Diffusers documentation

VisualCloze

Diffusers

You are viewing main version, which requires installation from source. If you'd like regular pip install, checkout the latest stable version (v0.42.1).

Join the Hugging Face community

and get access to the augmented documentation experience

Collaborate on models, datasets and Spaces

Faster examples with accelerated inference

Switch between documentation themes

to get started

VisualCloze

VisualCloze: A Universal Image Generation Framework via Visual In-Context Learning 是一个基于上下文学习的通用图像生成框架，提供以下关键能力：

支持多种领域内任务
通过上下文学习泛化到未见过的任务
将多个任务统一为一步，同时生成目标图像和中间结果
支持从目标图像逆向推导条件

概述

该论文的摘要如下：

扩散模型的最新进展显著推动了各类图像生成任务的发展。然而，当前主流方法仍专注于构建特定任务模型，在支持多样化需求时效率有限。虽然通用模型试图解决这一局限，但面临着可泛化的任务指令、合适的任务分布以及统一架构设计等关键挑战。为应对这些挑战，我们提出了 VisualCloze，一个通用图像生成框架，支持广泛的领域内任务、对未见任务的泛化、多任务的未见统一以及逆向生成。与依赖基于语言的任务指令、从而导致任务歧义和泛化能力较弱的现有方法不同，我们整合了视觉上下文学习，使模型能够从视觉演示中识别任务。同时，视觉任务分布固有的稀疏性阻碍了跨任务可迁移知识的学习。为此，我们引入了 Graph200K，一个图结构数据集，建立了各种相互关联的任务，增强了任务密度和可迁移知识。此外，我们发现我们的统一图像生成公式与图像填充共享了一致的目标，使我们能够在不修改架构的情况下利用预训练填充模型的强大生成先验。代码、数据集和模型可在 https://visualcloze.github.io 获取。

推理

模型加载

VisualCloze 是一个两阶段级联流水线，包含 VisualClozeGenerationPipeline 和 VisualClozeUpsamplingPipeline。

在 VisualClozeGenerationPipeline 中，每张图像在拼接为网格布局之前都会先进行下采样，以避免分辨率过高。VisualCloze 发布了两个适用于 diffusers 的模型，即 VisualClozePipeline-384 和 VisualClozePipeline-512，它们分别将图像下采样至 384 和 512 的分辨率。
VisualClozeUpsamplingPipeline 使用 SDEdit 实现高分辨率图像合成。

VisualClozePipeline 将两个阶段整合在一起，以支持便捷的端到端采样，同时也允许用户根据需要使用各个独立的 pipeline。

输入规范

任务和内容提示

任务提示：需要描述生成任务的意图
内容提示：目标图像的可选描述或说明
当不需要内容提示时，传入 None
对于批量推理，请传入 List[str|None]

图像输入格式

格式：List[List[Image|None]]
结构：
- 除最后一行外，所有行均表示上下文示例
- 最后一行表示当前查询（目标图像设置为 None）
对于批量推理，请传入 List[List[List[Image|None]]]

分辨率控制

默认行为：
- 第一阶段初始生成：区域为 ${pipe.resolution}^2$
- 第二阶段的：3 倍因子
自定义分辨率：使用 upsampling_height 和 upsampling_width 参数进行调整

示例

如需涵盖多种任务的完整示例，请参阅在线演示和GitHub 仓库。以下是三种情况的简单示例：掩码转图像、边缘检测以及主体驱动生成。

mask2image 示例

import torch
from diffusers import VisualClozePipeline
from diffusers.utils import load_image

pipe = VisualClozePipeline.from_pretrained("VisualCloze/VisualClozePipeline-384", resolution=384, dtype=torch.bfloat16)
pipe.to("cuda")  # or "mps", "xpu", "cpu"

# Load in-context images (make sure the paths are correct and accessible)
image_paths = [
    # in-context examples
    [
        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_mask2image_incontext-example-1_mask.jpg'),
        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_mask2image_incontext-example-1_image.jpg'),
    ],
    # query with the target image
    [
        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_mask2image_query_mask.jpg'),
        None, # No image needed for the target image
    ],
]

