Stable Diffusion T2I-adapter
Last updated
Last updated
by Chong Mou, Xintao Wang, Liangbin Xie, Jian Zhang, Zhongang Qi, Ying Shan, Xiaohu Qie.
Using the pretrained models we can provide control images (for example, a depth map) to control Stable Diffusion text-to-image generation so that it follows the structure of the depth image and fills in the details.
The abstract of the paper is the following:
The incredible generative ability of large-scale text-to-image (T2I) models has demonstrated strong power of learning complex structures and meaningful semantics. However, relying solely on text prompts cannot fully take advantage of the knowledge learned by the model, especially when flexible and accurate structure control is needed. In this paper, we aim to “dig out” the capabilities that T2I models have implicitly learned, and then explicitly use them to control the generation more granularly. Specifically, we propose to learn simple and small T2I-Adapters to align internal knowledge in T2I models with external control signals, while freezing the original large T2I models. In this way, we can train various adapters according to different conditions, and achieve rich control and editing effects. Further, the proposed T2I-Adapters have attractive properties of practical value, such as composability and generalization ability. Extensive experiments demonstrate that our T2I-Adapter has promising generation quality and a wide range of applications.
This model was contributed by the community contributor ❤️ .
Text-to-Image Generation with T2I-Adapter Conditioning
-
Text-to-Image Generation with T2I-Adapter Conditioning on StableDiffusion-XL
-
In the following we give a simple example of how to use a T2IAdapter checkpoint with Diffusers for inference based on StableDiffusion-1.4/1.5. All adapters use the same pipeline.
Images are first converted into the appropriate control image format.
The control image and prompt are passed to the .
Let’s have a look at a simple example using the .
Copied
Then we can create our color palette by simply resizing it to 8 by 8 pixels and then scaling it back to original size.
Copied
Let’s take a look at the processed image.
Next, create the adapter pipeline
Copied
Finally, pass the prompt and control image to the pipeline
Copied
In the following we give a simple example of how to use a T2IAdapter checkpoint with Diffusers for inference based on StableDiffusion-XL. All adapters use the same pipeline.
Images are first downloaded into the appropriate control image format.
Copied
Then, create the adapter pipeline
Copied
Finally, pass the prompt and control image to the pipeline
Copied
A image with 8x8 color palette.
A monochrome image with white edges on a black background.
A hand-drawn monochrome image with white outlines on a black background.
A grayscale image with black representing deep areas and white representing shallow areas.
MultiAdapter can be used for applying multiple conditionings at once.
Here we use the keypose adapter for the character posture and the depth adapter for creating the scene.
Copied
The two control images look as such:
MultiAdapter combines keypose and depth adapters.
adapter_conditioning_scale balances the relative influence of the different adapters.
Copied
( vae: AutoencoderKLtext_encoder: CLIPTextModeltokenizer: CLIPTokenizerunet: UNet2DConditionModeladapter: typing.Union[diffusers.models.adapter.T2IAdapter, diffusers.models.adapter.MultiAdapter, typing.List[diffusers.models.adapter.T2IAdapter]]scheduler: KarrasDiffusionSchedulerssafety_checker: StableDiffusionSafetyCheckerfeature_extractor: CLIPFeatureExtractoradapter_weights: typing.Optional[typing.List[float]] = Nonerequires_safety_checker: bool = True )
Parameters
adapter (T2IAdapter or MultiAdapter or List[T2IAdapter]) — Provides additional conditioning to the unet during the denoising process. If you set multiple Adapter as a list, the outputs from each Adapter are added together to create one combined additional conditioning.
adapter_weights (List[float], optional, defaults to None) — List of floats representing the weight which will be multiply to each adapter’s output before adding them together.
feature_extractor (CLIPFeatureExtractor) — Model that extracts features from generated images to be used as inputs for the safety_checker.
