Hugging Face's logo

Diffusers documentation

Stable Diffusion 3

You are viewing v0.30.1 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

Stable Diffusion 3

Stable Diffusion 3 (SD3) was proposed in Scaling Rectified Flow Transformers for High-Resolution Image Synthesis by Patrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari, Jonas Muller, Harry Saini, Yam Levi, Dominik Lorenz, Axel Sauer, Frederic Boesel, Dustin Podell, Tim Dockhorn, Zion English, Kyle Lacey, Alex Goodwin, Yannik Marek, and Robin Rombach.

The abstract from the paper is:

Diffusion models create data from noise by inverting the forward paths of data towards noise and have emerged as a powerful generative modeling technique for high-dimensional, perceptual data such as images and videos. Rectified flow is a recent generative model formulation that connects data and noise in a straight line. Despite its better theoretical properties and conceptual simplicity, it is not yet decisively established as standard practice. In this work, we improve existing noise sampling techniques for training rectified flow models by biasing them towards perceptually relevant scales. Through a large-scale study, we demonstrate the superior performance of this approach compared to established diffusion formulations for high-resolution text-to-image synthesis. Additionally, we present a novel transformer-based architecture for text-to-image generation that uses separate weights for the two modalities and enables a bidirectional flow of information between image and text tokens, improving text comprehension typography, and human preference ratings. We demonstrate that this architecture follows predictable scaling trends and correlates lower validation loss to improved text-to-image synthesis as measured by various metrics and human evaluations.

Usage Example

As the model is gated, before using it with diffusers you first need to go to the Stable Diffusion 3 Medium Hugging Face page, fill in the form and accept the gate. Once you are in, you need to login so that your system knows you’ve accepted the gate.

Use the command below to log in:

huggingface-cli login

The SD3 pipeline uses three text encoders to generate an image. Model offloading is necessary in order for it to run on most commodity hardware. Please use the torch.float16 data type for additional memory savings.

import torch
from diffusers import StableDiffusion3Pipeline

pipe = StableDiffusion3Pipeline.from_pretrained("stabilityai/stable-diffusion-3-medium-diffusers", torch_dtype=torch.float16)
pipe.to("cuda")

image = pipe(
    prompt="a photo of a cat holding a sign that says hello world",
    negative_prompt="",
    num_inference_steps=28,
    height=1024,
    width=1024,
    guidance_scale=7.0,
).images[0]

image.save("sd3_hello_world.png")

Memory Optimisations for SD3

SD3 uses three text encoders, one if which is the very large T5-XXL model. This makes it challenging to run the model on GPUs with less than 24GB of VRAM, even when using fp16 precision. The following section outlines a few memory optimizations in Diffusers that make it easier to run SD3 on low resource hardware.

Running Inference with Model Offloading

The most basic memory optimization available in Diffusers allows you to offload the components of the model to CPU during inference in order to save memory, while seeing a slight increase in inference latency. Model offloading will only move a model component onto the GPU when it needs to be executed, while keeping the remaining components on the CPU.

import torch
from diffusers import StableDiffusion3Pipeline

pipe = StableDiffusion3Pipeline.from_pretrained("stabilityai/stable-diffusion-3-medium-diffusers", torch_dtype=torch.float16)
pipe.enable_model_cpu_offload()

image = pipe(
    prompt="a photo of a cat holding a sign that says hello world",
    negative_prompt="",
    num_inference_steps=28,
    height=1024,
    width=1024,
    guidance_scale=7.0,
).images[0]

image.save("sd3_hello_world.png")

Dropping the T5 Text Encoder during Inference

Removing the memory-intensive 4.7B parameter T5-XXL text encoder during inference can significantly decrease the memory requirements for SD3 with only a slight loss in performance.

import torch
from diffusers import StableDiffusion3Pipeline

pipe = StableDiffusion3Pipeline.from_pretrained(
    "stabilityai/stable-diffusion-3-medium-diffusers",
    text_encoder_3=None,
    tokenizer_3=None,
    torch_dtype=torch.float16
)
pipe.to("cuda")

image = pipe(
    prompt="a photo of a cat holding a sign that says hello world",
    negative_prompt="",
    num_inference_steps=28,
    height=1024,
    width=1024,
    guidance_scale=7.0,
).images[0]

image.save("sd3_hello_world-no-T5.png")

Using a Quantized Version of the T5 Text Encoder

We can leverage the bitsandbytes library to load and quantize the T5-XXL text encoder to 8-bit precision. This allows you to keep using all three text encoders while only slightly impacting performance.

