GLIGEN (Grounded Language-to-Image Generation)
The GLIGEN model was created by researchers and engineers from University of Wisconsin-Madison, Columbia University, and Microsoft. The StableDiffusionGLIGENPipeline and StableDiffusionGLIGENTextImagePipeline can generate photorealistic images conditioned on grounding inputs. Along with text and bounding boxes with StableDiffusionGLIGENPipeline, if input images are given, StableDiffusionGLIGENTextImagePipeline can insert objects described by text at the region defined by bounding boxes. Otherwise, it’ll generate an image described by the caption/prompt and insert objects described by text at the region defined by bounding boxes. It’s trained on COCO2014D and COCO2014CD datasets, and the model uses a frozen CLIP ViT-L/14 text encoder to condition itself on grounding inputs.
The abstract from the paper is:
Large-scale text-to-image diffusion models have made amazing advances. However, the status quo is to use text input alone, which can impede controllability. In this work, we propose GLIGEN, Grounded-Language-to-Image Generation, a novel approach that builds upon and extends the functionality of existing pre-trained text-to-image diffusion models by enabling them to also be conditioned on grounding inputs. To preserve the vast concept knowledge of the pre-trained model, we freeze all of its weights and inject the grounding information into new trainable layers via a gated mechanism. Our model achieves open-world grounded text2img generation with caption and bounding box condition inputs, and the grounding ability generalizes well to novel spatial configurations and concepts. GLIGEN’s zeroshot performance on COCO and LVIS outperforms existing supervised layout-to-image baselines by a large margin.
Make sure to check out the Stable Diffusion Tips section to learn how to explore the tradeoff between scheduler speed and quality and how to reuse pipeline components efficiently!
If you want to use one of the official checkpoints for a task, explore the gligen Hub organizations!
StableDiffusionGLIGENPipeline was contributed by Nikhil Gajendrakumar and StableDiffusionGLIGENTextImagePipeline was contributed by Nguyễn Công Tú Anh.
StableDiffusionGLIGENPipeline
class diffusers.StableDiffusionGLIGENPipeline
< source >( vae: AutoencoderKL text_encoder: CLIPTextModel tokenizer: CLIPTokenizer unet: UNet2DConditionModel scheduler: KarrasDiffusionSchedulers safety_checker: StableDiffusionSafetyChecker feature_extractor: CLIPImageProcessor requires_safety_checker: bool = True )
Parameters
- vae (AutoencoderKL) — Variational Auto-Encoder (VAE) model to encode and decode images to and from latent representations.
- text_encoder (CLIPTextModel) — Frozen text-encoder (clip-vit-large-patch14).
- tokenizer (CLIPTokenizer) —
A
CLIPTokenizer
to tokenize text. - unet (UNet2DConditionModel) —
A
UNet2DConditionModel
to denoise the encoded image latents. - scheduler (SchedulerMixin) —
A scheduler to be used in combination with
unet
to denoise the encoded image latents. Can be one of DDIMScheduler, LMSDiscreteScheduler, or PNDMScheduler. - safety_checker (
StableDiffusionSafetyChecker
) — Classification module that estimates whether generated images could be considered offensive or harmful. Please refer to the model card for more details about a model’s potential harms. - feature_extractor (CLIPImageProcessor) —
A
CLIPImageProcessor
to extract features from generated images; used as inputs to thesafety_checker
.
Pipeline for text-to-image generation using Stable Diffusion with Grounded-Language-to-Image Generation (GLIGEN).
This model inherits from DiffusionPipeline. Check the superclass documentation for the generic methods the library implements for all the pipelines (such as downloading or saving, running on a particular device, etc.).
