • width (int, optional, defaults to self.unet.config.sample_size) — The width in pixels of the generated image.
  • 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) to make generation deterministic.
  • prompt_embeds (torch.FloatTensor, 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.FloatTensor, 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: PIL.Image.Image or np.array.
  • return_dict (bool, optional, defaults to True) — Whether or not to return a ~pipelines.stable_diffusion.IFPipelineOutput 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.FloatTensor).
  • 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.
  • clean_caption (bool, optional, defaults to True) — Whether or not to clean the caption before creating embeddings. Requires beautifulsoup4 and ftfy to be installed. If the dependencies are not installed, the embeddings will be created from the raw prompt.
  • cross_attention_kwargs (dict, optional) — A kwargs dictionary that if specified is passed along to the AttentionProcessor as defined under self.processor in diffusers.cross_attention.

Returns

~pipelines.stable_diffusion.IFPipelineOutput or tuple

~pipelines.stable_diffusion.IFPipelineOutput 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 bools denoting whether the corresponding generated image likely represents "not-safe-for-work" (nsfw) or watermarked content, according to the safety_checker`.

Function invoked when calling the pipeline for generation.

Examples:

>>> from diffusers import IFPipeline, IFSuperResolutionPipeline, DiffusionPipeline
>>> from diffusers.utils import pt_to_pil
>>> import torch

>>> pipe = IFPipeline.from_pretrained("DeepFloyd/IF-I-XL-v1.0", variant="fp16", torch_dtype=torch.float16)
>>> pipe.enable_model_cpu_offload()

>>> prompt = 'a photo of a kangaroo wearing an orange hoodie and blue sunglasses standing in front of the eiffel tower holding a sign that says "very deep learning"'
>>> prompt_embeds, negative_embeds = pipe.encode_prompt(prompt)

>>> image = pipe(prompt_embeds=prompt_embeds, negative_prompt_embeds=negative_embeds, output_type="pt").images

>>> # save intermediate image
>>> pil_image = pt_to_pil(image)
>>> pil_image[0].save("./if_stage_I.png")

>>> super_res_1_pipe = IFSuperResolutionPipeline.from_pretrained(
...     "DeepFloyd/IF-II-L-v1.0", text_encoder=None, variant="fp16", torch_dtype=torch.float16
... )
>>> super_res_1_pipe.enable_model_cpu_offload()

>>> image = super_res_1_pipe(
...     image=image, prompt_embeds=prompt_embeds, negative_prompt_embeds=negative_embeds, output_type="pt"
... ).images

>>> # save intermediate image
>>> pil_image = pt_to_pil(image)
>>> pil_image[0].save("./if_stage_I.png")

>>> safety_modules = {
...     "feature_extractor": pipe.feature_extractor,
...     "safety_checker": pipe.safety_checker,
...     "watermarker": pipe.watermarker,
... }
>>> super_res_2_pipe = DiffusionPipeline.from_pretrained(
...     "stabilityai/stable-diffusion-x4-upscaler", **safety_modules, torch_dtype=torch.float16
... )
>>> super_res_2_pipe.enable_model_cpu_offload()

>>> image = super_res_2_pipe(
...     prompt=prompt,
...     image=image,
... ).images
>>> image[0].save("./if_stage_II.png")

enable_model_cpu_offload

< >

( gpu_id = 0 )

Offloads all models to CPU using accelerate, reducing memory usage with a low impact on performance. Compared to enable_sequential_cpu_offload, this method moves one whole model at a time to the GPU when its forward method is called, and the model remains in GPU until the next model runs. Memory savings are lower than with enable_sequential_cpu_offload, but performance is much better due to the iterative execution of the unet.

encode_prompt

< >

( prompt do_classifier_free_guidance = True num_images_per_prompt = 1 device = None negative_prompt = None prompt_embeds: typing.Optional[torch.FloatTensor] = None negative_prompt_embeds: typing.Optional[torch.FloatTensor] = None clean_caption: bool = False )

Parameters

  • prompt (str or List[str], optional) — prompt to be encoded

Encodes the prompt into text encoder hidden states.

device: (torch.device, optional): torch device to place the resulting embeddings on num_images_per_prompt (int, optional, defaults to 1): number of images that should be generated per prompt do_classifier_free_guidance (bool, optional, defaults to True): 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. 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.FloatTensor, 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.FloatTensor, 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.