# Task and content prompt
task_prompt = "In each row, a logical task is demonstrated to achieve [IMAGE2] an aesthetically pleasing photograph based on [IMAGE1] sam 2-generated masks with rich color coding."
content_prompt = """Majestic photo of a golden eagle perched on a rocky outcrop in a mountainous landscape. 
The eagle is positioned in the right foreground, facing left, with its sharp beak and keen eyes prominently visible. 
Its plumage is a mix of dark brown and golden hues, with intricate feather details. 
The background features a soft-focus view of snow-capped mountains under a cloudy sky, creating a serene and grandiose atmosphere. 
The foreground includes rugged rocks and patches of green moss. Photorealistic, medium depth of field, 
soft natural lighting, cool color palette, high contrast, sharp focus on the eagle, blurred background, 
tranquil, majestic, wildlife photography."""

# Run the pipeline
image_result = pipe(
    task_prompt=task_prompt,
    content_prompt=content_prompt,
    image=image_paths,
    upsampling_width=1344,
    upsampling_height=768,
    upsampling_strength=0.4,
    guidance_scale=30,
    num_inference_steps=30,
    max_sequence_length=512,
    generator=torch.Generator("cpu").manual_seed(0)
).images[0][0]

# Save the resulting image
image_result.save("visualcloze.png")

边缘检测示例

import torch
from diffusers import VisualClozePipeline
from diffusers.utils import load_image

pipe = VisualClozePipeline.from_pretrained("VisualCloze/VisualClozePipeline-384", resolution=384, dtype=torch.bfloat16)
pipe.to("cuda")  # or "mps", "xpu", "cpu"

# Load in-context images (make sure the paths are correct and accessible)
image_paths = [
    # in-context examples
    [
        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_edgedetection_incontext-example-1_image.jpg'),
        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_edgedetection_incontext-example-1_edge.jpg'),
    ],
    [
        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_edgedetection_incontext-example-2_image.jpg'),
        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_edgedetection_incontext-example-2_edge.jpg'),
    ],
    # query with the target image
    [
        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_edgedetection_query_image.jpg'),
        None, # No image needed for the target image
    ],
]

# Task and content prompt
task_prompt = "Each row illustrates a pathway from [IMAGE1] a sharp and beautifully composed photograph to [IMAGE2] edge map with natural well-connected outlines using a clear logical task."
content_prompt = ""

# Run the pipeline
image_result = pipe(
    task_prompt=task_prompt,
    content_prompt=content_prompt,
    image=image_paths,
    upsampling_width=864,
    upsampling_height=1152,
    upsampling_strength=0.4,
    guidance_scale=30,
    num_inference_steps=30,
    max_sequence_length=512,
    generator=torch.Generator("cpu").manual_seed(0)
).images[0][0]

# Save the resulting image
image_result.save("visualcloze.png")

主题驱动生成的示例

import torch
from diffusers import VisualClozePipeline
from diffusers.utils import load_image

pipe = VisualClozePipeline.from_pretrained("VisualCloze/VisualClozePipeline-384", resolution=384, dtype=torch.bfloat16)
pipe.to("cuda")  # or "mps", "xpu", "cpu"

# Load in-context images (make sure the paths are correct and accessible)
image_paths = [
    # in-context examples
    [
        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_subjectdriven_incontext-example-1_reference.jpg'),
        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_subjectdriven_incontext-example-1_depth.jpg'),
        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_subjectdriven_incontext-example-1_image.jpg'),
    ],
    [
        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_subjectdriven_incontext-example-2_reference.jpg'),
        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_subjectdriven_incontext-example-2_depth.jpg'),
        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_subjectdriven_incontext-example-2_image.jpg'),
    ],
    # query with the target image
    [
        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_subjectdriven_query_reference.jpg'),
        load_image('https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_subjectdriven_query_depth.jpg'),
        None, # No image needed for the target image
    ],
]

# Task and content prompt
task_prompt = """Each row describes a process that begins with [IMAGE1] an image containing the key object, 
[IMAGE2] depth map revealing gray-toned spatial layers and results in 
[IMAGE3] an image with artistic qualitya high-quality image with exceptional detail."""
content_prompt = """A vintage porcelain collector's item. Beneath a blossoming cherry tree in early spring, 
this treasure is photographed up close, with soft pink petals drifting through the air and vibrant blossoms framing the scene."""