__call__
< source >( prompt: typing.Union[str, typing.List[str]] = None height: typing.Optional[int] = None width: typing.Optional[int] = None num_inference_steps: int = 50 guidance_scale: float = 7.5 gligen_scheduled_sampling_beta: float = 0.3 gligen_phrases: typing.List[str] = None gligen_boxes: typing.List[typing.List[float]] = None gligen_inpaint_image: typing.Optional[PIL.Image.Image] = None 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 latents: typing.Optional[torch.Tensor] = None prompt_embeds: typing.Optional[torch.Tensor] = None negative_prompt_embeds: typing.Optional[torch.Tensor] = None output_type: typing.Optional[str] = 'pil' return_dict: bool = True callback: typing.Optional[typing.Callable[[int, int, torch.Tensor], NoneType]] = None callback_steps: int = 1 cross_attention_kwargs: typing.Optional[typing.Dict[str, typing.Any]] = None clip_skip: typing.Optional[int] = None ) → StableDiffusionPipelineOutput or tuple
Parameters
- prompt (
str
orList[str]
, optional) — The prompt or prompts to guide image generation. If not defined, you need to passprompt_embeds
. - height (
int
, optional, defaults toself.unet.config.sample_size * self.vae_scale_factor
) — The height in pixels of the generated image. - width (
int
, optional, defaults toself.unet.config.sample_size * self.vae_scale_factor
) — The width in pixels of the generated image. - num_inference_steps (
int
, optional, defaults to 50) — The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference. - guidance_scale (
float
, optional, defaults to 7.5) — A higher guidance scale value encourages the model to generate images closely linked to the textprompt
at the expense of lower image quality. Guidance scale is enabled whenguidance_scale > 1
. - gligen_phrases (
List[str]
) — The phrases to guide what to include in each of the regions defined by the correspondinggligen_boxes
. There should only be one phrase per bounding box. - gligen_boxes (
List[List[float]]
) — The bounding boxes that identify rectangular regions of the image that are going to be filled with the content described by the correspondinggligen_phrases
. Each rectangular box is defined as aList[float]
of 4 elements[xmin, ymin, xmax, ymax]
where each value is between [0,1]. - gligen_inpaint_image (
PIL.Image.Image
, optional) — The input image, if provided, is inpainted with objects described by thegligen_boxes
andgligen_phrases
. Otherwise, it is treated as a generation task on a blank input image. - gligen_scheduled_sampling_beta (
float
, defaults to 0.3) — Scheduled Sampling factor from GLIGEN: Open-Set Grounded Text-to-Image Generation. Scheduled Sampling factor is only varied for scheduled sampling during inference for improved quality and controllability. - negative_prompt (
str
orList[str]
, optional) — The prompt or prompts to guide what to not include in image generation. If not defined, you need to passnegative_prompt_embeds
instead. Ignored when not using guidance (guidance_scale < 1
). - num_images_per_prompt (
int
, optional, defaults to 1) — The number of images to generate per prompt. - eta (
float
, optional, defaults to 0.0) — Corresponds to parameter eta (η) from the DDIM paper. Only applies to the DDIMScheduler, and is ignored in other schedulers. - generator (
torch.Generator
orList[torch.Generator]
, optional) — Atorch.Generator
to make generation deterministic. - latents (
torch.Tensor
, optional) — Pre-generated noisy latents sampled from a Gaussian distribution, to be used as inputs for image generation. Can be used to tweak the same generation with different prompts. If not provided, a latents tensor is generated by sampling using the supplied randomgenerator
. - prompt_embeds (
torch.Tensor
, optional) — Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not provided, text embeddings are generated from theprompt
input argument. - negative_prompt_embeds (
torch.Tensor
, optional) — Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not provided,negative_prompt_embeds
are generated from thenegative_prompt
input argument. - output_type (
str
, optional, defaults to"pil"
) — The output format of the generated image. Choose betweenPIL.Image
ornp.array
. - return_dict (
bool
, optional, defaults toTrue
) — Whether or not to return a StableDiffusionPipelineOutput instead of a plain tuple. - callback (
Callable
, optional) — A function that calls everycallback_steps
steps during inference. The function is called with the following arguments:callback(step: int, timestep: int, latents: torch.Tensor)
. - callback_steps (
int
, optional, defaults to 1) — The frequency at which thecallback
function is called. If not specified, the callback is called at every step. - cross_attention_kwargs (
dict
, optional) — A kwargs dictionary that if specified is passed along to theAttentionProcessor
as defined inself.processor
. - guidance_rescale (
float
, optional, defaults to 0.0) — Guidance rescale factor from Common Diffusion Noise Schedules and Sample Steps are Flawed. Guidance rescale factor should fix overexposure when using zero terminal SNR. - clip_skip (
int
, optional) — Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that the output of the pre-final layer will be used for computing the prompt embeddings.