IFSuperResolutionPipeline

class diffusers.IFSuperResolutionPipeline

< >

( tokenizer: T5Tokenizer text_encoder: T5EncoderModel unet: UNet2DConditionModel scheduler: DDPMScheduler image_noising_scheduler: DDPMScheduler safety_checker: typing.Optional[diffusers.pipelines.deepfloyd_if.safety_checker.IFSafetyChecker] feature_extractor: typing.Optional[transformers.models.clip.image_processing_clip.CLIPImageProcessor] watermarker: typing.Optional[diffusers.pipelines.deepfloyd_if.watermark.IFWatermarker] requires_safety_checker: bool = True )

__call__

< >

( prompt: typing.Union[str, typing.List[str]] = None height: int = None width: int = None image: typing.Union[PIL.Image.Image, numpy.ndarray, torch.FloatTensor] = None num_inference_steps: int = 50 timesteps: typing.List[int] = None guidance_scale: float = 4.0 negative_prompt: typing.Union[str, typing.List[str], NoneType] = None num_images_per_prompt: typing.Optional[int] = 1 eta: float = 0.0 generator: typing.Union[torch._C.Generator, typing.List[torch._C.Generator], NoneType] = None prompt_embeds: typing.Optional[torch.FloatTensor] = None negative_prompt_embeds: typing.Optional[torch.FloatTensor] = None output_type: typing.Optional[str] = 'pil' return_dict: bool = True callback: typing.Union[typing.Callable[[int, int, torch.FloatTensor], NoneType], NoneType] = None callback_steps: int = 1 cross_attention_kwargs: typing.Union[typing.Dict[str, typing.Any], NoneType] = None noise_level: int = 250 clean_caption: bool = True ) → ~pipelines.stable_diffusion.IFPipelineOutput or tuple

Parameters

  • 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.
  • height (int, optional, defaults to self.unet.config.sample_size) — The height in pixels of the generated image.
  • width (int, optional, defaults to self.unet.config.sample_size) — The width in pixels of the generated image.
  • image (PIL.Image.Image, np.ndarray, torch.FloatTensor) — The image to be upscaled.
  • 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. If not defined, equal spaced num_inference_steps timesteps are used. Must be in descending order.
  • guidance_scale (float, optional, defaults to 7.5) — Guidance scale as defined in Classifier-Free Diffusion Guidance. guidance_scale is defined as w of equation 2. of Imagen Paper. 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. 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) to make generation deterministic.
  • prompt_embeds (torch.FloatTensor, 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.FloatTensor, 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: PIL.Image.Image or np.array.
  • return_dict (bool, optional, defaults to True) — Whether or not to return a ~pipelines.stable_diffusion.IFPipelineOutput 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.FloatTensor).
  • 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 AttentionProcessor as defined under self.processor in diffusers.cross_attention.
  • noise_level (int, optional, defaults to 250) — The amount of noise to add to the upscaled image. Must be in the range [0, 1000)
  • clean_caption (bool, optional, defaults to True) — Whether or not to clean the caption before creating embeddings. Requires beautifulsoup4 and ftfy to be installed. If the dependencies are not installed, the embeddings will be created from the raw prompt.

Returns

~pipelines.stable_diffusion.IFPipelineOutput or tuple

~pipelines.stable_diffusion.IFPipelineOutput 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 bools denoting whether the corresponding generated image likely represents "not-safe-for-work" (nsfw) or watermarked content, according to the safety_checker`.

Function invoked when calling the pipeline for generation.

Examples:

>>> from diffusers import IFPipeline, IFSuperResolutionPipeline, DiffusionPipeline
>>> from diffusers.utils import pt_to_pil
>>> import torch

>>> pipe = IFPipeline.from_pretrained("DeepFloyd/IF-I-XL-v1.0", variant="fp16", torch_dtype=torch.float16)
>>> pipe.enable_model_cpu_offload()

>>> prompt = 'a photo of a kangaroo wearing an orange hoodie and blue sunglasses standing in front of the eiffel tower holding a sign that says "very deep learning"'
>>> prompt_embeds, negative_embeds = pipe.encode_prompt(prompt)

>>> image = pipe(prompt_embeds=prompt_embeds, negative_prompt_embeds=negative_embeds, output_type="pt").images

>>> # save intermediate image
>>> pil_image = pt_to_pil(image)
>>> pil_image[0].save("./if_stage_I.png")

>>> super_res_1_pipe = IFSuperResolutionPipeline.from_pretrained(
...     "DeepFloyd/IF-II-L-v1.0", text_encoder=None, variant="fp16", torch_dtype=torch.float16
... )
>>> super_res_1_pipe.enable_model_cpu_offload()

>>> image = super_res_1_pipe(
...     image=image, prompt_embeds=prompt_embeds, negative_prompt_embeds=negative_embeds
... ).images
>>> image[0].save("./if_stage_II.png")

enable_model_cpu_offload

< >

( gpu_id = 0 )

Offloads all models to CPU using accelerate, reducing memory usage with a low impact on performance. Compared to enable_sequential_cpu_offload, this method moves one whole model at a time to the GPU when its forward method is called, and the model remains in GPU until the next model runs. Memory savings are lower than with enable_sequential_cpu_offload, but performance is much better due to the iterative execution of the unet.

encode_prompt

< >

( prompt do_classifier_free_guidance = True num_images_per_prompt = 1 device = None negative_prompt = None prompt_embeds: typing.Optional[torch.FloatTensor] = None negative_prompt_embeds: typing.Optional[torch.FloatTensor] = None clean_caption: bool = False )

Parameters

  • prompt (str or List[str], optional) — prompt to be encoded

Encodes the prompt into text encoder hidden states.

device: (torch.device, optional): torch device to place the resulting embeddings on num_images_per_prompt (int, optional, defaults to 1): number of images that should be generated per prompt do_classifier_free_guidance (bool, optional, defaults to True): 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. 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.FloatTensor, 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.FloatTensor, 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.