# Run the pipeline
image_result = pipe(
    task_prompt=task_prompt,
    content_prompt=content_prompt,
    image=image_paths,
    upsampling_width=1024,
    upsampling_height=1024,
    upsampling_strength=0.2,
    guidance_scale=30,
    num_inference_steps=30,
    max_sequence_length=512,
    generator=torch.Generator("cpu").manual_seed(0)
).images[0][0]

# Save the resulting image
image_result.save("visualcloze.png")

独立使用每个流水线

import torch
from diffusers import VisualClozeGenerationPipeline, FluxFillPipeline as VisualClozeUpsamplingPipeline
from diffusers.utils import load_image
from PIL import Image

pipe = VisualClozeGenerationPipeline.from_pretrained(
    "VisualCloze/VisualClozePipeline-384", resolution=384, dtype=torch.bfloat16
)
pipe.to("cuda")  # or "mps", "xpu", "cpu"

image_paths = [
    # in-context examples
    [
        load_image(
            "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_mask2image_incontext-example-1_mask.jpg"
        ),
        load_image(
            "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_mask2image_incontext-example-1_image.jpg"
        ),
    ],
    # query with the target image
    [
        load_image(
            "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_mask2image_query_mask.jpg"
        ),
        None,  # No image needed for the target image
    ],
]
task_prompt = "In each row, a logical task is demonstrated to achieve [IMAGE2] an aesthetically pleasing photograph based on [IMAGE1] sam 2-generated masks with rich color coding."
content_prompt = "Majestic photo of a golden eagle perched on a rocky outcrop in a mountainous landscape. The eagle is positioned in the right foreground, facing left, with its sharp beak and keen eyes prominently visible. Its plumage is a mix of dark brown and golden hues, with intricate feather details. The background features a soft-focus view of snow-capped mountains under a cloudy sky, creating a serene and grandiose atmosphere. The foreground includes rugged rocks and patches of green moss. Photorealistic, medium depth of field, soft natural lighting, cool color palette, high contrast, sharp focus on the eagle, blurred background, tranquil, majestic, wildlife photography."

# Stage 1: Generate initial image
image = pipe(
    task_prompt=task_prompt,
    content_prompt=content_prompt,
    image=image_paths,
    guidance_scale=30,
    num_inference_steps=30,
    max_sequence_length=512,
    generator=torch.Generator("cpu").manual_seed(0),
).images[0][0]

# Stage 2 (optional): Upsample the generated image
pipe_upsample = VisualClozeUpsamplingPipeline.from_pipe(pipe)
pipe_upsample.to("cuda")

mask_image = Image.new("RGB", image.size, (255, 255, 255))

image = pipe_upsample(
    image=image,
    mask_image=mask_image,
    prompt=content_prompt,
    width=1344,
    height=768,
    strength=0.4,
    guidance_scale=30,
    num_inference_steps=30,
    max_sequence_length=512,
    generator=torch.Generator("cpu").manual_seed(0),
).images[0]

image.save("visualcloze.png")

VisualClozePipeline

class diffusers.VisualClozePipeline

< source >

( scheduler: FlowMatchEulerDiscreteSchedulervae: AutoencoderKLtext_encoder: CLIPTextModeltokenizer: CLIPTokenizertext_encoder_2: T5EncoderModeltokenizer_2: T5Tokenizertransformer: FluxTransformer2DModelresolution: int = 384 )