Returns
StableDiffusionPipelineOutput or tuple
If return_dict
is True
, StableDiffusionPipelineOutput is returned,
otherwise a tuple
is returned where the first element is a list with the generated images and the
second element is a list of bool
s indicating whether the corresponding generated image contains
“not-safe-for-work” (nsfw) content.
The call function to the pipeline for generation.
Examples:
>>> import torch
>>> from diffusers import StableDiffusionGLIGENPipeline
>>> from diffusers.utils import load_image
>>> # Insert objects described by text at the region defined by bounding boxes
>>> pipe = StableDiffusionGLIGENPipeline.from_pretrained(
... "masterful/gligen-1-4-inpainting-text-box", variant="fp16", torch_dtype=torch.float16
... )
>>> pipe = pipe.to("cuda")
>>> input_image = load_image(
... "https://hf.co/datasets/huggingface/documentation-images/resolve/main/diffusers/gligen/livingroom_modern.png"
... )
>>> prompt = "a birthday cake"
>>> boxes = [[0.2676, 0.6088, 0.4773, 0.7183]]
>>> phrases = ["a birthday cake"]
>>> images = pipe(
... prompt=prompt,
... gligen_phrases=phrases,
... gligen_inpaint_image=input_image,
... gligen_boxes=boxes,
... gligen_scheduled_sampling_beta=1,
... output_type="pil",
... num_inference_steps=50,
... ).images
>>> images[0].save("./gligen-1-4-inpainting-text-box.jpg")
>>> # Generate an image described by the prompt and
>>> # insert objects described by text at the region defined by bounding boxes
>>> pipe = StableDiffusionGLIGENPipeline.from_pretrained(
... "masterful/gligen-1-4-generation-text-box", variant="fp16", torch_dtype=torch.float16
... )
>>> pipe = pipe.to("cuda")
>>> prompt = "a waterfall and a modern high speed train running through the tunnel in a beautiful forest with fall foliage"
>>> boxes = [[0.1387, 0.2051, 0.4277, 0.7090], [0.4980, 0.4355, 0.8516, 0.7266]]
>>> phrases = ["a waterfall", "a modern high speed train running through the tunnel"]
>>> images = pipe(
... prompt=prompt,
... gligen_phrases=phrases,
... gligen_boxes=boxes,
... gligen_scheduled_sampling_beta=1,
... output_type="pil",
... num_inference_steps=50,
... ).images
>>> images[0].save("./gligen-1-4-generation-text-box.jpg")
Enable sliced VAE decoding. When this option is enabled, the VAE will split the input tensor in slices to compute decoding in several steps. This is useful to save some memory and allow larger batch sizes.
Disable sliced VAE decoding. If enable_vae_slicing
was previously enabled, this method will go back to
computing decoding in one step.
Enable tiled VAE decoding. When this option is enabled, the VAE will split the input tensor into tiles to compute decoding and encoding in several steps. This is useful for saving a large amount of memory and to allow processing larger images.
Disable tiled VAE decoding. If enable_vae_tiling
was previously enabled, this method will go back to
computing decoding in one step.
enable_model_cpu_offload
< source >( gpu_id: typing.Optional[int] = None device: typing.Union[torch.device, str] = 'cuda' )
Parameters
- gpu_id (
int
, optional) — The ID of the accelerator that shall be used in inference. If not specified, it will default to 0. - device (
torch.Device
orstr
, optional, defaults to “cuda”) — The PyTorch device type of the accelerator that shall be used in inference. If not specified, it will default to “cuda”.