__call__
( prompt: typing.Union[str, typing.List[str]] = Noneimage: typing.Union[torch.Tensor, PIL.Image.Image, typing.List[PIL.Image.Image]] = Noneheight: typing.Optional[int] = Nonewidth: typing.Optional[int] = Nonenum_inference_steps: int = 50guidance_scale: float = 7.5negative_prompt: typing.Union[str, typing.List[str], NoneType] = Nonenum_images_per_prompt: typing.Optional[int] = 1eta: float = 0.0generator: typing.Union[torch._C.Generator, typing.List[torch._C.Generator], NoneType] = Nonelatents: typing.Optional[torch.FloatTensor] = Noneprompt_embeds: typing.Optional[torch.FloatTensor] = Nonenegative_prompt_embeds: typing.Optional[torch.FloatTensor] = Noneoutput_type: typing.Optional[str] = 'pil'return_dict: bool = Truecallback: typing.Union[typing.Callable[[int, int, torch.FloatTensor], NoneType], NoneType] = Nonecallback_steps: int = 1cross_attention_kwargs: typing.Union[typing.Dict[str, typing.Any], NoneType] = Noneadapter_conditioning_scale: typing.Union[float, typing.List[float]] = 1.0 ) → ~pipelines.stable_diffusion.StableDiffusionAdapterPipelineOutput 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, PIL.Image.Image, List[torch.FloatTensor] or List[PIL.Image.Image] or List[List[PIL.Image.Image]]) — The Adapter input condition. Adapter uses this input condition to generate guidance to Unet. If the type is specified as Torch.FloatTensor, it is passed to Adapter as is. PIL.Image.Image` can also be accepted as an image. The control image is automatically resized to fit the output image.
height (int, optional, defaults to self.unet.config.sample_size * self.vae_scale_factor) — The height in pixels of the generated image.
width (int, optional, defaults to self.unet.config.sample_size * self.vae_scale_factor) — The width in pixels of the generated image.
num_inference_steps (int, optional, defaults to 50) — The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference.
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).
num_images_per_prompt (int, optional, defaults to 1) — The number of images to generate per prompt.
latents (torch.FloatTensor, optional) — Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image generation. Can be used to tweak the same generation with different prompts. If not provided, a latents tensor will ge generated by sampling using the supplied random generator.
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.
return_dict (bool, optional, defaults to True) — Whether or not to return a ~pipelines.stable_diffusion.StableDiffusionAdapterPipelineOutput 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.
adapter_conditioning_scale (float or List[float], optional, defaults to 1.0) — The outputs of the adapter are multiplied by adapter_conditioning_scale before they are added to the residual in the original unet. If multiple adapters are specified in init, you can set the corresponding scale as a list.
Returns
~pipelines.stable_diffusion.StableDiffusionAdapterPipelineOutput or tuple
~pipelines.stable_diffusion.StableDiffusionAdapterPipelineOutput 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) content, according to the safety_checker`.
Function invoked when calling the pipeline for generation.
Examples:
Copied
enable_attention_slicing
( slice_size: typing.Union[str, int, NoneType] = 'auto' )
Parameters
slice_size (str or int, optional, defaults to "auto") — When "auto", halves the input to the attention heads, so attention will be computed in two steps. If "max", maximum amount of memory will be saved by running only one slice at a time. If a number is provided, uses as many slices as attention_head_dim // slice_size. In this case, attention_head_dim must be a multiple of slice_size.
Enable sliced attention computation. When this option is enabled, the attention module splits the input tensor in slices to compute attention in several steps. For more than one attention head, the computation is performed sequentially over each head. This is useful to save some memory in exchange for a small speed decrease.
⚠️ Don’t enable attention slicing if you’re already using scaled_dot_product_attention (SDPA) from PyTorch 2.0 or xFormers. These attention computations are already very memory efficient so you won’t need to enable this function. If you enable attention slicing with SDPA or xFormers, it can lead to serious slow downs!
Examples:
Copied
disable_attention_slicing
( )
Disable sliced attention computation. If enable_attention_slicing was previously called, attention is computed in one step.
enable_vae_slicing
( )
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_vae_slicing
( )
Disable sliced VAE decoding. If enable_vae_slicing was previously enabled, this method will go back to computing decoding in one step.
enable_xformers_memory_efficient_attention
( attention_op: typing.Optional[typing.Callable] = None )
Parameters
⚠️ When memory efficient attention and sliced attention are both enabled, memory efficient attention takes precedent.