参数

transformer (FluxTransformer2DModel) — 用于对编码后的图像潜变量进行去噪的条件 Transformer (MMDiT) 架构。
scheduler (FlowMatchEulerDiscreteScheduler) — 用于与 transformer 配合，对编码后的图像潜变量进行去噪的调度器。
vae (AutoencoderKL) — 变分自编码器（VAE）模型，用于将图像编码为潜在表示，以及从潜在表示解码回图像。
text_encoder (CLIPTextModel) — CLIP，具体为 clip-vit-large-patch14 变体。
text_encoder_2 (T5EncoderModel) — T5，具体为 google/t5-v1_1-xxl 变体。
tokenizer (CLIPTokenizer) — CLIPTokenizer 类的分词器。
tokenizer_2（T5TokenizerFast）—— 第二个 T5TokenizerFast 类的 Tokenizer。
resolution (int，可选，默认为 384) — 在拼接查询和上下文示例中的图像时，每张图像的分辨率。

用于基于视觉上下文进行图像生成的 VisualCloze 流水线。参考：https://github.com/lzyhha/VisualCloze/tree/main。该流水线旨在根据视觉上下文示例生成图像。

call

< source >

( task_prompt: str | list[str] = Nonecontent_prompt: str | list[str] = Noneimage: typing.Optional[torch.FloatTensor] = Noneupsampling_height: int | None = Noneupsampling_width: int | None = Nonenum_inference_steps: int = 50sigmas: list[float] | None = Noneguidance_scale: float = 30.0num_images_per_prompt: int | None = 1generator: typing.Union[torch.Generator, list[torch.Generator], NoneType] = Nonelatents: typing.Optional[torch.FloatTensor] = Noneprompt_embeds: typing.Optional[torch.FloatTensor] = Nonepooled_prompt_embeds: typing.Optional[torch.FloatTensor] = Noneoutput_type: str | None = 'pil'return_dict: bool = Truejoint_attention_kwargs: dict[str, typing.Any] | None = Nonecallback_on_step_end: typing.Optional[typing.Callable[[int, int], NoneType]] = Nonecallback_on_step_end_tensor_inputs: list = ['latents']max_sequence_length: int = 512upsampling_strength: float = 1.0 ) → ~pipelines.flux.FluxPipelineOutput or tuple