IFImg2ImgPipeline

class diffusers.IFImg2ImgPipeline

< >

( tokenizer: T5Tokenizer text_encoder: T5EncoderModel unet: UNet2DConditionModel scheduler: DDPMScheduler safety_checker: typing.Optional[diffusers.pipelines.deepfloyd_if.safety_checker.IFSafetyChecker] feature_extractor: typing.Optional[transformers.models.clip.image_processing_clip.CLIPImageProcessor] watermarker: typing.Optional[diffusers.pipelines.deepfloyd_if.watermark.IFWatermarker] requires_safety_checker: bool = True )

__call__

< >

( prompt: typing.Union[str, typing.List[str]] = None image: typing.Union[PIL.Image.Image, torch.Tensor, numpy.ndarray, typing.List[PIL.Image.Image], typing.List[torch.Tensor], typing.List[numpy.ndarray]] = None strength: float = 0.7 num_inference_steps: int = 80 timesteps: typing.List[int] = None guidance_scale: float = 10.0 negative_prompt: typing.Union[str, typing.List[str], NoneType] = None num_images_per_prompt: typing.Optional[int] = 1 eta: float = 0.0 generator: typing.Union[torch._C.Generator, typing.List[torch._C.Generator], NoneType] = None prompt_embeds: typing.Optional[torch.FloatTensor] = None negative_prompt_embeds: typing.Optional[torch.FloatTensor] = None output_type: typing.Optional[str] = 'pil' return_dict: bool = True callback: typing.Union[typing.Callable[[int, int, torch.FloatTensor], NoneType], NoneType] = None callback_steps: int = 1 clean_caption: bool = True cross_attention_kwargs: typing.Union[typing.Dict[str, typing.Any], NoneType] = None ) → ~pipelines.stable_diffusion.IFPipelineOutput or tuple

Parameters

  • 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.FloatTensor or PIL.Image.Image) — Image, or tensor representing an image batch, that will be used as the starting point for the process.
  • strength (float, optional, defaults to 0.8) — Conceptually, indicates how much to transform the reference image. Must be between 0 and 1. image will be used as a starting point, adding more noise to it the larger the strength. The number of denoising steps depends on the amount of noise initially added. When strength is 1, added noise will be maximum and the denoising process will run for the full number of iterations specified in num_inference_steps. A value of 1, therefore, essentially ignores 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. If not defined, equal spaced num_inference_steps timesteps are used. Must be in descending order.
  • guidance_scale (float, optional, defaults to 7.5) — Guidance scale as defined in Classifier-Free Diffusion Guidance. guidance_scale is defined as w of equation 2. of Imagen Paper. 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. 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) to make generation deterministic.
  • prompt_embeds (torch.FloatTensor, 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.FloatTensor, 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: PIL.Image.Image or np.array.
  • return_dict (bool, optional, defaults to True) — Whether or not to return a ~pipelines.stable_diffusion.IFPipelineOutput 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.FloatTensor).
  • 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.
  • clean_caption (bool, optional, defaults to True) — Whether or not to clean the caption before creating embeddings. Requires beautifulsoup4 and ftfy to be installed. If the dependencies are not installed, the embeddings will be created from the raw prompt.
  • cross_attention_kwargs (dict, optional) — A kwargs dictionary that if specified is passed along to the AttentionProcessor as defined under self.processor in diffusers.cross_attention.

Returns

~pipelines.stable_diffusion.IFPipelineOutput or tuple

~pipelines.stable_diffusion.IFPipelineOutput 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 bools denoting whether the corresponding generated image likely represents "not-safe-for-work" (nsfw) or watermarked content, according to the safety_checker`.

Function invoked when calling the pipeline for generation.

