Safe Stable Diffusion

Safe Stable Diffusion

Safe Stable Diffusion was proposed in Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models and mitigates inappropriate degeneration from Stable Diffusion models because they’re trained on unfiltered web-crawled datasets. For instance Stable Diffusion may unexpectedly generate nudity, violence, images depicting self-harm, and otherwise offensive content. Safe Stable Diffusion is an extension of Stable Diffusion that drastically reduces this type of content.

The abstract from the paper is:

Text-conditioned image generation models have recently achieved astonishing results in image quality and text alignment and are consequently employed in a fast-growing number of applications. Since they are highly data-driven, relying on billion-sized datasets randomly scraped from the internet, they also suffer, as we demonstrate, from degenerated and biased human behavior. In turn, they may even reinforce such biases. To help combat these undesired side effects, we present safe latent diffusion (SLD). Specifically, to measure the inappropriate degeneration due to unfiltered and imbalanced training sets, we establish a novel image generation test bed-inappropriate image prompts (I2P)-containing dedicated, real-world image-to-text prompts covering concepts such as nudity and violence. As our exhaustive empirical evaluation demonstrates, the introduced SLD removes and suppresses inappropriate image parts during the diffusion process, with no additional training required and no adverse effect on overall image quality or text alignment.

Tips

Use the safety_concept property of StableDiffusionPipelineSafe to check and edit the current safety concept:

Copied

>>> from diffusers import StableDiffusionPipelineSafe

>>> pipeline = StableDiffusionPipelineSafe.from_pretrained("AIML-TUDA/stable-diffusion-safe")
>>> pipeline.safety_concept
'an image showing hate, harassment, violence, suffering, humiliation, harm, suicide, sexual, nudity, bodily fluids, blood, obscene gestures, illegal activity, drug use, theft, vandalism, weapons, child abuse, brutality, cruelty'

For each image generation the active concept is also contained in StableDiffusionSafePipelineOutput.

There are 4 configurations (SafetyConfig.WEAK, SafetyConfig.MEDIUM, SafetyConfig.STRONG, and SafetyConfig.MAX) that can be applied:

Copied

>>> from diffusers import StableDiffusionPipelineSafe
>>> from diffusers.pipelines.stable_diffusion_safe import SafetyConfig

>>> pipeline = StableDiffusionPipelineSafe.from_pretrained("AIML-TUDA/stable-diffusion-safe")
>>> prompt = "the four horsewomen of the apocalypse, painting by tom of finland, gaston bussiere, craig mullins, j. c. leyendecker"
>>> out = pipeline(prompt=prompt, **SafetyConfig.MAX)

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!

StableDiffusionPipelineSafe

class diffusers.StableDiffusionPipelineSafe

<source>

( vae: AutoencoderKLtext_encoder: CLIPTextModeltokenizer: CLIPTokenizerunet: UNet2DConditionModelscheduler: KarrasDiffusionSchedulerssafety_checker: SafeStableDiffusionSafetyCheckerfeature_extractor: CLIPImageProcessorrequires_safety_checker: bool = True )

Parameters

  • vae (AutoencoderKL) β€” Variational Auto-Encoder (VAE) model to encode and decode images to and from latent representations.

  • text_encoder (CLIPTextModel) β€” Frozen text-encoder (clip-vit-large-patch14).

  • tokenizer (CLIPTokenizer) β€” A CLIPTokenizer to tokenize text.

  • unet (UNet2DConditionModel) β€” A UNet2DConditionModel to denoise the encoded image latents.

  • scheduler (SchedulerMixin) β€” A scheduler to be used in combination with unet to denoise the encoded image latents. Can be one of DDIMScheduler, LMSDiscreteScheduler, or PNDMScheduler.

  • safety_checker (StableDiffusionSafetyChecker) β€” Classification module that estimates whether generated images could be considered offensive or harmful. Please refer to the model card for more details about a model’s potential harms.

  • feature_extractor (CLIPImageProcessor) β€” A CLIPImageProcessor to extract features from generated images; used as inputs to the safety_checker.

Pipeline based on the StableDiffusionPipeline for text-to-image generation using Safe Latent Diffusion.

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.).