Examples:
Copied
disable_xformers_memory_efficient_attention
( )
encode_prompt
( promptdevicenum_images_per_promptdo_classifier_free_guidancenegative_prompt = Noneprompt_embeds: typing.Optional[torch.FloatTensor] = Nonenegative_prompt_embeds: typing.Optional[torch.FloatTensor] = Nonelora_scale: typing.Optional[float] = None )
Parameters
prompt (str or List[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 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).
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.
lora_scale (float, optional) — A lora scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded.
Encodes the prompt into text encoder hidden states.
( vae: AutoencoderKLtext_encoder: CLIPTextModeltext_encoder_2: CLIPTextModelWithProjectiontokenizer: CLIPTokenizertokenizer_2: CLIPTokenizerunet: UNet2DConditionModeladapter: typing.Union[diffusers.models.adapter.T2IAdapter, diffusers.models.adapter.MultiAdapter, typing.List[diffusers.models.adapter.T2IAdapter]]scheduler: KarrasDiffusionSchedulersforce_zeros_for_empty_prompt: bool = True )
Parameters
adapter (T2IAdapter or MultiAdapter or List[T2IAdapter]) — Provides additional conditioning to the unet during the denoising process. If you set multiple Adapter as a list, the outputs from each Adapter are added together to create one combined additional conditioning.
adapter_weights (List[float], optional, defaults to None) — List of floats representing the weight which will be multiply to each adapter’s output before adding them together.
feature_extractor (CLIPFeatureExtractor) — Model that extracts features from generated images to be used as inputs for the safety_checker.
__call__
( prompt: typing.Union[str, typing.List[str]] = Noneprompt_2: typing.Union[str, typing.List[str], NoneType] = Noneimage: typing.Union[torch.Tensor, PIL.Image.Image, typing.List[PIL.Image.Image]] = Noneheight: typing.Optional[int] = Nonewidth: typing.Optional[int] = Nonenum_inference_steps: int = 50denoising_end: typing.Optional[float] = Noneguidance_scale: float = 5.0negative_prompt: typing.Union[str, typing.List[str], NoneType] = Nonenegative_prompt_2: typing.Union[str, typing.List[str], NoneType] = Nonenum_images_per_prompt: typing.Optional[int] = 1eta: float = 0.0generator: typing.Union[torch._C.Generator, typing.List[torch._C.Generator], NoneType] = Nonelatents: typing.Optional[torch.FloatTensor] = Noneprompt_embeds: typing.Optional[torch.FloatTensor] = Nonenegative_prompt_embeds: typing.Optional[torch.FloatTensor] = Nonepooled_prompt_embeds: typing.Optional[torch.FloatTensor] = Nonenegative_pooled_prompt_embeds: typing.Optional[torch.FloatTensor] = Noneoutput_type: typing.Optional[str] = 'pil'return_dict: bool = Truecallback: typing.Union[typing.Callable[[int, int, torch.FloatTensor], NoneType], NoneType] = Nonecallback_steps: int = 1cross_attention_kwargs: typing.Union[typing.Dict[str, typing.Any], NoneType] = Noneguidance_rescale: float = 0.0original_size: typing.Union[typing.Tuple[int, int], NoneType] = Nonecrops_coords_top_left: typing.Tuple[int, int] = (0, 0)target_size: typing.Union[typing.Tuple[int, int], NoneType] = Nonenegative_original_size: typing.Union[typing.Tuple[int, int], NoneType] = Nonenegative_crops_coords_top_left: typing.Tuple[int, int] = (0, 0)negative_target_size: typing.Union[typing.Tuple[int, int], NoneType] = Noneadapter_conditioning_scale: typing.Union[float, typing.List[float]] = 1.0adapter_conditioning_factor: float = 1.0 ) → ~pipelines.stable_diffusion.StableDiffusionAdapterPipelineOutput 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.