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
.
prepare_latents
< source >( batch_size num_channels_latents height width dtype device generator latents = None )
encode_prompt
< source >( prompt device num_images_per_prompt do_classifier_free_guidance negative_prompt = None prompt_embeds: typing.Optional[torch.Tensor] = None negative_prompt_embeds: typing.Optional[torch.Tensor] = None lora_scale: typing.Optional[float] = None clip_skip: typing.Optional[int] = None )
Parameters
- prompt (
str
orList[str]
, optional) — prompt to be encoded - device — (
torch.device
): torch device - num_images_per_prompt (
int
) — number of images that should be generated per prompt - do_classifier_free_guidance (
bool
) — whether to use classifier free guidance or not - negative_prompt (
str
orList[str]
, optional) — The prompt or prompts not to guide the image generation. If not defined, one has to passnegative_prompt_embeds
instead. Ignored when not using guidance (i.e., ignored ifguidance_scale
is less than1
). - prompt_embeds (
torch.Tensor
, optional) — Pre-generated text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, text embeddings will be generated fromprompt
input argument. - negative_prompt_embeds (
torch.Tensor
, optional) — Pre-generated negative text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, negative_prompt_embeds will be generated fromnegative_prompt
input argument. - lora_scale (
float
, optional) — A LoRA scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded. - clip_skip (
int
, optional) — Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that the output of the pre-final layer will be used for computing the prompt embeddings.
Encodes the prompt into text encoder hidden states.
StableDiffusionGLIGENTextImagePipeline
class diffusers.StableDiffusionGLIGENTextImagePipeline
< source >( vae: AutoencoderKL text_encoder: CLIPTextModel tokenizer: CLIPTokenizer processor: CLIPProcessor image_encoder: CLIPVisionModelWithProjection image_project: CLIPImageProjection unet: UNet2DConditionModel scheduler: KarrasDiffusionSchedulers safety_checker: StableDiffusionSafetyChecker feature_extractor: CLIPImageProcessor requires_safety_checker: bool = True )
Parameters
- vae (AutoencoderKL) — Variational Auto-Encoder (VAE) model to encode and decode images to and from latent representations.
- text_encoder (CLIPTextModel) — Frozen text-encoder (clip-vit-large-patch14).
- tokenizer (CLIPTokenizer) —
A
CLIPTokenizer
to tokenize text. - processor (CLIPProcessor) —
A
CLIPProcessor
to procces reference image. - image_encoder (CLIPVisionModelWithProjection) — Frozen image-encoder (clip-vit-large-patch14).
- image_project (
CLIPImageProjection
) — ACLIPImageProjection
to project image embedding into phrases embedding space. - unet (UNet2DConditionModel) —
A
UNet2DConditionModel
to denoise the encoded image latents. - scheduler (SchedulerMixin) —
A scheduler to be used in combination with
unet
to denoise the encoded image latents. Can be one of DDIMScheduler, LMSDiscreteScheduler, or PNDMScheduler. - safety_checker (
StableDiffusionSafetyChecker
) — Classification module that estimates whether generated images could be considered offensive or harmful. Please refer to the model card for more details about a model’s potential harms. - feature_extractor (CLIPImageProcessor) —
A
CLIPImageProcessor
to extract features from generated images; used as inputs to thesafety_checker
.
Pipeline for text-to-image generation using Stable Diffusion with Grounded-Language-to-Image Generation (GLIGEN).
This model inherits from DiffusionPipeline. Check the superclass documentation for the generic methods the library implements for all the pipelines (such as downloading or saving, running on a particular device, etc.).
