diffusers/pr_12509/en/api/pipelines/stable_diffusion/upscale.md

Super-resolution

The Stable Diffusion upscaler diffusion model was created by the researchers and engineers from CompVis, Stability AI, and LAION. It is used to enhance the resolution of input images by a factor of 4.

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're interested in using one of the official checkpoints for a task, explore the CompVis and Stability AI Hub organizations!

StableDiffusionUpscalePipeline[[diffusers.StableDiffusionUpscalePipeline]]

class diffusers.StableDiffusionUpscalePipelinediffusers.StableDiffusionUpscalePipelinehttps://github.com/huggingface/diffusers/blob/vr_12509/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_upscale.py#L82[{"name": "vae", "val": ": AutoencoderKL"}, {"name": "text_encoder", "val": ": CLIPTextModel"}, {"name": "tokenizer", "val": ": CLIPTokenizer"}, {"name": "unet", "val": ": UNet2DConditionModel"}, {"name": "low_res_scheduler", "val": ": DDPMScheduler"}, {"name": "scheduler", "val": ": KarrasDiffusionSchedulers"}, {"name": "safety_checker", "val": ": typing.Optional[typing.Any] = None"}, {"name": "feature_extractor", "val": ": typing.Optional[transformers.models.clip.image_processing_clip.CLIPImageProcessor] = None"}, {"name": "watermarker", "val": ": typing.Optional[typing.Any] = None"}, {"name": "max_noise_level", "val": ": int = 350"}]- 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.
• low_res_scheduler (SchedulerMixin) -- A scheduler used to add initial noise to the low resolution conditioning image. It must be an instance of DDPMScheduler.
• 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.0

Pipeline for text-guided image super-resolution using Stable Diffusion 2.

This model inherits from DiffusionPipeline. Check the superclass documentation for the generic methods implemented for all pipelines (downloading, saving, running on a particular device, etc.).

The pipeline also inherits the following loading methods:

• load_textual_inversion() for loading textual inversion embeddings
• load_lora_weights() for loading LoRA weights
• save_lora_weights() for saving LoRA weights
• from_single_file() for loading .ckpt files

calldiffusers.StableDiffusionUpscalePipeline.callhttps://github.com/huggingface/diffusers/blob/vr_12509/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_upscale.py#L548[{"name": "prompt", "val": ": typing.Union[str, typing.List[str]] = None"}, {"name": "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": "num_inference_steps", "val": ": int = 75"}, {"name": "guidance_scale", "val": ": float = 9.0"}, {"name": "noise_level", "val": ": int = 20"}, {"name": "negative_prompt", "val": ": typing.Union[str, typing.List[str], NoneType] = None"}, {"name": "num_images_per_prompt", "val": ": typing.Optional[int] = 1"}, {"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": "negative_prompt_embeds", "val": ": typing.Optional[torch.Tensor] = None"}, {"name": "output_type", "val": ": typing.Optional[str] = 'pil'"}, {"name": "return_dict", "val": ": bool = True"}, {"name": "callback", "val": ": typing.Optional[typing.Callable[[int, int, torch.Tensor], NoneType]] = None"}, {"name": "callback_steps", "val": ": int = 1"}, {"name": "cross_attention_kwargs", "val": ": typing.Optional[typing.Dict[str, typing.Any]] = None"}, {"name": "clip_skip", "val": ": int = None"}]- prompt (str or List[str], optional) -- The prompt or prompts to guide image generation. If not defined, you need to pass prompt_embeds.

• image (torch.Tensor, PIL.Image.Image, np.ndarray, List[torch.Tensor], List[PIL.Image.Image], or List[np.ndarray]) -- Image or tensor representing an image batch to be upscaled.
• 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 text prompt at the expense of lower image quality. Guidance scale is enabled when guidance_scale > 1.
• negative_prompt (str or List[str], optional) -- 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).
• 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 or List[torch.Generator], optional) -- A torch.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 random generator.
• 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 the prompt 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 the negative_prompt input argument.
• output_type (str, optional, defaults to "pil") -- The output format of the generated image. Choose between PIL.Image or np.array.
• return_dict (bool, optional, defaults to True) -- Whether or not to return a StableDiffusionPipelineOutput instead of a plain tuple.
• callback (Callable, optional) -- A function that calls every callback_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 the callback 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 the AttentionProcessor as defined in self.processor.
• 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.0StableDiffusionPipelineOutput or tupleIf 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 bools indicating whether the corresponding generated image contains "not-safe-for-work" (nsfw) content.

The call function to the pipeline for generation.