Examples:

>>> from diffusers import IFImg2ImgPipeline, IFImg2ImgSuperResolutionPipeline, DiffusionPipeline
>>> from diffusers.utils import pt_to_pil
>>> import torch
>>> from PIL import Image
>>> import requests
>>> from io import BytesIO

>>> url = "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"
>>> response = requests.get(url)
>>> original_image = Image.open(BytesIO(response.content)).convert("RGB")
>>> original_image = original_image.resize((768, 512))

>>> pipe = IFImg2ImgPipeline.from_pretrained(
...     "DeepFloyd/IF-I-XL-v1.0",
...     variant="fp16",
...     torch_dtype=torch.float16,
... )
>>> pipe.enable_model_cpu_offload()

>>> prompt = "A fantasy landscape in style minecraft"
>>> prompt_embeds, negative_embeds = pipe.encode_prompt(prompt)

>>> image = pipe(
...     image=original_image,
...     prompt_embeds=prompt_embeds,
...     negative_prompt_embeds=negative_embeds,
...     output_type="pt",
... ).images

>>> # save intermediate image
>>> pil_image = pt_to_pil(image)
>>> pil_image[0].save("./if_stage_I.png")

>>> super_res_1_pipe = IFImg2ImgSuperResolutionPipeline.from_pretrained(
...     "DeepFloyd/IF-II-L-v1.0",
...     text_encoder=None,
...     variant="fp16",
...     torch_dtype=torch.float16,
... )
>>> super_res_1_pipe.enable_model_cpu_offload()

>>> image = super_res_1_pipe(
...     image=image,
...     original_image=original_image,
...     prompt_embeds=prompt_embeds,
...     negative_prompt_embeds=negative_embeds,
... ).images
>>> image[0].save("./if_stage_II.png")

enable_model_cpu_offload

< >

( gpu_id = 0 )

Offloads all models to CPU using accelerate, reducing memory usage with a low impact on performance. Compared to enable_sequential_cpu_offload, this method moves one whole model at a time to the GPU when its forward method is called, and the model remains in GPU until the next model runs. Memory savings are lower than with enable_sequential_cpu_offload, but performance is much better due to the iterative execution of the unet.

encode_prompt

< >

( prompt do_classifier_free_guidance = True num_images_per_prompt = 1 device = None negative_prompt = None prompt_embeds: typing.Optional[torch.FloatTensor] = None negative_prompt_embeds: typing.Optional[torch.FloatTensor] = None clean_caption: bool = False )

Parameters

  • prompt (str or List[str], optional) — prompt to be encoded

Encodes the prompt into text encoder hidden states.

device: (torch.device, optional): torch device to place the resulting embeddings on num_images_per_prompt (int, optional, defaults to 1): number of images that should be generated per prompt do_classifier_free_guidance (bool, optional, defaults to True): 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. 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.FloatTensor, 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.FloatTensor, 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.

IFImg2ImgSuperResolutionPipeline

class diffusers.IFImg2ImgSuperResolutionPipeline

< >

( tokenizer: T5Tokenizer text_encoder: T5EncoderModel unet: UNet2DConditionModel scheduler: DDPMScheduler image_noising_scheduler: DDPMScheduler safety_checker: typing.Optional[diffusers.pipelines.deepfloyd_if.safety_checker.IFSafetyChecker] feature_extractor: typing.Optional[transformers.models.clip.image_processing_clip.CLIPImageProcessor] watermarker: typing.Optional[diffusers.pipelines.deepfloyd_if.watermark.IFWatermarker] requires_safety_checker: bool = True )

__call__

< >

( image: typing.Union[PIL.Image.Image, numpy.ndarray, torch.FloatTensor] original_image: typing.Union[PIL.Image.Image, torch.Tensor, numpy.ndarray, typing.List[PIL.Image.Image], typing.List[torch.Tensor], typing.List[numpy.ndarray]] = None strength: float = 0.8 prompt: typing.Union[str, typing.List[str]] = None num_inference_steps: int = 50 timesteps: typing.List[int] = None guidance_scale: float = 4.0 negative_prompt: typing.Union[str, typing.List[str], NoneType] = None num_images_per_prompt: typing.Optional[int] = 1 eta: float = 0.0 generator: typing.Union[torch._C.Generator, typing.List[torch._C.Generator], NoneType] = None prompt_embeds: typing.Optional[torch.FloatTensor] = None negative_prompt_embeds: typing.Optional[torch.FloatTensor] = None output_type: typing.Optional[str] = 'pil' return_dict: bool = True callback: typing.Union[typing.Callable[[int, int, torch.FloatTensor], NoneType], NoneType] = None callback_steps: int = 1 cross_attention_kwargs: typing.Union[typing.Dict[str, typing.Any], NoneType] = None noise_level: int = 250 clean_caption: bool = True ) → ~pipelines.stable_diffusion.IFPipelineOutput or tuple