__call__
< source >( prompt: typing.Union[str, typing.List[str]] = None height: typing.Optional[int] = None width: typing.Optional[int] = None num_inference_steps: int = 50 guidance_scale: float = 7.5 gligen_scheduled_sampling_beta: float = 0.3 gligen_phrases: typing.List[str] = None gligen_images: typing.List[PIL.Image.Image] = None input_phrases_mask: typing.Union[int, typing.List[int]] = None input_images_mask: typing.Union[int, typing.List[int]] = None gligen_boxes: typing.List[typing.List[float]] = None gligen_inpaint_image: typing.Optional[PIL.Image.Image] = None 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 latents: typing.Optional[torch.Tensor] = None prompt_embeds: typing.Optional[torch.Tensor] = None negative_prompt_embeds: typing.Optional[torch.Tensor] = None output_type: typing.Optional[str] = 'pil' return_dict: bool = True callback: typing.Optional[typing.Callable[[int, int, torch.Tensor], NoneType]] = None callback_steps: int = 1 cross_attention_kwargs: typing.Optional[typing.Dict[str, typing.Any]] = None gligen_normalize_constant: float = 28.7 clip_skip: int = None ) → StableDiffusionPipelineOutput or tuple
Parameters
- prompt (
str
orList[str]
, optional) — The prompt or prompts to guide image generation. If not defined, you need to passprompt_embeds
. - height (
int
, optional, defaults toself.unet.config.sample_size * self.vae_scale_factor
) — The height in pixels of the generated image. - width (
int
, optional, defaults toself.unet.config.sample_size * self.vae_scale_factor
) — The width in pixels of the generated image. - num_inference_steps (
int
, optional, defaults to 50) — The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference. - guidance_scale (
float
, optional, defaults to 7.5) — A higher guidance scale value encourages the model to generate images closely linked to the textprompt
at the expense of lower image quality. Guidance scale is enabled whenguidance_scale > 1
. - gligen_phrases (
List[str]
) — The phrases to guide what to include in each of the regions defined by the correspondinggligen_boxes
. There should only be one phrase per bounding box. - gligen_images (
List[PIL.Image.Image]
) — The images to guide what to include in each of the regions defined by the correspondinggligen_boxes
. There should only be one image per bounding box - input_phrases_mask (
int
orList[int]
) — pre phrases mask input defined by the correspongdinginput_phrases_mask
- input_images_mask (
int
orList[int]
) — pre images mask input defined by the correspongdinginput_images_mask
- gligen_boxes (
List[List[float]]
) — The bounding boxes that identify rectangular regions of the image that are going to be filled with the content described by the correspondinggligen_phrases
. Each rectangular box is defined as aList[float]
of 4 elements[xmin, ymin, xmax, ymax]
where each value is between [0,1]. - gligen_inpaint_image (
PIL.Image.Image
, optional) — The input image, if provided, is inpainted with objects described by thegligen_boxes
andgligen_phrases
. Otherwise, it is treated as a generation task on a blank input image. - gligen_scheduled_sampling_beta (
float
, defaults to 0.3) — Scheduled Sampling factor from GLIGEN: Open-Set Grounded Text-to-Image Generation. Scheduled Sampling factor is only varied for scheduled sampling during inference for improved quality and controllability. - negative_prompt (
str
orList[str]
, optional) — The prompt or prompts to guide what to not include in image generation. If not defined, you need to passnegative_prompt_embeds
instead. Ignored when not using guidance (guidance_scale < 1
). - num_images_per_prompt (
int
, optional, defaults to 1) — The number of images to generate per prompt. - eta (
float
, optional, defaults to 0.0) — Corresponds to parameter eta (η) from the DDIM paper. Only applies to the DDIMScheduler, and is ignored in other schedulers. - generator (
torch.Generator
orList[torch.Generator]
, optional) — Atorch.Generator
to make generation deterministic. - latents (
torch.Tensor
, optional) — Pre-generated noisy latents sampled from a Gaussian distribution, to be used as inputs for image generation. Can be used to tweak the same generation with different prompts. If not provided, a latents tensor is generated by sampling using the supplied randomgenerator
. - prompt_embeds (
torch.Tensor
, optional) — Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not provided, text embeddings are generated from theprompt
input argument. - negative_prompt_embeds (
torch.Tensor
, optional) — Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not provided,negative_prompt_embeds
are generated from thenegative_prompt
input argument. - output_type (
str
, optional, defaults to"pil"
) — The output format of the generated image. Choose betweenPIL.Image
ornp.array
. - return_dict (
bool
, optional, defaults toTrue
) — Whether or not to return a StableDiffusionPipelineOutput instead of a plain tuple. - callback (
Callable
, optional) — A function that calls everycallback_steps
steps during inference. The function is called with the following arguments:callback(step: int, timestep: int, latents: torch.Tensor)
. - callback_steps (
int
, optional, defaults to 1) — The frequency at which thecallback
function is called. If not specified, the callback is called at every step. - cross_attention_kwargs (
dict
, optional) — A kwargs dictionary that if specified is passed along to theAttentionProcessor
as defined inself.processor
. - gligen_normalize_constant (
float
, optional, defaults to 28.7) — The normalize value of the image embedding. - clip_skip (
int
, optional) — Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that the output of the pre-final layer will be used for computing the prompt embeddings.