参数

task_prompt (str 或 list[str]，可选) — 用于定义任务意图的提示词或提示词列表。
content_prompt (str 或 list[str]，可选) — 用于定义要生成的目标图像的内容或说明的提示词或提示词列表。
image (torch.Tensor、PIL.Image.Image、np.ndarray、list[torch.Tensor]、list[PIL.Image.Image] 或 list[np.ndarray]) — Image、numpy 数组或张量，表示用作起点的图像批次。对于 numpy 数组和 pytorch 张量，预期的取值范围为 [0, 1]。如果是张量或张量列表，预期的形状应为 (B, C, H, W) 或 (C, H, W)。如果是 numpy 数组或数组列表，预期的形状应为 (B, H, W, C) 或 (H, W, C)。
upsampling_height (int, 可选，默认为 self.unet.config.sample_size * self.vae_scale_factor) — 通过 SDEdit 进行上采样后生成图像（即输出图像）的像素高度。默认情况下，图像会放大三倍，基础分辨率由流水线的 resolution 参数决定。如果仅指定了 upsampling_height 或 upsampling_width 中的一个，另一个将根据宽高比自动设置。
upsampling_width (int, 可选，默认为 self.unet.config.sample_size * self.vae_scale_factor) — 通过 SDEdit 进行上采样后生成图像（即输出图像）的像素宽度。默认情况下，图像会放大三倍，基础分辨率由 pipeline 的 resolution 参数决定。如果只指定了 upsampling_height 或 upsampling_width 中的一个，另一个将根据宽高比自动设置。
num_inference_steps (int，可选，默认为 50) — 去噪步数。更多的去噪步数通常能生成更高质量的图像，但代价是推理速度变慢。
sigmas (list[float]，可选) — 用于在支持 sigmas 参数的调度器的 set_timesteps 方法中，为去噪过程指定自定义的 sigmas。如果未定义，则使用传入 num_inference_steps 时的默认行为。
guidance_scale (float，可选，默认为 30.0) — Classifier-Free Diffusion Guidance 中定义的引导尺度。guidance_scale 定义为 Imagen Paper 中公式 2 的 w。通过设置 guidance_scale > 1 来启用引导尺度。较高的引导尺度会促使生成与文本 prompt 紧密关联的图像，通常以牺牲图像质量为代价。
num_images_per_prompt (int，可选，默认为 1) — 每个提示词生成的图像数量。
generator (torch.Generator 或 list[torch.Generator]，可选) — 一个或一组 torch 生成器，用于使生成过程具有确定性。
latents (torch.FloatTensor, 可选) — 预先生成的噪声潜变量，从高斯分布中采样，用作图像生成的输入。可用于使用不同的提示词对同一生成过程进行微调。如果未提供，将通过使用提供的随机generator进行采样来生成一个潜变量张量。
prompt_embeds (torch.FloatTensor, 可选) — 预生成的文本嵌入。可用于轻松调整文本输入，例如提示词加权。如果未提供，文本嵌入将从 prompt 输入参数生成。
pooled_prompt_embeds (torch.FloatTensor，可选) — 预生成的池化文本嵌入。可用于轻松调整文本输入，例如提示词加权。如果未提供，将从 prompt 输入参数生成池化文本嵌入。
output_type (str，可选，默认为 "pil") — 生成图像的输出格式。可选值为 PIL：PIL.Image.Image 或 np.array。
return_dict (bool，可选，默认为 True) — 是否返回 ~pipelines.flux.FluxPipelineOutput 而不是普通元组。
joint_attention_kwargs (dict, 可选) — 一个 kwargs 字典，如果指定，将作为参数传递给 diffusers.models.attention_processor 中 self.processor 下定义的 AttentionProcessor。
callback_on_step_end (Callable, 可选) — 一个在推理过程中每个去噪步骤结束时调用的函数。该函数以以下参数被调用：callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int, callback_kwargs: Dict)。callback_kwargs 将包含由 callback_on_step_end_tensor_inputs 指定的所有张量列表。
callback_on_step_end_tensor_inputs (list，可选) — callback_on_step_end 函数的张量输入列表。列表中指定的张量将作为 callback_kwargs 参数传递。您只能包含流水线类 ._callback_tensor_inputs 属性中列出的变量。
max_sequence_length（int，默认为 512）— 与 prompt 配合使用的最大序列长度。
upsampling_strength (float, 可选, ，默认值为 1.0）—— 指示在放大结果时对参考 image 进行变换的程度。取值必须在 0 和
1. 生成的图像用作起点，upsampling_strength 越高，添加的噪声越多。去噪步数取决于初始添加的噪声量。当 upsampling_strength 为 1 时，添加的噪声达到最大值，去噪过程将运行 num_inference_steps 中指定的完整迭代次数。值为 0 时会跳过上采样步骤，并以 self.resolution 的分辨率输出结果。

返回值

~pipelines.flux.FluxPipelineOutput 或 tuple

~pipelines.flux.FluxPipelineOutput（当 return_dict 为 True 时），否则为 tuple。返回元组时，第一个元素是包含生成图像的列表。

调用 VisualCloze 流水线进行生成时调用的函数。

示例：

>>> import torch
>>> from diffusers import VisualClozePipeline
>>> from diffusers.utils import load_image

