Stable Diffusion XL ControlNet¶

The prompt or prompts to guide image generation. If not defined, you need to pass prompt_embeds.

The prompt or prompts to be sent to tokenizer_2 and text_encoder_2. If not defined, prompt is used in both text-encoders.

The ControlNet input condition to provide guidance to the unet for generation. If the type is specified as torch.FloatTensor, it is passed to ControlNet as is. PIL.Image.Image can also be accepted as an image. The dimensions of the output image defaults to image's dimensions. If height and/or width are passed, image is resized accordingly. If multiple ControlNets are specified in init, images must be passed as a list such that each element of the list can be correctly batched for input to a single ControlNet.

The height in pixels of the generated image. Anything below 512 pixels won't work well for stabilityai/stable-diffusion-xl-base-1.0 and checkpoints that are not specifically fine-tuned on low resolutions.

The width in pixels of the generated image. Anything below 512 pixels won't work well for stabilityai/stable-diffusion-xl-base-1.0 and checkpoints that are not specifically fine-tuned on low resolutions.

The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference.

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 Refining the Image Output

A higher guidance scale value encourages the model to generate images closely linked to the text prompt at the expense of lower image quality. Guidance scale is enabled when guidance_scale > 1.

The prompt or prompts to guide what to not include in image generation. If not defined, you need to pass negative_prompt_embeds instead. Ignored when not using guidance (guidance_scale < 1).

The prompt or prompts to guide what to not include in image generation. This is sent to tokenizer_2 and text_encoder_2. If not defined, negative_prompt is used in both text-encoders.

The number of images to generate per prompt.

Corresponds to parameter eta (η) from the DDIM paper. Only applies to the [~schedulers.DDIMScheduler], and is ignored in other schedulers.

A torch.Generator to make generation deterministic.

Pre-generated noisy latents sampled from a Gaussian distribution, to be used as inputs for image generation. Can be used to tweak the same generation with different prompts. If not provided, a latents tensor is generated by sampling using the supplied random generator.

Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not provided, text embeddings are generated from the prompt input argument.

Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not provided, negative_prompt_embeds are generated from the negative_prompt input argument.

Pre-generated pooled text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not provided, pooled text embeddings are generated from prompt input argument.

Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not provided, pooled negative_prompt_embeds are generated from negative_prompt input argument.

(PipelineImageInput, optional): Optional image input to work with IP Adapters.

Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of IP-adapters. Each element should be a tensor of shape (batch_size, num_images, emb_dim). It should contain the negative image embedding if do_classifier_free_guidance is set to True. If not provided, embeddings are computed from the ip_adapter_image input argument.

The output format of the generated image. Choose between PIL.Image or np.array.

Whether or not to return a [~pipelines.stable_diffusion.StableDiffusionPipelineOutput] instead of a plain tuple.

A kwargs dictionary that if specified is passed along to the [AttentionProcessor] as defined in self.processor.

The outputs of the ControlNet are multiplied by controlnet_conditioning_scale before they are added to the residual in the original unet. If multiple ControlNets are specified in init, you can set the corresponding scale as a list.

The ControlNet encoder tries to recognize the content of the input image even if you remove all prompts. A guidance_scale value between 3.0 and 5.0 is recommended.

The percentage of total steps at which the ControlNet starts applying.

The percentage of total steps at which the ControlNet stops applying.

If original_size is not the same as target_size the image will appear to be down- or upsampled. original_size defaults to (height, width) if not specified. Part of SDXL's micro-conditioning as explained in section 2.2 of https://huggingface.co/papers/2307.01952.

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 https://huggingface.co/papers/2307.01952.

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 (height, width). Part of SDXL's micro-conditioning as explained in section 2.2 of https://huggingface.co/papers/2307.01952.

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 https://huggingface.co/papers/2307.01952. For more information, refer to this issue thread: https://github.com/huggingface/diffusers/issues/4208.

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 https://huggingface.co/papers/2307.01952. For more information, refer to this issue thread: https://github.com/huggingface/diffusers/issues/4208.

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 https://huggingface.co/papers/2307.01952. For more information, refer to this issue thread: https://github.com/huggingface/diffusers/issues/4208.

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.

A function that calls at the end of each denoising steps during the inference. The function is called with the following arguments: callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int, callback_kwargs: Dict). callback_kwargs will include a list of all tensors as specified by callback_on_step_end_tensor_inputs.

The list of tensor inputs for the callback_on_step_end function. The tensors specified in the list will be passed as callback_kwargs argument. You will only be able to include variables listed in the ._callback_tensor_inputs attribute of your pipeine class.

[~pipelines.stable_diffusion.StableDiffusionPipelineOutput] or tuple: If return_dict is True, [~pipelines.stable_diffusion.StableDiffusionPipelineOutput] is returned, otherwise a tuple is returned containing the output images.

The model ID or path to the pretrained model to load. Can be either:

• A model ID from the HuggingFace Hub
• A local path to a saved model directory

If True, takes a PyTorch model from model_id and compiles it for RBLN NPU execution. If False, loads an already compiled RBLN model from model_id without recompilation.