Parameters

  • image (torch.FloatTensor or PIL.Image.Image) — Image, or tensor representing an image batch, that will be used as the starting point for the process.
  • original_image (torch.FloatTensor or PIL.Image.Image) — The original image that image was varied from.
  • strength (float, optional, defaults to 0.8) — Conceptually, indicates how much to transform the reference image. Must be between 0 and 1. image will be used as a starting point, adding more noise to it the larger the strength. The number of denoising steps depends on the amount of noise initially added. When strength is 1, added noise will be maximum and the denoising process will run for the full number of iterations specified in num_inference_steps. A value of 1, therefore, essentially ignores image.
  • 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.
  • 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. If not defined, equal spaced num_inference_steps timesteps are used. Must be in descending order.
  • guidance_scale (float, optional, defaults to 7.5) — Guidance scale as defined in Classifier-Free Diffusion Guidance. guidance_scale is defined as w of equation 2. of Imagen Paper. 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. 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) to make generation deterministic.
  • prompt_embeds (torch.FloatTensor, 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.FloatTensor, 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: PIL.Image.Image or np.array.
  • return_dict (bool, optional, defaults to True) — Whether or not to return a ~pipelines.stable_diffusion.IFPipelineOutput 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.FloatTensor).
  • 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 AttentionProcessor as defined under self.processor in diffusers.cross_attention.
  • noise_level (int, optional, defaults to 250) — The amount of noise to add to the upscaled image. Must be in the range [0, 1000)
  • clean_caption (bool, optional, defaults to True) — Whether or not to clean the caption before creating embeddings. Requires beautifulsoup4 and ftfy to be installed. If the dependencies are not installed, the embeddings will be created from the raw prompt.

Returns

~pipelines.stable_diffusion.IFPipelineOutput or tuple

~pipelines.stable_diffusion.IFPipelineOutput 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 bools denoting whether the corresponding generated image likely represents "not-safe-for-work" (nsfw) or watermarked content, according to the safety_checker`.

Function invoked when calling the pipeline for generation.

Examples:

>>> from diffusers import IFImg2ImgPipeline, IFImg2ImgSuperResolutionPipeline, DiffusionPipeline
>>> from diffusers.utils import pt_to_pil
>>> import torch
>>> from PIL import Image
>>> import requests
>>> from io import BytesIO

>>> url = "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"
>>> response = requests.get(url)
>>> original_image = Image.open(BytesIO(response.content)).convert("RGB")
>>> original_image = original_image.resize((768, 512))

>>> pipe = IFImg2ImgPipeline.from_pretrained(
...     "DeepFloyd/IF-I-XL-v1.0",
...     variant="fp16",
...     torch_dtype=torch.float16,
... )
>>> pipe.enable_model_cpu_offload()

>>> prompt = "A fantasy landscape in style minecraft"
>>> prompt_embeds, negative_embeds = pipe.encode_prompt(prompt)

>>> image = pipe(
...     image=original_image,
...     prompt_embeds=prompt_embeds,
...     negative_prompt_embeds=negative_embeds,
...     output_type="pt",
... ).images

>>> # save intermediate image
>>> pil_image = pt_to_pil(image)
>>> pil_image[0].save("./if_stage_I.png")

>>> super_res_1_pipe = IFImg2ImgSuperResolutionPipeline.from_pretrained(
...     "DeepFloyd/IF-II-L-v1.0",
...     text_encoder=None,
...     variant="fp16",
...     torch_dtype=torch.float16,
... )
>>> super_res_1_pipe.enable_model_cpu_offload()

>>> image = super_res_1_pipe(
...     image=image,
...     original_image=original_image,
...     prompt_embeds=prompt_embeds,
...     negative_prompt_embeds=negative_embeds,
... ).images
>>> image[0].save("./if_stage_II.png")

enable_model_cpu_offload

< >

( gpu_id = 0 )

Offloads all models to CPU using accelerate, reducing memory usage with a low impact on performance. Compared to enable_sequential_cpu_offload, this method moves one whole model at a time to the GPU when its forward method is called, and the model remains in GPU until the next model runs. Memory savings are lower than with enable_sequential_cpu_offload, but performance is much better due to the iterative execution of the unet.

encode_prompt

< >

( prompt do_classifier_free_guidance = True num_images_per_prompt = 1 device = None negative_prompt = None prompt_embeds: typing.Optional[torch.FloatTensor] = None negative_prompt_embeds: typing.Optional[torch.FloatTensor] = None clean_caption: bool = False )

Parameters

  • prompt (str or List[str], optional) — prompt to be encoded

Encodes the prompt into text encoder hidden states.

device: (torch.device, optional): torch device to place the resulting embeddings on num_images_per_prompt (int, optional, defaults to 1): number of images that should be generated per prompt do_classifier_free_guidance (bool, optional, defaults to True): 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. 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.FloatTensor, 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.FloatTensor, 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.