>>> image_paths = [
...     # in-context examples
...     [
...         load_image(
...             "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_mask2image_incontext-example-1_mask.jpg"
...         ),
...         load_image(
...             "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_mask2image_incontext-example-1_image.jpg"
...         ),
...     ],
...     # query with the target image
...     [
...         load_image(
...             "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_mask2image_query_mask.jpg"
...         ),
...         None,  # No image needed for the target image
...     ],
... ]
>>> task_prompt = "In each row, a logical task is demonstrated to achieve [IMAGE2] an aesthetically pleasing photograph based on [IMAGE1] sam 2-generated masks with rich color coding."
>>> content_prompt = "Majestic photo of a golden eagle perched on a rocky outcrop in a mountainous landscape. The eagle is positioned in the right foreground, facing left, with its sharp beak and keen eyes prominently visible. Its plumage is a mix of dark brown and golden hues, with intricate feather details. The background features a soft-focus view of snow-capped mountains under a cloudy sky, creating a serene and grandiose atmosphere. The foreground includes rugged rocks and patches of green moss. Photorealistic, medium depth of field, soft natural lighting, cool color palette, high contrast, sharp focus on the eagle, blurred background, tranquil, majestic, wildlife photography."
>>> pipe = VisualClozePipeline.from_pretrained(
...     "VisualCloze/VisualClozePipeline-384", resolution=384, torch_dtype=torch.bfloat16
... )
>>> pipe.to("cuda")

>>> image = pipe(
...     task_prompt=task_prompt,
...     content_prompt=content_prompt,
...     image=image_paths,
...     upsampling_width=1344,
...     upsampling_height=768,
...     upsampling_strength=0.4,
...     guidance_scale=30,
...     num_inference_steps=30,
...     max_sequence_length=512,
...     generator=torch.Generator("cpu").manual_seed(0),
... ).images[0][0]
>>> image.save("visualcloze.png")

VisualClozeGenerationPipeline

class diffusers.VisualClozeGenerationPipeline

< source >

参数

transformer (FluxTransformer2DModel) — 用于对编码后的图像潜变量进行去噪的条件 Transformer (MMDiT) 架构。
scheduler (FlowMatchEulerDiscreteScheduler) — 用于与 transformer 配合，对编码后的图像潜变量进行去噪的调度器。
vae (AutoencoderKL) — 变分自编码器（VAE）模型，用于将图像编码为潜在表示，以及从潜在表示解码回图像。
text_encoder (CLIPTextModel) — CLIP，具体为 clip-vit-large-patch14 变体。
text_encoder_2 (T5EncoderModel) — T5，具体为 google/t5-v1_1-xxl 变体。
tokenizer (CLIPTokenizer) — CLIPTokenizer 类的分词器。
tokenizer_2（T5TokenizerFast）—— 第二个 T5TokenizerFast 类的 Tokenizer。
resolution (int，可选，默认为 384) — 在拼接查询和上下文示例中的图像时，每张图像的分辨率。

用于基于视觉上下文进行图像生成的 VisualCloze 流水线。参考：https://github.com/lzyhha/VisualCloze/tree/main 该流水线旨在根据视觉上下文示例生成图像。

call

< source >

( task_prompt: str | list[str] = Nonecontent_prompt: str | list[str] = Noneimage: typing.Optional[torch.FloatTensor] = Nonenum_inference_steps: int = 50sigmas: list[float] | None = Noneguidance_scale: float = 30.0num_images_per_prompt: int | None = 1generator: typing.Union[torch.Generator, list[torch.Generator], NoneType] = Nonelatents: typing.Optional[torch.FloatTensor] = Noneprompt_embeds: typing.Optional[torch.FloatTensor] = Nonepooled_prompt_embeds: typing.Optional[torch.FloatTensor] = Noneoutput_type: str | None = 'pil'return_dict: bool = Truejoint_attention_kwargs: dict[str, typing.Any] | None = Nonecallback_on_step_end: typing.Optional[typing.Callable[[int, int], NoneType]] = Nonecallback_on_step_end_tensor_inputs: list = ['latents']max_sequence_length: int = 512 ) → ~pipelines.flux.FluxPipelineOutput or tuple

