diffusers/pr_12229/en/api/pipelines/controlnet_sana.md

ControlNet

ControlNet was introduced in Adding Conditional Control to Text-to-Image Diffusion Models by Lvmin Zhang, Anyi Rao, and Maneesh Agrawala.

With a ControlNet model, you can provide an additional control image to condition and control Stable Diffusion generation. For example, if you provide a depth map, the ControlNet model generates an image that'll preserve the spatial information from the depth map. It is a more flexible and accurate way to control the image generation process.

The abstract from the paper is:

We present ControlNet, a neural network architecture to add spatial conditioning controls to large, pretrained text-to-image diffusion models. ControlNet locks the production-ready large diffusion models, and reuses their deep and robust encoding layers pretrained with billions of images as a strong backbone to learn a diverse set of conditional controls. The neural architecture is connected with "zero convolutions" (zero-initialized convolution layers) that progressively grow the parameters from zero and ensure that no harmful noise could affect the finetuning. We test various conditioning controls, eg, edges, depth, segmentation, human pose, etc, with Stable Diffusion, using single or multiple conditions, with or without prompts. We show that the training of ControlNets is robust with small (<50k) and large (>1m) datasets. Extensive results show that ControlNet may facilitate wider applications to control image diffusion models.

This pipeline was contributed by ishan24. ❤️ The original codebase can be found at NVlabs/Sana, and you can find official ControlNet checkpoints on Efficient-Large-Model's Hub profile.

SanaControlNetPipeline[[diffusers.SanaControlNetPipeline]]

class diffusers.SanaControlNetPipelinediffusers.SanaControlNetPipelinehttps://github.com/huggingface/diffusers/blob/vr_12229/src/diffusers/pipelines/sana/pipeline_sana_controlnet.py#L197[{"name": "tokenizer", "val": ": typing.Union[transformers.models.gemma.tokenization_gemma.GemmaTokenizer, transformers.models.gemma.tokenization_gemma_fast.GemmaTokenizerFast]"}, {"name": "text_encoder", "val": ": Gemma2PreTrainedModel"}, {"name": "vae", "val": ": AutoencoderDC"}, {"name": "transformer", "val": ": SanaTransformer2DModel"}, {"name": "controlnet", "val": ": SanaControlNetModel"}, {"name": "scheduler", "val": ": DPMSolverMultistepScheduler"}]

Pipeline for text-to-image generation using Sana.

calldiffusers.SanaControlNetPipeline.callhttps://github.com/huggingface/diffusers/blob/vr_12229/src/diffusers/pipelines/sana/pipeline_sana_controlnet.py#L776[{"name": "prompt", "val": ": typing.Union[str, typing.List[str]] = None"}, {"name": "negative_prompt", "val": ": str = ''"}, {"name": "num_inference_steps", "val": ": int = 20"}, {"name": "timesteps", "val": ": typing.List[int] = None"}, {"name": "sigmas", "val": ": typing.List[float] = None"}, {"name": "guidance_scale", "val": ": float = 4.5"}, {"name": "control_image", "val": ": typing.Union[PIL.Image.Image, numpy.ndarray, torch.Tensor, typing.List[PIL.Image.Image], typing.List[numpy.ndarray], typing.List[torch.Tensor]] = None"}, {"name": "controlnet_conditioning_scale", "val": ": typing.Union[float, typing.List[float]] = 1.0"}, {"name": "num_images_per_prompt", "val": ": typing.Optional[int] = 1"}, {"name": "height", "val": ": int = 1024"}, {"name": "width", "val": ": int = 1024"}, {"name": "eta", "val": ": float = 0.0"}, {"name": "generator", "val": ": typing.Union[torch._C.Generator, typing.List[torch._C.Generator], NoneType] = None"}, {"name": "latents", "val": ": typing.Optional[torch.Tensor] = None"}, {"name": "prompt_embeds", "val": ": typing.Optional[torch.Tensor] = None"}, {"name": "prompt_attention_mask", "val": ": typing.Optional[torch.Tensor] = None"}, {"name": "negative_prompt_embeds", "val": ": typing.Optional[torch.Tensor] = None"}, {"name": "negative_prompt_attention_mask", "val": ": typing.Optional[torch.Tensor] = None"}, {"name": "output_type", "val": ": typing.Optional[str] = 'pil'"}, {"name": "return_dict", "val": ": bool = True"}, {"name": "clean_caption", "val": ": bool = False"}, {"name": "use_resolution_binning", "val": ": bool = True"}, {"name": "attention_kwargs", "val": ": typing.Optional[typing.Dict[str, typing.Any]] = None"}, {"name": "callback_on_step_end", "val": ": typing.Optional[typing.Callable[[int, int, typing.Dict], NoneType]] = None"}, {"name": "callback_on_step_end_tensor_inputs", "val": ": typing.List[str] = ['latents']"}, {"name": "max_sequence_length", "val": ": int = 300"}, {"name": "complex_human_instruction", "val": ": typing.List[str] = ["Given a user prompt, generate an 'Enhanced prompt' that provides detailed visual descriptions suitable for image generation. Evaluate the level of detail in the user prompt:", '- If the prompt is simple, focus on adding specifics about colors, shapes, sizes, textures, and spatial relationships to create vivid and concrete scenes.', '- If the prompt is already detailed, refine and enhance the existing details slightly without overcomplicating.', 'Here are examples of how to transform or refine prompts:', '- User Prompt: A cat sleeping -> Enhanced: A small, fluffy white cat curled up in a round shape, sleeping peacefully on a warm sunny windowsill, surrounded by pots of blooming red flowers.', '- User Prompt: A busy city street -> Enhanced: A bustling city street scene at dusk, featuring glowing street lamps, a diverse crowd of people in colorful clothing, and a double-decker bus passing by towering glass skyscrapers.', 'Please generate only the enhanced description for the prompt below and avoid including any additional commentary or evaluations:', 'User Prompt: ']"}]- 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.