IFInpaintingPipeline

class diffusers.IFInpaintingPipeline

< >

( tokenizer: T5Tokenizer text_encoder: T5EncoderModel unet: UNet2DConditionModel scheduler: DDPMScheduler safety_checker: typing.Optional[diffusers.pipelines.deepfloyd_if.safety_checker.IFSafetyChecker] feature_extractor: typing.Optional[transformers.models.clip.image_processing_clip.CLIPImageProcessor] watermarker: typing.Optional[diffusers.pipelines.deepfloyd_if.watermark.IFWatermarker] requires_safety_checker: bool = True )

__call__

< >

( prompt: typing.Union[str, typing.List[str]] = None image: typing.Union[PIL.Image.Image, torch.Tensor, numpy.ndarray, typing.List[PIL.Image.Image], typing.List[torch.Tensor], typing.List[numpy.ndarray]] = None mask_image: typing.Union[PIL.Image.Image, torch.Tensor, numpy.ndarray, typing.List[PIL.Image.Image], typing.List[torch.Tensor], typing.List[numpy.ndarray]] = None strength: float = 1.0 num_inference_steps: int = 50 timesteps: typing.List[int] = None guidance_scale: float = 7.0 negative_prompt: typing.Union[str, typing.List[str], NoneType] = None num_images_per_prompt: typing.Optional[int] = 1 eta: float = 0.0 generator: typing.Union[torch._C.Generator, typing.List[torch._C.Generator], NoneType] = None prompt_embeds: typing.Optional[torch.FloatTensor] = None negative_prompt_embeds: typing.Optional[torch.FloatTensor] = None output_type: typing.Optional[str] = 'pil' return_dict: bool = True callback: typing.Union[typing.Callable[[int, int, torch.FloatTensor], NoneType], NoneType] = None callback_steps: int = 1 clean_caption: bool = True cross_attention_kwargs: typing.Union[typing.Dict[str, typing.Any], NoneType] = None ) → ~pipelines.stable_diffusion.IFPipelineOutput or tuple

Parameters

  • 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.FloatTensor or PIL.Image.Image) — Image, or tensor representing an image batch, that will be used as the starting point for the process.
  • mask_image (PIL.Image.Image) — Image, or tensor representing an image batch, to mask image. White pixels in the mask will be repainted, while black pixels will be preserved. If mask_image is a PIL image, it will be converted to a single channel (luminance) before use. If it’s a tensor, it should contain one color channel (L) instead of 3, so the expected shape would be (B, H, W, 1).
  • strength (float, optional, defaults to 0.8) — Conceptually, indicates how much to transform the reference image. Must be between 0 and 1. image will be used as a starting point, adding more noise to it the larger the strength. The number of denoising steps depends on the amount of noise initially added. When strength is 1, added noise will be maximum and the denoising process will run for the full number of iterations specified in num_inference_steps. A value of 1, therefore, essentially ignores 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. If not defined, equal spaced num_inference_steps timesteps are used. Must be in descending order.
  • guidance_scale (float, optional, defaults to 7.5) — Guidance scale as defined in Classifier-Free Diffusion Guidance. guidance_scale is defined as w of equation 2. of Imagen Paper. 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. 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) to make generation deterministic.
  • prompt_embeds (torch.FloatTensor, 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.FloatTensor, 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: PIL.Image.Image or np.array.
  • return_dict (bool, optional, defaults to True) — Whether or not to return a ~pipelines.stable_diffusion.IFPipelineOutput 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.FloatTensor).
  • 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.
  • clean_caption (bool, optional, defaults to True) — Whether or not to clean the caption before creating embeddings. Requires beautifulsoup4 and ftfy to be installed. If the dependencies are not installed, the embeddings will be created from the raw prompt.
  • cross_attention_kwargs (dict, optional) — A kwargs dictionary that if specified is passed along to the AttentionProcessor as defined under self.processor in diffusers.cross_attention.

Returns

~pipelines.stable_diffusion.IFPipelineOutput or tuple

~pipelines.stable_diffusion.IFPipelineOutput 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 bools denoting whether the corresponding generated image likely represents "not-safe-for-work" (nsfw) or watermarked content, according to the safety_checker`.

Function invoked when calling the pipeline for generation.

Examples:

>>> from diffusers import IFInpaintingPipeline, IFInpaintingSuperResolutionPipeline, DiffusionPipeline
>>> from diffusers.utils import pt_to_pil
>>> import torch
>>> from PIL import Image
>>> import requests
>>> from io import BytesIO

>>> url = "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/if/person.png"
>>> response = requests.get(url)
>>> original_image = Image.open(BytesIO(response.content)).convert("RGB")
>>> original_image = original_image

>>> url = "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/if/glasses_mask.png"
>>> response = requests.get(url)
>>> mask_image = Image.open(BytesIO(response.content))
>>> mask_image = mask_image

>>> pipe = IFInpaintingPipeline.from_pretrained(
...     "DeepFloyd/IF-I-XL-v1.0", variant="fp16", torch_dtype=torch.float16
... )
>>> pipe.enable_model_cpu_offload()

>>> prompt = "blue sunglasses"
>>> prompt_embeds, negative_embeds = pipe.encode_prompt(prompt)

