Hugging Face's logo

Diffusers documentation

Latent upscaler

You are viewing v0.30.0 version. A newer version v0.31.0 is available.
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

Latent upscaler

The Stable Diffusion latent upscaler model was created by Katherine Crowson in collaboration with Stability AI. It is used to enhance the output image resolution by a factor of 2 (see this demo notebook for a demonstration of the original implementation).

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, Runway, and Stability AI Hub organizations!

StableDiffusionLatentUpscalePipeline

class diffusers.StableDiffusionLatentUpscalePipeline

< >

( vae: AutoencoderKL text_encoder: CLIPTextModel tokenizer: CLIPTokenizer unet: UNet2DConditionModel scheduler: EulerDiscreteScheduler )

Parameters

Pipeline for upscaling Stable Diffusion output image resolution by a factor of 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:

__call__

< >

( prompt: Union image: Union = None num_inference_steps: int = 75 guidance_scale: float = 9.0 negative_prompt: Union = None generator: Union = None latents: Optional = None output_type: Optional = 'pil' return_dict: bool = True callback: Optional = None callback_steps: int = 1 ) → StableDiffusionPipelineOutput or tuple

Parameters

  • prompt (str or List[str]) — The prompt or prompts to guide image upscaling.
  • 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. If it’s a tensor, it can be either a latent output from a Stable Diffusion model or an image tensor in the range [-1, 1]. It is considered a latent if image.shape[1] is 4; otherwise, it is considered to be an image representation and encoded using this pipeline’s vae encoder.
  • 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).
  • 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.
  • 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.

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.

The call function to the pipeline for generation.

Examples:

>>> from diffusers import StableDiffusionLatentUpscalePipeline, StableDiffusionPipeline
>>> import torch


>>> pipeline = StableDiffusionPipeline.from_pretrained(
...     "CompVis/stable-diffusion-v1-4", torch_dtype=torch.float16
... )
>>> pipeline.to("cuda")

>>> model_id = "stabilityai/sd-x2-latent-upscaler"
>>> upscaler = StableDiffusionLatentUpscalePipeline.from_pretrained(model_id, torch_dtype=torch.float16)
>>> upscaler.to("cuda")

>>> prompt = "a photo of an astronaut high resolution, unreal engine, ultra realistic"
>>> generator = torch.manual_seed(33)

>>> low_res_latents = pipeline(prompt, generator=generator, output_type="latent").images

>>> with torch.no_grad():
...     image = pipeline.decode_latents(low_res_latents)
>>> image = pipeline.numpy_to_pil(image)[0]

>>> image.save("../images/a1.png")

>>> upscaled_image = upscaler(
...     prompt=prompt,
...     image=low_res_latents,
...     num_inference_steps=20,
...     guidance_scale=0,
...     generator=generator,
... ).images[0]

>>> upscaled_image.save("../images/a2.png")

enable_sequential_cpu_offload

< >

( gpu_id: Optional = None device: Union = '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 or str, 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, significantly reducing memory usage. When called, the state dicts of all torch.nn.Module components (except those in self._exclude_from_cpu_offload) are saved to CPU and then moved to torch.device('meta') and loaded to GPU only when their specific submodule has its forward method called. Offloading happens on a submodule basis. Memory savings are higher than with enable_model_cpu_offload, but performance is lower.

enable_attention_slicing

< >

( slice_size: Union = '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:

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

>>> pipe = StableDiffusionPipeline.from_pretrained(
...     "runwayml/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_slicing

< >

( )

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

enable_xformers_memory_efficient_attention

< >

( attention_op: Optional = None )

Parameters

  • attention_op (Callable, optional) — Override the default None operator for use as op argument to the memory_efficient_attention() function of xFormers.

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_attention

< >

( )

Disable memory efficient attention from xFormers.

StableDiffusionPipelineOutput

class diffusers.pipelines.stable_diffusion.StableDiffusionPipelineOutput

< >

( images: Union nsfw_content_detected: Optional )

Parameters

  • 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.

Output class for Stable Diffusion pipelines.

< > Update on GitHub

←SDXL Turbo Super-resolution→