Returns
StableDiffusionPipelineOutput or tuple
If return_dict
is True
, StableDiffusionPipelineOutput is returned,
otherwise a tuple
is returned where the first element is a list with the generated images and the
second element is a list of bool
s indicating whether the corresponding generated image contains
“not-safe-for-work” (nsfw) content.
The call function to the pipeline for generation.
Examples:
>>> import torch
>>> from diffusers import StableDiffusionGLIGENTextImagePipeline
>>> from diffusers.utils import load_image
>>> # Insert objects described by image at the region defined by bounding boxes
>>> pipe = StableDiffusionGLIGENTextImagePipeline.from_pretrained(
... "anhnct/Gligen_Inpainting_Text_Image", torch_dtype=torch.float16
... )
>>> pipe = pipe.to("cuda")
>>> input_image = load_image(
... "https://hf.co/datasets/huggingface/documentation-images/resolve/main/diffusers/gligen/livingroom_modern.png"
... )
>>> prompt = "a backpack"
>>> boxes = [[0.2676, 0.4088, 0.4773, 0.7183]]
>>> phrases = None
>>> gligen_image = load_image(
... "https://huggingface.co./datasets/huggingface/documentation-images/resolve/main/diffusers/gligen/backpack.jpeg"
... )
>>> images = pipe(
... prompt=prompt,
... gligen_phrases=phrases,
... gligen_inpaint_image=input_image,
... gligen_boxes=boxes,
... gligen_images=[gligen_image],
... gligen_scheduled_sampling_beta=1,
... output_type="pil",
... num_inference_steps=50,
... ).images
>>> images[0].save("./gligen-inpainting-text-image-box.jpg")
>>> # Generate an image described by the prompt and
>>> # insert objects described by text and image at the region defined by bounding boxes
>>> pipe = StableDiffusionGLIGENTextImagePipeline.from_pretrained(
... "anhnct/Gligen_Text_Image", torch_dtype=torch.float16
... )
>>> pipe = pipe.to("cuda")
>>> prompt = "a flower sitting on the beach"
>>> boxes = [[0.0, 0.09, 0.53, 0.76]]
>>> phrases = ["flower"]
>>> gligen_image = load_image(
... "https://huggingface.co./datasets/huggingface/documentation-images/resolve/main/diffusers/gligen/pexels-pixabay-60597.jpg"
... )
>>> images = pipe(
... prompt=prompt,
... gligen_phrases=phrases,
... gligen_images=[gligen_image],
... gligen_boxes=boxes,
... gligen_scheduled_sampling_beta=1,
... output_type="pil",
... num_inference_steps=50,
... ).images
>>> images[0].save("./gligen-generation-text-image-box.jpg")
>>> # Generate an image described by the prompt and
>>> # transfer style described by image at the region defined by bounding boxes
>>> pipe = StableDiffusionGLIGENTextImagePipeline.from_pretrained(
... "anhnct/Gligen_Text_Image", torch_dtype=torch.float16
... )
>>> pipe = pipe.to("cuda")
>>> prompt = "a dragon flying on the sky"
>>> boxes = [[0.4, 0.2, 1.0, 0.8], [0.0, 1.0, 0.0, 1.0]] # Set `[0.0, 1.0, 0.0, 1.0]` for the style
>>> gligen_image = load_image(
... "https://huggingface.co./datasets/huggingface/documentation-images/resolve/main/diffusers/landscape.png"
... )
>>> gligen_placeholder = load_image(
... "https://huggingface.co./datasets/huggingface/documentation-images/resolve/main/diffusers/landscape.png"
... )
>>> images = pipe(
... prompt=prompt,
... gligen_phrases=[
... "dragon",
... "placeholder",
... ], # Can use any text instead of `placeholder` token, because we will use mask here
... gligen_images=[
... gligen_placeholder,
... gligen_image,
... ], # Can use any image in gligen_placeholder, because we will use mask here
... input_phrases_mask=[1, 0], # Set 0 for the placeholder token
... input_images_mask=[0, 1], # Set 0 for the placeholder image
... gligen_boxes=boxes,
... gligen_scheduled_sampling_beta=1,
... output_type="pil",
... num_inference_steps=50,
... ).images
>>> images[0].save("./gligen-generation-text-image-box-style-transfer.jpg")
Enable sliced VAE decoding. When this option is enabled, the VAE will split the input tensor in slices to compute decoding in several steps. This is useful to save some memory and allow larger batch sizes.