Examples:

>>> import requests
>>> from PIL import Image
>>> from io import BytesIO
>>> from diffusers import StableDiffusionUpscalePipeline
>>> import torch

>>> # load model and scheduler
>>> model_id = "stabilityai/stable-diffusion-x4-upscaler"
>>> pipeline = StableDiffusionUpscalePipeline.from_pretrained(
...     model_id, variant="fp16", torch_dtype=torch.float16
... )
>>> pipeline = pipeline.to("cuda")

>>> # let's download an  image
>>> url = "https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/sd2-upscale/low_res_cat.png"
>>> response = requests.get(url)
>>> low_res_img = Image.open(BytesIO(response.content)).convert("RGB")
>>> low_res_img = low_res_img.resize((128, 128))
>>> prompt = "a white cat"

>>> upscaled_image = pipeline(prompt=prompt, image=low_res_img).images[0]
>>> upscaled_image.save("upsampled_cat.png")

enable_attention_slicingdiffusers.StableDiffusionUpscalePipeline.enable_attention_slicinghttps://github.com/huggingface/diffusers/blob/vr_12509/src/diffusers/pipelines/pipeline_utils.py#L1978[{"name": "slice_size", "val": ": typing.Union[int, str, NoneType] = 'auto'"}]- 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.0

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:

>>> import torch
>>> from diffusers import StableDiffusionPipeline

>>> pipe = StableDiffusionPipeline.from_pretrained(
...     "stable-diffusion-v1-5/stable-diffusion-v1-5",
...     torch_dtype=torch.float16,
...     use_safetensors=True,
... )

>>> prompt = "a photo of an astronaut riding a horse on mars"
>>> pipe.enable_attention_slicing()
>>> image = pipe(prompt).images[0]

disable_attention_slicingdiffusers.StableDiffusionUpscalePipeline.disable_attention_slicinghttps://github.com/huggingface/diffusers/blob/vr_12509/src/diffusers/pipelines/pipeline_utils.py#L2015[]

Disable sliced attention computation. If enable_attention_slicing was previously called, attention is computed in one step.

enable_xformers_memory_efficient_attentiondiffusers.StableDiffusionUpscalePipeline.enable_xformers_memory_efficient_attentionhttps://github.com/huggingface/diffusers/blob/vr_12509/src/diffusers/pipelines/pipeline_utils.py#L1921[{"name": "attention_op", "val": ": typing.Optional[typing.Callable] = None"}]- attention_op (Callable, optional) -- Override the default None operator for use as op argument to the memory_efficient_attention() function of xFormers.0

Enable memory efficient attention from xFormers. 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.

> ⚠️ When memory efficient attention and sliced attention are both enabled, memory efficient attention takes > precedent.

Examples:

>>> import torch
>>> from diffusers import DiffusionPipeline
>>> from xformers.ops import MemoryEfficientAttentionFlashAttentionOp

>>> pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-2-1", torch_dtype=torch.float16)
>>> pipe = pipe.to("cuda")
>>> pipe.enable_xformers_memory_efficient_attention(attention_op=MemoryEfficientAttentionFlashAttentionOp)
>>> # Workaround for not accepting attention shape using VAE for Flash Attention
>>> pipe.vae.enable_xformers_memory_efficient_attention(attention_op=None)

disable_xformers_memory_efficient_attentiondiffusers.StableDiffusionUpscalePipeline.disable_xformers_memory_efficient_attentionhttps://github.com/huggingface/diffusers/blob/vr_12509/src/diffusers/pipelines/pipeline_utils.py#L1952[]

Disable memory efficient attention from xFormers.

encode_promptdiffusers.StableDiffusionUpscalePipeline.encode_prompthttps://github.com/huggingface/diffusers/blob/vr_12509/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_upscale.py#L221[{"name": "prompt", "val": ""}, {"name": "device", "val": ""}, {"name": "num_images_per_prompt", "val": ""}, {"name": "do_classifier_free_guidance", "val": ""}, {"name": "negative_prompt", "val": " = None"}, {"name": "prompt_embeds", "val": ": typing.Optional[torch.Tensor] = None"}, {"name": "negative_prompt_embeds", "val": ": typing.Optional[torch.Tensor] = None"}, {"name": "lora_scale", "val": ": typing.Optional[float] = None"}, {"name": "clip_skip", "val": ": typing.Optional[int] = None"}]- 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.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. 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.
• 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.0

Encodes the prompt into text encoder hidden states.

StableDiffusionPipelineOutput[[diffusers.pipelines.stable_diffusion.StableDiffusionPipelineOutput]]

class diffusers.pipelines.stable_diffusion.StableDiffusionPipelineOutputdiffusers.pipelines.stable_diffusion.StableDiffusionPipelineOutputhttps://github.com/huggingface/diffusers/blob/vr_12509/src/diffusers/pipelines/stable_diffusion/pipeline_output.py#L11[{"name": "images", "val": ": typing.Union[typing.List[PIL.Image.Image], numpy.ndarray]"}, {"name": "nsfw_content_detected", "val": ": typing.Optional[typing.List[bool]]"}]- 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).

• nsfw_content_detected (List[bool]) -- List indicating whether the corresponding generated image contains "not-safe-for-work" (nsfw) content or None if safety checking could not be performed.0

Output class for Stable Diffusion pipelines.