prompt_2 (str or List[str], optional) — The prompt or prompts to be sent to the tokenizer_2 and text_encoder_2. If not defined, prompt is used in both text-encoders
image (torch.FloatTensor, PIL.Image.Image, List[torch.FloatTensor] or List[PIL.Image.Image] or List[List[PIL.Image.Image]]) — The Adapter input condition. Adapter uses this input condition to generate guidance to Unet. If the type is specified as Torch.FloatTensor, it is passed to Adapter as is. PIL.Image.Image` can also be accepted as an image. The control image is automatically resized to fit the output 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.
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).
negative_prompt_2 (str or List[str], optional) — The prompt or prompts not to guide the image generation to be sent to tokenizer_2 and text_encoder_2. If not defined, negative_prompt is used in both text-encoders
num_images_per_prompt (int, optional, defaults to 1) — The number of images to generate per prompt.
latents (torch.FloatTensor, optional) — Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image generation. Can be used to tweak the same generation with different prompts. If not provided, a latents tensor will ge generated by sampling using the supplied random generator.
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.
pooled_prompt_embeds (torch.FloatTensor, optional) — Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, pooled text embeddings will be generated from prompt input argument.
negative_pooled_prompt_embeds (torch.FloatTensor, optional) — Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, pooled negative_prompt_embeds will be generated from negative_prompt input argument.
return_dict (bool, optional, defaults to True) — Whether or not to return a ~pipelines.stable_diffusion_xl.StableDiffusionAdapterPipelineOutput 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.
adapter_conditioning_scale (float or List[float], optional, defaults to 1.0) — The outputs of the adapter are multiplied by adapter_conditioning_scale before they are added to the residual in the original unet. If multiple adapters are specified in init, you can set the corresponding scale as a list.
adapter_conditioning_factor (float, optional, defaults to 1.0) — The fraction of timesteps for which adapter should be applied. If adapter_conditioning_factor is 0.0, adapter is not applied at all. If adapter_conditioning_factor is 1.0, adapter is applied for all timesteps. If adapter_conditioning_factor is 0.5, adapter is applied for half of the timesteps.
Returns
~pipelines.stable_diffusion.StableDiffusionAdapterPipelineOutput or tuple
~pipelines.stable_diffusion.StableDiffusionAdapterPipelineOutput if return_dict is True, otherwise a tuple. When returning a tuple, the first element is a list with the generated images.
Function invoked when calling the pipeline for generation.
Examples:
Copied
enable_attention_slicing
( slice_size: typing.Union[str, int, NoneType] = 'auto' )
Parameters
slice_size (str or int, optional, defaults to "auto") — When "auto", halves the input to the attention heads, so attention will be computed in two steps. If "max", maximum amount of memory will be saved by running only one slice at a time. If a number is provided, uses as many slices as attention_head_dim // slice_size. In this case, attention_head_dim must be a multiple of slice_size.
Enable sliced attention computation. When this option is enabled, the attention module splits the input tensor in slices to compute attention in several steps. For more than one attention head, the computation is performed sequentially over each head. This is useful to save some memory in exchange for a small speed decrease.
⚠️ Don’t enable attention slicing if you’re already using scaled_dot_product_attention (SDPA) from PyTorch 2.0 or xFormers. These attention computations are already very memory efficient so you won’t need to enable this function. If you enable attention slicing with SDPA or xFormers, it can lead to serious slow downs!
Examples:
Copied
disable_attention_slicing
( )
Disable sliced attention computation. If enable_attention_slicing was previously called, attention is computed in one step.
enable_vae_slicing
( )
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_vae_slicing
( )
Disable sliced VAE decoding. If enable_vae_slicing was previously enabled, this method will go back to computing decoding in one step.
enable_xformers_memory_efficient_attention
( attention_op: typing.Optional[typing.Callable] = None )
Parameters
⚠️ When memory efficient attention and sliced attention are both enabled, memory efficient attention takes precedent.