Directory to save the compiled model artifacts. Only used when export=True. If not provided and export=True, a temporary directory is used.

Configuration options for RBLN compilation. Can include settings for specific submodules such as text_encoder, unet, and vae. Configuration can be tailored to the specific pipeline being compiled.

LoRA adapter ID(s) to load and apply before compilation. LoRA weights are fused into the model weights during compilation. Only used when export=True.

Names of specific LoRA weight files to load, corresponding to lora_ids. Only used when export=True.

Scaling factor(s) to apply to the LoRA adapter(s). Only used when export=True.

Additional arguments to pass to the underlying diffusion pipeline constructor or the RBLN compilation process. These may include parameters specific to individual submodules or the particular diffusion pipeline being used.

A compiled or loaded diffusion pipeline that can be used for inference on RBLN NPU. The returned object is an instance of the class that called this method, inheriting from RBLNDiffusionMixin.

The prompt or prompts to guide the image generation. If not defined, one has to pass prompt_embeds. instead.

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

The initial image will be used as the starting point for the image generation process. Can also accept image latents as image, if passing latents directly, it will not be encoded again.

The ControlNet input condition. ControlNet uses this input condition to generate guidance to Unet. If the type is specified as Torch.FloatTensor, it is passed to ControlNet as is. PIL.Image.Image can also be accepted as an image. The dimensions of the output image defaults to image's dimensions. If height and/or width are passed, image is resized according to them. If multiple ControlNets are specified in init, images must be passed as a list such that each element of the list can be correctly batched for input to a single controlnet.

The height in pixels of the generated image. Anything below 512 pixels won't work well for stabilityai/stable-diffusion-xl-base-1.0 and checkpoints that are not specifically fine-tuned on low resolutions.

The width in pixels of the generated image. Anything below 512 pixels won't work well for stabilityai/stable-diffusion-xl-base-1.0 and checkpoints that are not specifically fine-tuned on low resolutions.

Indicates extent to transform the reference image. Must be between 0 and 1. image is used as a starting point and more noise is added the higher the strength. The number of denoising steps depends on the amount of noise initially added. When strength is 1, added noise is maximum and the denoising process runs for the full number of iterations specified in num_inference_steps. A value of 1 essentially ignores image.

The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference.

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.

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).

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

The number of images to generate per prompt.

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.

One or a list of torch generator(s) to make generation deterministic.

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.

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.

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.

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.

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.

(PipelineImageInput, optional): Optional image input to work with IP Adapters.

Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of IP-adapters. Each element should be a tensor of shape (batch_size, num_images, emb_dim). It should contain the negative image embedding if do_classifier_free_guidance is set to True. If not provided, embeddings are computed from the ip_adapter_image input argument.

The output format of the generate image. Choose between PIL: PIL.Image.Image or np.array.

Whether or not to return a [~pipelines.stable_diffusion.StableDiffusionPipelineOutput] instead of a plain tuple.

A kwargs dictionary that if specified is passed along to the AttentionProcessor as defined under self.processor in diffusers.models.attention_processor.

The outputs of the controlnet are multiplied by controlnet_conditioning_scale before they are added to the residual in the original unet. If multiple ControlNets are specified in init, you can set the corresponding scale as a list.

In this mode, the ControlNet encoder will try best to recognize the content of the input image even if you remove all prompts. The guidance_scale between 3.0 and 5.0 is recommended.

The percentage of total steps at which the controlnet starts applying.

The percentage of total steps at which the controlnet stops applying.

If original_size is not the same as target_size the image will appear to be down- or upsampled. original_size defaults to (height, width) if not specified. Part of SDXL's micro-conditioning as explained in section 2.2 of https://huggingface.co/papers/2307.01952.

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 https://huggingface.co/papers/2307.01952.

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 (height, width). Part of SDXL's micro-conditioning as explained in section 2.2 of https://huggingface.co/papers/2307.01952.

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 https://huggingface.co/papers/2307.01952. For more information, refer to this issue thread: https://github.com/huggingface/diffusers/issues/4208.

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 https://huggingface.co/papers/2307.01952. For more information, refer to this issue thread: https://github.com/huggingface/diffusers/issues/4208.

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 https://huggingface.co/papers/2307.01952. For more information, refer to this issue thread: https://github.com/huggingface/diffusers/issues/4208.

Used to simulate an aesthetic score of the generated image by influencing the positive text condition. Part of SDXL's micro-conditioning as explained in section 2.2 of https://huggingface.co/papers/2307.01952.

Part of SDXL's micro-conditioning as explained in section 2.2 of https://huggingface.co/papers/2307.01952. Can be used to simulate an aesthetic score of the generated image by influencing the negative text condition.

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.

A function that calls at the end of each denoising steps during the inference. The function is called with the following arguments: callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int, callback_kwargs: Dict). callback_kwargs will include a list of all tensors as specified by callback_on_step_end_tensor_inputs.

The list of tensor inputs for the callback_on_step_end function. The tensors specified in the list will be passed as callback_kwargs argument. You will only be able to include variables listed in the ._callback_tensor_inputs attribute of your pipeine class.