• negative_prompt (str or List[str], optional) -- The prompt or prompts not to guide the image generation. If not defined, one has to pass negative_prompt_embeds instead. Ignored when not using guidance (i.e., ignored if guidance_scale is less than 1).
• num_inference_steps (int, optional, defaults to 20) -- The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference.
• timesteps (List[int], optional) -- Custom timesteps to use for the denoising process with schedulers which support a timesteps argument in their set_timesteps method. If not defined, the default behavior when num_inference_steps is passed will be used. Must be in descending order.
• sigmas (List[float], optional) -- Custom sigmas to use for the denoising process with schedulers which support a sigmas argument in their set_timesteps method. If not defined, the default behavior when num_inference_steps is passed will be used.
• guidance_scale (float, optional, defaults to 4.5) -- Guidance scale as defined in Classifier-Free Diffusion Guidance. guidance_scale is defined as w of equation 2. of Imagen Paper. Guidance scale is enabled by setting guidance_scale > 1. Higher guidance scale encourages to generate images that are closely linked to the text prompt, usually at the expense of lower image quality.
• control_image (torch.Tensor, PIL.Image.Image, np.ndarray, List[torch.Tensor], List[PIL.Image.Image], List[np.ndarray], -- List[List[torch.Tensor]], List[List[np.ndarray]] or List[List[PIL.Image.Image]]): The ControlNet input condition to provide guidance to the unet for generation. If the type is specified as torch.Tensor, 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.
• controlnet_conditioning_scale (float or List[float], optional, defaults to 1.0) -- 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.
• num_images_per_prompt (int, optional, defaults to 1) -- The number of images to generate per prompt.
• height (int, optional, defaults to self.unet.config.sample_size) -- The height in pixels of the generated image.
• width (int, optional, defaults to self.unet.config.sample_size) -- The width in pixels of the generated image.
• eta (float, optional, defaults to 0.0) -- Corresponds to parameter eta (η) in the DDIM paper: https://huggingface.co/papers/2010.02502. Only applies to schedulers.DDIMScheduler, will be ignored for others.
• generator (torch.Generator or List[torch.Generator], optional) -- One or a list of torch generator(s) to make generation deterministic.
• 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 will be generated by sampling using the supplied random generator.
• 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 from prompt input argument.
• prompt_attention_mask (torch.Tensor, optional) -- Pre-generated attention mask for text embeddings.
• negative_prompt_embeds (torch.Tensor, optional) -- Pre-generated negative text embeddings. For PixArt-Sigma this negative prompt should be "". If not provided, negative_prompt_embeds will be generated from negative_prompt input argument.
• negative_prompt_attention_mask (torch.Tensor, optional) -- Pre-generated attention mask for negative text embeddings.
• output_type (str, optional, defaults to "pil") -- The output format of the generate image. Choose between PIL: PIL.Image.Image or np.array.
• return_dict (bool, optional, defaults to True) -- Whether or not to return a ~pipelines.stable_diffusion.IFPipelineOutput instead of a plain tuple.
• attention_kwargs -- A kwargs dictionary that if specified is passed along to the AttentionProcessor as defined under self.processor in diffusers.models.attention_processor.
• clean_caption (bool, optional, defaults to True) -- Whether or not to clean the caption before creating embeddings. Requires beautifulsoup4 and ftfy to be installed. If the dependencies are not installed, the embeddings will be created from the raw prompt.
• use_resolution_binning (bool defaults to True) -- If set to True, the requested height and width are first mapped to the closest resolutions using ASPECT_RATIO_1024_BIN. After the produced latents are decoded into images, they are resized back to the requested resolution. Useful for generating non-square images.
• callback_on_step_end (Callable, optional) -- 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.
• callback_on_step_end_tensor_inputs (List, optional) -- 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 pipeline class.
• max_sequence_length (int defaults to 300) -- Maximum sequence length to use with the prompt.
• complex_human_instruction (List[str], optional) -- Instructions for complex human attention: https://github.com/NVlabs/Sana/blob/main/configs/sana_app_config/Sana_1600M_app.yaml#L55.0SanaPipelineOutput or tupleIf return_dict is True, SanaPipelineOutput is returned, otherwise a tuple is returned where the first element is a list with the generated images

Function invoked when calling the pipeline for generation.