Examples:
Copied
disable_xformers_memory_efficient_attention
( )
disable_vae_tiling
( )
Disable tiled VAE decoding. If enable_vae_tiling was previously enabled, this method will go back to computing decoding in one step.
enable_vae_tiling
( )
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.
encode_prompt
( prompt: strprompt_2: typing.Optional[str] = Nonedevice: typing.Optional[torch.device] = Nonenum_images_per_prompt: int = 1do_classifier_free_guidance: bool = Truenegative_prompt: typing.Optional[str] = Nonenegative_prompt_2: typing.Optional[str] = Noneprompt_embeds: typing.Optional[torch.FloatTensor] = Nonenegative_prompt_embeds: typing.Optional[torch.FloatTensor] = Nonepooled_prompt_embeds: typing.Optional[torch.FloatTensor] = Nonenegative_pooled_prompt_embeds: typing.Optional[torch.FloatTensor] = Nonelora_scale: typing.Optional[float] = None )
Parameters
prompt (str or List[str], optional) — prompt to be encoded
prompt_2 (str or List[str], optional) — The prompt or prompts to be sent to the tokenizer_2 and text_encoder_2. If not defined, prompt is used in both text-encoders 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 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).
negative_prompt_2 (str or List[str], optional) — The prompt or prompts not to guide the image generation to be sent to tokenizer_2 and text_encoder_2. If not defined, negative_prompt is used in both text-encoders
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.
pooled_prompt_embeds (torch.FloatTensor, optional) — Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, pooled text embeddings will be generated from prompt input argument.
negative_pooled_prompt_embeds (torch.FloatTensor, optional) — Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, pooled negative_prompt_embeds will be generated from negative_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.
Encodes the prompt into text encoder hidden states.
The control image and prompt are passed to the .
Let’s have a look at a simple example using the .
Non-diffusers checkpoints can be found under .
Trained with spatial color palette
Trained with canny edge detection
Trained with edge detection
Trained with Midas depth estimation
Trained with OpenPose bone image
A image.
Trained with mmpose skeleton image
A image.
Trained with semantic segmentation
An segmentation protocol image.
T2I-Adapter is similar to . T2i-Adapter uses a smaller auxiliary network which is only run once for the entire diffusion process. However, T2I-Adapter performs slightly worse than ControlNet.
vae () — Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.
text_encoder (CLIPTextModel) — Frozen text-encoder. Stable Diffusion uses the text portion of , specifically the variant.
tokenizer (CLIPTokenizer) — Tokenizer of class .
unet () — Conditional U-Net architecture to denoise the encoded image latents.
scheduler () — A scheduler to be used in combination with unet to denoise the encoded image latents. Can be one of , , or .
safety_checker (StableDiffusionSafetyChecker) — Classification module that estimates whether generated images could be considered offensive or harmful. Please, refer to the for details.
Pipeline for text-to-image generation using Stable Diffusion augmented with T2I-Adapter
This model inherits from . 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.)
guidance_scale (float, optional, defaults to 7.5) — Guidance scale as defined in . guidance_scale is defined as w of equation 2. of . 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.
eta (float, optional, defaults to 0.0) — Corresponds to parameter eta (η) in the DDIM paper: . Only applies to , will be ignored for others.
generator (torch.Generator or List[torch.Generator], optional) — One or a list of to make generation deterministic.
output_type (str, optional, defaults to "pil") — The output format of the generate image. Choose between : PIL.Image.Image or np.array.
cross_attention_kwargs (dict, optional) — A kwargs dictionary that if specified is passed along to the AttnProcessor as defined under self.processor in .
attention_op (Callable, optional) — Override the default None operator for use as op argument to the function of xFormers.
Enable memory efficient attention from . When this option is enabled, you should observe lower GPU memory usage and a potential speed up during inference. Speed up during training is not guaranteed.