__call__

<source>

( prompt: typing.Union[str, typing.List[str]]height: 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] = Noneoutput_type: typing.Optional[str] = 'pil'return_dict: bool = Truecallback: typing.Union[typing.Callable[[int, int, torch.FloatTensor], NoneType], NoneType] = Nonecallback_steps: int = 1sld_guidance_scale: typing.Optional[float] = 1000sld_warmup_steps: typing.Optional[int] = 10sld_threshold: typing.Optional[float] = 0.01sld_momentum_scale: typing.Optional[float] = 0.3sld_mom_beta: typing.Optional[float] = 0.4 ) β†’ StableDiffusionPipelineOutput or tuple

Parameters

  • prompt (str or List[str]) β€” The prompt or prompts to guide image generation. If not defined, you need to pass prompt_embeds.

  • height (int, optional, defaults to self.unet.config.sample_size * self.vae_scale_factor) β€” The height in pixels of the generated image.

  • width (int, optional, defaults to self.unet.config.sample_size * self.vae_scale_factor) β€” The width in pixels of the generated image.

  • num_inference_steps (int, optional, defaults to 50) β€” 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) β€” 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) β€” 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) β€” The number of images to generate per prompt.

  • eta (float, optional, defaults to 0.0) β€” Corresponds to parameter eta (Ξ·) from the DDIM paper. Only applies to the DDIMScheduler, and is ignored in other schedulers.

  • generator (torch.Generator or List[torch.Generator], optional) β€” A torch.Generator to make generation deterministic.

  • latents (torch.FloatTensor, optional) β€” 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") β€” The output format of the generated image. Choose between PIL.Image or np.array.

  • return_dict (bool, optional, defaults to True) β€” Whether or not to return a StableDiffusionPipelineOutput instead of a plain tuple.

  • callback (Callable, optional) β€” 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.FloatTensor).

  • callback_steps (int, optional, defaults to 1) β€” The frequency at which the callback function is called. If not specified, the callback is called at every step.

  • sld_guidance_scale (float, optional, defaults to 1000) β€” If sld_guidance_scale < 1, safety guidance is disabled.

  • sld_warmup_steps (int, optional, defaults to 10) β€” Number of warmup steps for safety guidance. SLD is only be applied for diffusion steps greater than sld_warmup_steps.

  • sld_threshold (float, optional, defaults to 0.01) β€” Threshold that separates the hyperplane between appropriate and inappropriate images.

  • sld_momentum_scale (float, optional, defaults to 0.3) β€” Scale of the SLD momentum to be added to the safety guidance at each diffusion step. If set to 0.0, momentum is disabled. Momentum is built up during warmup for diffusion steps smaller than sld_warmup_steps.

  • sld_mom_beta (float, optional, defaults to 0.4) β€” Defines how safety guidance momentum builds up. sld_mom_beta indicates how much of the previous momentum is kept. Momentum is built up during warmup for diffusion steps smaller than sld_warmup_steps.

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 and the second element is a list of bools indicating whether the corresponding generated image contains β€œnot-safe-for-work” (nsfw) content.

The call function to the pipeline for generation.

Examples:

Copied

import torch
from diffusers import StableDiffusionPipelineSafe

pipeline = StableDiffusionPipelineSafe.from_pretrained(
    "AIML-TUDA/stable-diffusion-safe", torch_dtype=torch.float16
)
prompt = "the four horsewomen of the apocalypse, painting by tom of finland, gaston bussiere, craig mullins, j. c. leyendecker"
image = pipeline(prompt=prompt, **SafetyConfig.MEDIUM).images[0]

StableDiffusionSafePipelineOutput

class diffusers.pipelines.stable_diffusion_safe.StableDiffusionSafePipelineOutput

<source>

( images: typing.Union[typing.List[PIL.Image.Image], numpy.ndarray]nsfw_content_detected: typing.Optional[typing.List[bool]]unsafe_images: typing.Union[typing.List[PIL.Image.Image], numpy.ndarray, NoneType]applied_safety_concept: typing.Optional[str] )

Parameters

  • images (List[PIL.Image.Image] or np.ndarray) β€” 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.

  • nsfw_content_detected (List[bool]) β€” List of flags denoting whether the corresponding generated image likely represents β€œnot-safe-for-work” (nsfw) content, or None if safety checking could not be performed.

  • images (List[PIL.Image.Image] or np.ndarray) β€” List of denoised PIL images that were flagged by the safety checker any may contain β€œnot-safe-for-work” (nsfw) content, or None if no safety check was performed or no images were flagged.

  • applied_safety_concept (str) β€” The safety concept that was applied for safety guidance, or None if safety guidance was disabled

Output class for Safe Stable Diffusion pipelines.

__call__

( *args**kwargs )

Call self as a function.

Last updated