>>> image = pipe(
...     image=original_image,
...     mask_image=mask_image,
...     prompt_embeds=prompt_embeds,
...     negative_prompt_embeds=negative_embeds,
...     output_type="pt",
... ).images

>>> # save intermediate image
>>> pil_image = pt_to_pil(image)
>>> pil_image[0].save("./if_stage_I.png")

>>> super_res_1_pipe = IFInpaintingSuperResolutionPipeline.from_pretrained(
...     "DeepFloyd/IF-II-L-v1.0", text_encoder=None, variant="fp16", torch_dtype=torch.float16
... )
>>> super_res_1_pipe.enable_model_cpu_offload()

>>> image = super_res_1_pipe(
...     image=image,
...     mask_image=mask_image,
...     original_image=original_image,
...     prompt_embeds=prompt_embeds,
...     negative_prompt_embeds=negative_embeds,
... ).images
>>> image[0].save("./if_stage_II.png")

enable_model_cpu_offload

< >

( gpu_id = 0 )

Offloads all models to CPU using accelerate, reducing memory usage with a low impact on performance. Compared to enable_sequential_cpu_offload, this method moves one whole model at a time to the GPU when its forward method is called, and the model remains in GPU until the next model runs. Memory savings are lower than with enable_sequential_cpu_offload, but performance is much better due to the iterative execution of the unet.

encode_prompt

< >

( prompt do_classifier_free_guidance = True num_images_per_prompt = 1 device = None negative_prompt = None prompt_embeds: typing.Optional[torch.FloatTensor] = None negative_prompt_embeds: typing.Optional[torch.FloatTensor] = None clean_caption: bool = False )

Parameters

  • prompt (str or List[str], optional) — prompt to be encoded

Encodes the prompt into text encoder hidden states.

device: (torch.device, optional): torch device to place the resulting embeddings on num_images_per_prompt (int, optional, defaults to 1): number of images that should be generated per prompt do_classifier_free_guidance (bool, optional, defaults to True): 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. 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.FloatTensor, 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.FloatTensor, 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.

IFInpaintingSuperResolutionPipeline

class diffusers.IFInpaintingSuperResolutionPipeline

< >

( tokenizer: T5Tokenizer text_encoder: T5EncoderModel unet: UNet2DConditionModel scheduler: DDPMScheduler image_noising_scheduler: DDPMScheduler safety_checker: typing.Optional[diffusers.pipelines.deepfloyd_if.safety_checker.IFSafetyChecker] feature_extractor: typing.Optional[transformers.models.clip.image_processing_clip.CLIPImageProcessor] watermarker: typing.Optional[diffusers.pipelines.deepfloyd_if.watermark.IFWatermarker] requires_safety_checker: bool = True )

__call__

< >

( image: typing.Union[PIL.Image.Image, numpy.ndarray, torch.FloatTensor] original_image: typing.Union[PIL.Image.Image, torch.Tensor, numpy.ndarray, typing.List[PIL.Image.Image], typing.List[torch.Tensor], typing.List[numpy.ndarray]] = None mask_image: typing.Union[PIL.Image.Image, torch.Tensor, numpy.ndarray, typing.List[PIL.Image.Image], typing.List[torch.Tensor], typing.List[numpy.ndarray]] = None strength: float = 0.8 prompt: typing.Union[str, typing.List[str]] = None num_inference_steps: int = 100 timesteps: typing.List[int] = None guidance_scale: float = 4.0 negative_prompt: typing.Union[str, typing.List[str], NoneType] = None num_images_per_prompt: typing.Optional[int] = 1 eta: float = 0.0 generator: typing.Union[torch._C.Generator, typing.List[torch._C.Generator], NoneType] = None prompt_embeds: typing.Optional[torch.FloatTensor] = None negative_prompt_embeds: typing.Optional[torch.FloatTensor] = None output_type: typing.Optional[str] = 'pil' return_dict: bool = True callback: typing.Union[typing.Callable[[int, int, torch.FloatTensor], NoneType], NoneType] = None callback_steps: int = 1 cross_attention_kwargs: typing.Union[typing.Dict[str, typing.Any], NoneType] = None noise_level: int = 0 clean_caption: bool = True ) → ~pipelines.stable_diffusion.IFPipelineOutput or tuple