Disable memory efficient attention from .
vae () — Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.
text_encoder (CLIPTextModel) — Frozen text-encoder. Stable Diffusion uses the text portion of , specifically the variant.
tokenizer (CLIPTokenizer) — Tokenizer of class .
unet () — Conditional U-Net architecture to denoise the encoded image latents.
scheduler () — A scheduler to be used in combination with unet to denoise the encoded image latents. Can be one of , , or .
safety_checker (StableDiffusionSafetyChecker) — Classification module that estimates whether generated images could be considered offensive or harmful. Please, refer to the for details.
Pipeline for text-to-image generation using Stable Diffusion augmented with T2I-Adapter
This model inherits from . 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.)
height (int, optional, defaults to self.unet.config.sample_size * self.vae_scale_factor) — The height in pixels of the generated image. Anything below 512 pixels won’t work well for and checkpoints that are not specifically fine-tuned on low resolutions.
width (int, optional, defaults to self.unet.config.sample_size * self.vae_scale_factor) — The width in pixels of the generated image. Anything below 512 pixels won’t work well for and checkpoints that are not specifically fine-tuned on low resolutions.
denoising_end (float, optional) — When specified, determines the fraction (between 0.0 and 1.0) of the total denoising process to be completed before it is intentionally prematurely terminated. As a result, the returned sample will still retain a substantial amount of noise as determined by the discrete timesteps selected by the scheduler. The denoising_end parameter should ideally be utilized when this pipeline forms a part of a “Mixture of Denoisers” multi-pipeline setup, as elaborated in
guidance_scale (float, optional, defaults to 5.0) — Guidance scale as defined in . guidance_scale is defined as w of equation 2. of . 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.
eta (float, optional, defaults to 0.0) — Corresponds to parameter eta (η) in the DDIM paper: . Only applies to , will be ignored for others.
generator (torch.Generator or List[torch.Generator], optional) — One or a list of to make generation deterministic.
output_type (str, optional, defaults to "pil") — The output format of the generate image. Choose between : PIL.Image.Image or np.array.
cross_attention_kwargs (dict, optional) — A kwargs dictionary that if specified is passed along to the AttentionProcessor as defined under self.processor in .
guidance_rescale (float, optional, defaults to 0.7) — Guidance rescale factor proposed by guidance_scale is defined as φ in equation 16. of . Guidance rescale factor should fix overexposure when using zero terminal SNR.
original_size (Tuple[int], optional, defaults to (1024, 1024)) — If original_size is not the same as target_size the image will appear to be down- or upsampled. original_size defaults to (width, height) if not specified. Part of SDXL’s micro-conditioning as explained in section 2.2 of .
crops_coords_top_left (Tuple[int], optional, defaults to (0, 0)) — crops_coords_top_left can be used to generate an image that appears to be “cropped” from the position crops_coords_top_left downwards. Favorable, well-centered images are usually achieved by setting crops_coords_top_left to (0, 0). Part of SDXL’s micro-conditioning as explained in section 2.2 of .
target_size (Tuple[int], optional, defaults to (1024, 1024)) — For most cases, target_size should be set to the desired height and width of the generated image. If not specified it will default to (width, height). Part of SDXL’s micro-conditioning as explained in section 2.2 of . section 2.2 of .
negative_original_size (Tuple[int], optional, defaults to (1024, 1024)) — To negatively condition the generation process based on a specific image resolution. Part of SDXL’s micro-conditioning as explained in section 2.2 of . For more information, refer to this issue thread: .
negative_crops_coords_top_left (Tuple[int], optional, defaults to (0, 0)) — To negatively condition the generation process based on a specific crop coordinates. Part of SDXL’s micro-conditioning as explained in section 2.2 of . For more information, refer to this issue thread: .
negative_target_size (Tuple[int], optional, defaults to (1024, 1024)) — To negatively condition the generation process based on a target image resolution. It should be as same as the target_size for most cases. Part of SDXL’s micro-conditioning as explained in section 2.2 of . For more information, refer to this issue thread: .
attention_op (Callable, optional) — Override the default None operator for use as op argument to the function of xFormers.
Enable memory efficient attention from . When this option is enabled, you should observe lower GPU memory usage and a potential speed up during inference. Speed up during training is not guaranteed.
Disable memory efficient attention from .