参数

task_prompt (str 或 list[str]，可选) — 用于定义任务意图的提示词或提示词列表。
content_prompt (str 或 list[str]，可选) — 用于定义要生成的目标图像的内容或说明的提示词或提示词列表。
image (torch.Tensor、PIL.Image.Image、np.ndarray、list[torch.Tensor]、list[PIL.Image.Image] 或 list[np.ndarray]) — Image、numpy 数组或张量，表示用作起点的图像批次。对于 numpy 数组和 pytorch 张量，预期的取值范围为 [0, 1]。如果是张量或张量列表，预期的形状应为 (B, C, H, W) 或 (C, H, W)。如果是 numpy 数组或数组列表，预期的形状应为 (B, H, W, C) 或 (H, W, C)。
num_inference_steps (int，可选，默认为 50) — 去噪步数。更多的去噪步数通常能生成更高质量的图像，但代价是推理速度变慢。
sigmas (list[float]，可选) — 用于在支持 sigmas 参数的调度器的 set_timesteps 方法中，为去噪过程指定自定义的 sigmas。如果未定义，则使用传入 num_inference_steps 时的默认行为。
guidance_scale (float，可选，默认为 30.0) — Classifier-Free Diffusion Guidance 中定义的引导尺度。guidance_scale 定义为 Imagen Paper 中公式 2 的 w。通过设置 guidance_scale > 1 来启用引导尺度。较高的引导尺度会促使生成与文本 prompt 紧密关联的图像，通常以牺牲图像质量为代价。
num_images_per_prompt (int，可选，默认为 1) — 每个提示词生成的图像数量。
generator (torch.Generator 或 list[torch.Generator]，可选) — 一个或一组 torch 生成器，用于使生成过程具有确定性。
latents (torch.FloatTensor, 可选) — 预先生成的噪声潜变量，从高斯分布中采样，用作图像生成的输入。可用于使用不同的提示词对同一生成过程进行微调。如果未提供，将通过使用提供的随机generator进行采样来生成一个潜变量张量。
prompt_embeds (torch.FloatTensor, 可选) — 预生成的文本嵌入。可用于轻松调整文本输入，例如提示词加权。如果未提供，文本嵌入将从 prompt 输入参数生成。
pooled_prompt_embeds (torch.FloatTensor，可选) — 预生成的池化文本嵌入。可用于轻松调整文本输入，例如提示词加权。如果未提供，将从 prompt 输入参数生成池化文本嵌入。
output_type (str，可选，默认为 "pil") — 生成图像的输出格式。可选 "pil" （PIL：PIL.Image.Image）、"np"（np.array）或 "pt" （torch.Tensor）。
return_dict (bool，可选，默认为 True) — 是否返回 ~pipelines.flux.FluxPipelineOutput 而不是普通元组。
joint_attention_kwargs (dict, 可选) — 一个 kwargs 字典，如果指定，将作为参数传递给 diffusers.models.attention_processor 中 self.processor 下定义的 AttentionProcessor。
callback_on_step_end (Callable, 可选) — 一个在推理过程中每个去噪步骤结束时调用的函数。该函数以以下参数被调用：callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int, callback_kwargs: Dict)。callback_kwargs 将包含由 callback_on_step_end_tensor_inputs 指定的所有张量列表。
callback_on_step_end_tensor_inputs (list，可选) — callback_on_step_end 函数的张量输入列表。列表中指定的张量将作为 callback_kwargs 参数传递。您只能包含流水线类 ._callback_tensor_inputs 属性中列出的变量。
max_sequence_length（int，默认为 512）— 与 prompt 配合使用的最大序列长度。

返回值

~pipelines.flux.FluxPipelineOutput 或 tuple

~pipelines.flux.FluxPipelineOutput（当 return_dict 为 True 时），否则为 tuple。返回元组时，第一个元素是包含生成图像的列表。

调用 VisualCloze 流水线进行生成时调用的函数。

示例：

>>> import torch
>>> from diffusers import VisualClozeGenerationPipeline, FluxFillPipeline as VisualClozeUpsamplingPipeline
>>> from diffusers.utils import load_image
>>> from PIL import Image