[~pipelines.stable_diffusion.StableDiffusionPipelineOutput] or tuple:

[~pipelines.stable_diffusion.StableDiffusionPipelineOutput] if return_dict is True, otherwise a tuple

containing the output images.

The model ID or path to the pretrained model to load. Can be either:

• A model ID from the HuggingFace Hub
• A local path to a saved model directory

If True, takes a PyTorch model from model_id and compiles it for RBLN NPU execution. If False, loads an already compiled RBLN model from model_id without recompilation.

Directory to save the compiled model artifacts. Only used when export=True. If not provided and export=True, a temporary directory is used.

Configuration options for RBLN compilation. Can include settings for specific submodules such as text_encoder, unet, and vae. Configuration can be tailored to the specific pipeline being compiled.

LoRA adapter ID(s) to load and apply before compilation. LoRA weights are fused into the model weights during compilation. Only used when export=True.

Names of specific LoRA weight files to load, corresponding to lora_ids. Only used when export=True.

Scaling factor(s) to apply to the LoRA adapter(s). Only used when export=True.

Additional arguments to pass to the underlying diffusion pipeline constructor or the RBLN compilation process. These may include parameters specific to individual submodules or the particular diffusion pipeline being used.

A compiled or loaded diffusion pipeline that can be used for inference on RBLN NPU. The returned object is an instance of the class that called this method, inheriting from RBLNDiffusionMixin.

Configuration for the primary text encoder. Initialized as RBLNCLIPTextModelConfig if not provided.

Configuration for the secondary text encoder. Initialized as RBLNCLIPTextModelWithProjectionConfig if not provided.

Configuration for the UNet model component. Initialized as RBLNUNet2DConditionModelConfig if not provided.

Configuration for the VAE model component. Initialized as RBLNAutoencoderKLConfig if not provided.

Configuration for the ControlNet model component. Initialized as RBLNControlNetModelConfig if not provided.

Batch size for inference, applied to all submodules.

Height of the generated images.

Width of the generated images.

Height of the generated images.

Width of the generated images.

Spatial dimensions for the UNet model.

Alternative way to specify image dimensions. Cannot be used together with img_height/img_width.

Scale for classifier-free guidance.

Additional arguments passed to the parent RBLNModelConfig.

If both image_size and img_height/img_width are provided.

Path to the RBLNModelConfig file or directory containing the config file.

Additional configuration to override.

Whether to return unused kwargs.

Additional keyword arguments to override configuration values. Keys starting with 'rbln_' will have the prefix removed and be used to update the configuration.

The loaded configuration instance.

Dictionary of load overrides, keyed like the rbln_config dict accepted by from_pretrained.

Configuration for the primary text encoder. Initialized as RBLNCLIPTextModelConfig if not provided.

Configuration for the secondary text encoder. Initialized as RBLNCLIPTextModelWithProjectionConfig if not provided.

Configuration for the UNet model component. Initialized as RBLNUNet2DConditionModelConfig if not provided.

Configuration for the VAE model component. Initialized as RBLNAutoencoderKLConfig if not provided.

Configuration for the ControlNet model component. Initialized as RBLNControlNetModelConfig if not provided.

Batch size for inference, applied to all submodules.

Height of the generated images.

Width of the generated images.

Height of the generated images.

Width of the generated images.

Spatial dimensions for the UNet model.

Alternative way to specify image dimensions. Cannot be used together with img_height/img_width.

Scale for classifier-free guidance.

Additional arguments passed to the parent RBLNModelConfig.

If both image_size and img_height/img_width are provided.

Dictionary of load overrides, keyed like the rbln_config dict accepted by from_pretrained.

Path to the RBLNModelConfig file or directory containing the config file.

Additional configuration to override.

Whether to return unused kwargs.

Additional keyword arguments to override configuration values. Keys starting with 'rbln_' will have the prefix removed and be used to update the configuration.

The loaded configuration instance.

Configuration for the primary text encoder. Initialized as RBLNCLIPTextModelConfig if not provided.

Configuration for the secondary text encoder. Initialized as RBLNCLIPTextModelWithProjectionConfig if not provided.

Configuration for the UNet model component. Initialized as RBLNUNet2DConditionModelConfig if not provided.

Configuration for the VAE model component. Initialized as RBLNAutoencoderKLConfig if not provided.

Configuration for the ControlNet model component. Initialized as RBLNControlNetModelConfig if not provided.

Batch size for inference, applied to all submodules.

Height of the generated images.

Width of the generated images.

Height of the generated images.

Width of the generated images.

Spatial dimensions for the UNet model.

Alternative way to specify image dimensions. Cannot be used together with img_height/img_width.

Scale for classifier-free guidance.

Additional arguments passed to the parent RBLNModelConfig.

If both image_size and img_height/img_width are provided.

Dictionary of load overrides, keyed like the rbln_config dict accepted by from_pretrained.

Path to the RBLNModelConfig file or directory containing the config file.

Additional configuration to override.

Whether to return unused kwargs.

Additional keyword arguments to override configuration values. Keys starting with 'rbln_' will have the prefix removed and be used to update the configuration.

The loaded configuration instance.