Disable sliced VAE decoding. If enable_vae_slicing
was previously enabled, this method will go back to
computing decoding in one step.
Enable tiled VAE decoding. When this option is enabled, the VAE will split the input tensor into tiles to compute decoding and encoding in several steps. This is useful for saving a large amount of memory and to allow processing larger images.
Disable tiled VAE decoding. If enable_vae_tiling
was previously enabled, this method will go back to
computing decoding in one step.
enable_model_cpu_offload
< source >( gpu_id: typing.Optional[int] = None device: typing.Union[torch.device, str] = 'cuda' )
Parameters
- gpu_id (
int
, optional) — The ID of the accelerator that shall be used in inference. If not specified, it will default to 0. - device (
torch.Device
orstr
, optional, defaults to “cuda”) — The PyTorch device type of the accelerator that shall be used in inference. If not specified, it will default to “cuda”.
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
.
prepare_latents
< source >( batch_size num_channels_latents height width dtype device generator latents = None )
Based on the input mask corresponding value 0 or 1
for each phrases and image, mask the features
corresponding to phrases and images.
Crop the input image to the specified dimensions.
Create an inpainting mask based on given boxes. This function generates an inpainting mask using the provided boxes to mark regions that need to be inpainted.
encode_prompt
< source >( prompt device num_images_per_prompt do_classifier_free_guidance negative_prompt = None prompt_embeds: typing.Optional[torch.Tensor] = None negative_prompt_embeds: typing.Optional[torch.Tensor] = None lora_scale: typing.Optional[float] = None clip_skip: typing.Optional[int] = None )
Parameters
- prompt (
str
orList[str]
, optional) — prompt to be encoded - device — (
torch.device
): torch device - num_images_per_prompt (
int
) — number of images that should be generated per prompt - do_classifier_free_guidance (
bool
) — whether to use classifier free guidance or not - negative_prompt (
str
orList[str]
, optional) — The prompt or prompts not to guide the image generation. If not defined, one has to passnegative_prompt_embeds
instead. Ignored when not using guidance (i.e., ignored ifguidance_scale
is less than1
). - prompt_embeds (
torch.Tensor
, optional) — Pre-generated text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, text embeddings will be generated fromprompt
input argument. - negative_prompt_embeds (
torch.Tensor
, optional) — Pre-generated negative text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, negative_prompt_embeds will be generated fromnegative_prompt
input argument. - lora_scale (
float
, optional) — A LoRA scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded. - clip_skip (
int
, optional) — Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that the output of the pre-final layer will be used for computing the prompt embeddings.
Encodes the prompt into text encoder hidden states.
Get image and phrases embedding by using CLIP pretrain model. The image embedding is transformed into the phrases embedding space through a projection.
get_cross_attention_kwargs_with_grounded
< source >( hidden_size gligen_phrases gligen_images gligen_boxes input_phrases_mask input_images_mask repeat_batch normalize_constant max_objs device )
Prepare the cross-attention kwargs containing information about the grounded input (boxes, mask, image embedding, phrases embedding).
Prepare the cross-attention kwargs without information about the grounded input (boxes, mask, image embedding, phrases embedding) (All are zero tensor).
Crop and resize the image to the target size while keeping the center.
StableDiffusionPipelineOutput
class diffusers.pipelines.stable_diffusion.StableDiffusionPipelineOutput
< source >( images: typing.Union[typing.List[PIL.Image.Image], numpy.ndarray] nsfw_content_detected: typing.Optional[typing.List[bool]] )
Parameters
- images (
List[PIL.Image.Image]
ornp.ndarray
) — List of denoised PIL images of lengthbatch_size
or NumPy array of shape(batch_size, height, width, num_channels)
. - nsfw_content_detected (
List[bool]
) — List indicating whether the corresponding generated image contains “not-safe-for-work” (nsfw) content orNone
if safety checking could not be performed.
Output class for Stable Diffusion pipelines.