Parameters

  • image (torch.FloatTensor or PIL.Image.Image) — Image, or tensor representing an image batch, that will be used as the starting point for the process.
  • original_image (torch.FloatTensor or PIL.Image.Image) — The original image that image was varied from.
  • mask_image (PIL.Image.Image) — Image, or tensor representing an image batch, to mask image. White pixels in the mask will be repainted, while black pixels will be preserved. If mask_image is a PIL image, it will be converted to a single channel (luminance) before use. If it’s a tensor, it should contain one color channel (L) instead of 3, so the expected shape would be (B, H, W, 1).
  • strength (float, optional, defaults to 0.8) — Conceptually, indicates how much to transform the reference image. Must be between 0 and 1. image will be used as a starting point, adding more noise to it the larger the strength. The number of denoising steps depends on the amount of noise initially added. When strength is 1, added noise will be maximum and the denoising process will run for the full number of iterations specified in num_inference_steps. A value of 1, therefore, essentially ignores image.
  • 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.
  • 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. If not defined, equal spaced num_inference_steps timesteps are used. Must be in descending order.
  • guidance_scale (float, optional, defaults to 7.5) — Guidance scale as defined in Classifier-Free Diffusion Guidance. guidance_scale is defined as w of equation 2. of Imagen Paper. 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. 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) to make generation deterministic.
  • prompt_embeds (torch.FloatTensor, 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.FloatTensor, 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: PIL.Image.Image or np.array.
  • return_dict (bool, optional, defaults to True) — Whether or not to return a ~pipelines.stable_diffusion.IFPipelineOutput 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.FloatTensor).
  • 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 AttentionProcessor as defined under self.processor in diffusers.cross_attention.
  • noise_level (int, optional, defaults to 0) — The amount of noise to add to the upscaled image. Must be in the range [0, 1000)
  • clean_caption (bool, optional, defaults to True) — Whether or not to clean the caption before creating embeddings. Requires beautifulsoup4 and ftfy to be installed. If the dependencies are not installed, the embeddings will be created from the raw prompt.

Returns

~pipelines.stable_diffusion.IFPipelineOutput or tuple

~pipelines.stable_diffusion.IFPipelineOutput 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 bools denoting whether the corresponding generated image likely represents "not-safe-for-work" (nsfw) or watermarked content, according to the safety_checker`.

Function invoked when calling the pipeline for generation.

Examples:

>>> from diffusers import IFInpaintingPipeline, IFInpaintingSuperResolutionPipeline, DiffusionPipeline
>>> from diffusers.utils import pt_to_pil
>>> import torch
>>> from PIL import Image
>>> import requests
>>> from io import BytesIO

>>> url = "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/if/person.png"
>>> response = requests.get(url)
>>> original_image = Image.open(BytesIO(response.content)).convert("RGB")
>>> original_image = original_image

>>> url = "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/if/glasses_mask.png"
>>> response = requests.get(url)
>>> mask_image = Image.open(BytesIO(response.content))
>>> mask_image = mask_image

>>> pipe = IFInpaintingPipeline.from_pretrained(
...     "DeepFloyd/IF-I-XL-v1.0", variant="fp16", torch_dtype=torch.float16
... )
>>> pipe.enable_model_cpu_offload()

>>> prompt = "blue sunglasses"

>>> prompt_embeds, negative_embeds = pipe.encode_prompt(prompt)
>>> image = pipe(
...     image=original_image,
...     mask_image=mask_image,
...     prompt_embeds=prompt_embeds,
...     negative_prompt_embeds=negative_embeds,
...     output_type="pt",
... ).images

>>> # save intermediate image
>>> pil_image = pt_to_pil(image)
>>> pil_image[0].save("./if_stage_I.png")

>>> super_res_1_pipe = IFInpaintingSuperResolutionPipeline.from_pretrained(
...     "DeepFloyd/IF-II-L-v1.0", text_encoder=None, variant="fp16", torch_dtype=torch.float16
... )
>>> super_res_1_pipe.enable_model_cpu_offload()

>>> image = super_res_1_pipe(
...     image=image,
...     mask_image=mask_image,
...     original_image=original_image,
...     prompt_embeds=prompt_embeds,
...     negative_prompt_embeds=negative_embeds,
... ).images
>>> image[0].save("./if_stage_II.png")

enable_model_cpu_offload

< >

( gpu_id = 0 )

Offloads all models to CPU using accelerate, reducing memory usage with a low impact on performance. Compared to enable_sequential_cpu_offload, this method moves one whole model at a time to the GPU when its forward method is called, and the model remains in GPU until the next model runs. Memory savings are lower than with enable_sequential_cpu_offload, but performance is much better due to the iterative execution of the unet.

encode_prompt

< >

( prompt do_classifier_free_guidance = True num_images_per_prompt = 1 device = None negative_prompt = None prompt_embeds: typing.Optional[torch.FloatTensor] = None negative_prompt_embeds: typing.Optional[torch.FloatTensor] = None clean_caption: bool = False )

Parameters

  • prompt (str or List[str], optional) — prompt to be encoded

Encodes the prompt into text encoder hidden states.

device: (torch.device, optional): torch device to place the resulting embeddings on num_images_per_prompt (int, optional, defaults to 1): number of images that should be generated per prompt do_classifier_free_guidance (bool, optional, defaults to True): 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. 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.FloatTensor, 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.FloatTensor, 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.

←DDPM DiffEdit→