>>> image_paths = [
...     # in-context examples
...     [
...         load_image(
...             "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_mask2image_incontext-example-1_mask.jpg"
...         ),
...         load_image(
...             "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_mask2image_incontext-example-1_image.jpg"
...         ),
...     ],
...     # query with the target image
...     [
...         load_image(
...             "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/visualcloze/visualcloze_mask2image_query_mask.jpg"
...         ),
...         None,  # No image needed for the target image
...     ],
... ]
>>> task_prompt = "In each row, a logical task is demonstrated to achieve [IMAGE2] an aesthetically pleasing photograph based on [IMAGE1] sam 2-generated masks with rich color coding."
>>> content_prompt = "Majestic photo of a golden eagle perched on a rocky outcrop in a mountainous landscape. The eagle is positioned in the right foreground, facing left, with its sharp beak and keen eyes prominently visible. Its plumage is a mix of dark brown and golden hues, with intricate feather details. The background features a soft-focus view of snow-capped mountains under a cloudy sky, creating a serene and grandiose atmosphere. The foreground includes rugged rocks and patches of green moss. Photorealistic, medium depth of field, soft natural lighting, cool color palette, high contrast, sharp focus on the eagle, blurred background, tranquil, majestic, wildlife photography."
>>> pipe = VisualClozeGenerationPipeline.from_pretrained(
...     "VisualCloze/VisualClozePipeline-384", resolution=384, torch_dtype=torch.bfloat16
... )
>>> pipe.to("cuda")

>>> image = pipe(
...     task_prompt=task_prompt,
...     content_prompt=content_prompt,
...     image=image_paths,
...     guidance_scale=30,
...     num_inference_steps=30,
...     max_sequence_length=512,
...     generator=torch.Generator("cpu").manual_seed(0),
... ).images[0][0]

>>> # optional, upsampling the generated image
>>> pipe_upsample = VisualClozeUpsamplingPipeline.from_pipe(pipe)
>>> pipe_upsample.to("cuda")

>>> mask_image = Image.new("RGB", image.size, (255, 255, 255))

>>> image = pipe_upsample(
...     image=image,
...     mask_image=mask_image,
...     prompt=content_prompt,
...     width=1344,
...     height=768,
...     strength=0.4,
...     guidance_scale=30,
...     num_inference_steps=30,
...     max_sequence_length=512,
...     generator=torch.Generator("cpu").manual_seed(0),
... ).images[0]

>>> image.save("visualcloze.png")

encode_prompt

< source >

( layout_prompt: str | list[str]task_prompt: str | list[str]content_prompt: str | list[str]device: typing.Optional[torch.device] = Nonenum_images_per_prompt: int = 1prompt_embeds: typing.Optional[torch.FloatTensor] = Nonepooled_prompt_embeds: typing.Optional[torch.FloatTensor] = Nonemax_sequence_length: int = 512lora_scale: float | None = None )

参数

layout_prompt (str 或 list[str]，可选) — 用于定义任务中上下文示例数量和涉及图像数量的提示词或提示词列表。
task_prompt (str 或 list[str]，可选) — 用于定义任务意图的提示词或提示词列表。
content_prompt (str 或 list[str]，可选) — 用于定义要生成的目标图像的内容或说明的提示词或提示词列表。
device — (torch.device)： torch 设备
num_images_per_prompt (int) — 每个提示词应生成的图像数量
prompt_embeds (torch.FloatTensor, 可选) — 预生成的文本嵌入。可用于轻松调整文本输入，例如提示词加权。如果未提供，文本嵌入将从 prompt 输入参数生成。
pooled_prompt_embeds (torch.FloatTensor，可选) — 预生成的池化文本嵌入。可用于轻松调整文本输入，例如提示词加权。如果未提供，将从 prompt 输入参数生成池化文本嵌入。
lora_scale (float, 可选) — 如果加载了 LoRA 层，将应用于文本编码器所有 LoRA 层的 LoRA 缩放系数。

Update on GitHub

←价值引导采样 Z-Image→

Diffusers

VisualCloze

概述

推理

模型加载

输入规范

任务和内容提示

图像输入格式

分辨率控制

示例

mask2image 示例

边缘检测示例

主题驱动生成的示例

独立使用每个流水线

VisualClozePipeline

class diffusers.VisualClozePipeline

__call__

VisualClozeGenerationPipeline

class diffusers.VisualClozeGenerationPipeline

__call__

encode_prompt

call

call