Examples:

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

>>> pipe = SanaControlNetPipeline.from_pretrained(
...     "ishan24/Sana_600M_1024px_ControlNetPlus_diffusers",
...     variant="fp16",
...     torch_dtype={"default": torch.bfloat16, "controlnet": torch.float16, "transformer": torch.float16},
...     device_map="balanced",
... )
>>> cond_image = load_image(
...     "https://huggingface.co/ishan24/Sana_600M_1024px_ControlNet_diffusers/resolve/main/hed_example.png"
... )
>>> prompt = 'a cat with a neon sign that says "Sana"'
>>> image = pipe(
...     prompt,
...     control_image=cond_image,
... ).images[0]
>>> image.save("output.png")

disable_vae_slicingdiffusers.SanaControlNetPipeline.disable_vae_slicinghttps://github.com/huggingface/diffusers/blob/vr_12229/src/diffusers/pipelines/sana/pipeline_sana_controlnet.py#L249[]

Disable sliced VAE decoding. If enable_vae_slicing was previously enabled, this method will go back to computing decoding in one step.

disable_vae_tilingdiffusers.SanaControlNetPipeline.disable_vae_tilinghttps://github.com/huggingface/diffusers/blob/vr_12229/src/diffusers/pipelines/sana/pipeline_sana_controlnet.py#L276[]

Disable tiled VAE decoding. If enable_vae_tiling was previously enabled, this method will go back to computing decoding in one step.

enable_vae_slicingdiffusers.SanaControlNetPipeline.enable_vae_slicinghttps://github.com/huggingface/diffusers/blob/vr_12229/src/diffusers/pipelines/sana/pipeline_sana_controlnet.py#L236[]

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.

enable_vae_tilingdiffusers.SanaControlNetPipeline.enable_vae_tilinghttps://github.com/huggingface/diffusers/blob/vr_12229/src/diffusers/pipelines/sana/pipeline_sana_controlnet.py#L262[]

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_promptdiffusers.SanaControlNetPipeline.encode_prompthttps://github.com/huggingface/diffusers/blob/vr_12229/src/diffusers/pipelines/sana/pipeline_sana_controlnet.py#L349[{"name": "prompt", "val": ": typing.Union[str, typing.List[str]]"}, {"name": "do_classifier_free_guidance", "val": ": bool = True"}, {"name": "negative_prompt", "val": ": str = ''"}, {"name": "num_images_per_prompt", "val": ": int = 1"}, {"name": "device", "val": ": typing.Optional[torch.device] = None"}, {"name": "prompt_embeds", "val": ": typing.Optional[torch.Tensor] = None"}, {"name": "negative_prompt_embeds", "val": ": typing.Optional[torch.Tensor] = None"}, {"name": "prompt_attention_mask", "val": ": typing.Optional[torch.Tensor] = None"}, {"name": "negative_prompt_attention_mask", "val": ": typing.Optional[torch.Tensor] = None"}, {"name": "clean_caption", "val": ": bool = False"}, {"name": "max_sequence_length", "val": ": int = 300"}, {"name": "complex_human_instruction", "val": ": typing.Optional[typing.List[str]] = None"}, {"name": "lora_scale", "val": ": typing.Optional[float] = None"}]- prompt (str or List[str], optional) -- prompt to be encoded

• negative_prompt (str or List[str], optional) -- The prompt 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). For PixArt-Alpha, this should be "".
• do_classifier_free_guidance (bool, optional, defaults to True) -- whether to use classifier free guidance or not
• num_images_per_prompt (int, optional, defaults to 1) -- number of images that should be generated per prompt
• device -- (torch.device, optional): torch device to place the resulting embeddings on
• 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 from prompt input argument.
• negative_prompt_embeds (torch.Tensor, optional) -- Pre-generated negative text embeddings. For Sana, it's should be the embeddings of the "" string.
• clean_caption (bool, defaults to False) -- If True, the function will preprocess and clean the provided caption before encoding.
• max_sequence_length (int, defaults to 300) -- Maximum sequence length to use for the prompt.
• complex_human_instruction (list[str], defaults to complex_human_instruction) -- If complex_human_instruction is not empty, the function will use the complex Human instruction for the prompt.0

Encodes the prompt into text encoder hidden states.

SanaPipelineOutput[[diffusers.pipelines.sana.pipeline_output.SanaPipelineOutput]]

class diffusers.pipelines.sana.pipeline_output.SanaPipelineOutputdiffusers.pipelines.sana.pipeline_output.SanaPipelineOutputhttps://github.com/huggingface/diffusers/blob/vr_12229/src/diffusers/pipelines/sana/pipeline_output.py#L11[{"name": "images", "val": ": typing.Union[typing.List[PIL.Image.Image], numpy.ndarray]"}]- images (List[PIL.Image.Image] or np.ndarray) -- List of denoised PIL images of length batch_size or numpy array of shape (batch_size, height, width, num_channels). PIL images or numpy array present the denoised images of the diffusion pipeline.0

Output class for Sana pipelines.