First install the bitsandbytes library.

pip install bitsandbytes

Then load the T5-XXL model using the BitsAndBytesConfig.

import torch
from diffusers import StableDiffusion3Pipeline
from transformers import T5EncoderModel, BitsAndBytesConfig

quantization_config = BitsAndBytesConfig(load_in_8bit=True)

model_id = "stabilityai/stable-diffusion-3-medium-diffusers"
text_encoder = T5EncoderModel.from_pretrained(
    model_id,
    subfolder="text_encoder_3",
    quantization_config=quantization_config,
)
pipe = StableDiffusion3Pipeline.from_pretrained(
    model_id,
    text_encoder_3=text_encoder,
    device_map="balanced",
    torch_dtype=torch.float16
)

image = pipe(
    prompt="a photo of a cat holding a sign that says hello world",
    negative_prompt="",
    num_inference_steps=28,
    height=1024,
    width=1024,
    guidance_scale=7.0,
).images[0]

image.save("sd3_hello_world-8bit-T5.png")

You can find the end-to-end script here.

Performance Optimizations for SD3

Using Torch Compile to Speed Up Inference

Using compiled components in the SD3 pipeline can speed up inference by as much as 4X. The following code snippet demonstrates how to compile the Transformer and VAE components of the SD3 pipeline.

import torch
from diffusers import StableDiffusion3Pipeline

torch.set_float32_matmul_precision("high")

torch._inductor.config.conv_1x1_as_mm = True
torch._inductor.config.coordinate_descent_tuning = True
torch._inductor.config.epilogue_fusion = False
torch._inductor.config.coordinate_descent_check_all_directions = True

pipe = StableDiffusion3Pipeline.from_pretrained(
    "stabilityai/stable-diffusion-3-medium-diffusers",
    torch_dtype=torch.float16
).to("cuda")
pipe.set_progress_bar_config(disable=True)

pipe.transformer.to(memory_format=torch.channels_last)
pipe.vae.to(memory_format=torch.channels_last)

pipe.transformer = torch.compile(pipe.transformer, mode="max-autotune", fullgraph=True)
pipe.vae.decode = torch.compile(pipe.vae.decode, mode="max-autotune", fullgraph=True)

# Warm Up
prompt = "a photo of a cat holding a sign that says hello world"
for _ in range(3):
    _ = pipe(prompt=prompt, generator=torch.manual_seed(1))

# Run Inference
image = pipe(prompt=prompt, generator=torch.manual_seed(1)).images[0]
image.save("sd3_hello_world.png")

Check out the full script here.

Using Long Prompts with the T5 Text Encoder

By default, the T5 Text Encoder prompt uses a maximum sequence length of 256. This can be adjusted by setting the max_sequence_length to accept fewer or more tokens. Keep in mind that longer sequences require additional resources and result in longer generation times, such as during batch inference.

prompt = "A whimsical and creative image depicting a hybrid creature that is a mix of a waffle and a hippopotamus, basking in a river of melted butter amidst a breakfast-themed landscape. It features the distinctive, bulky body shape of a hippo. However, instead of the usual grey skin, the creature’s body resembles a golden-brown, crispy waffle fresh off the griddle. The skin is textured with the familiar grid pattern of a waffle, each square filled with a glistening sheen of syrup. The environment combines the natural habitat of a hippo with elements of a breakfast table setting, a river of warm, melted butter, with oversized utensils or plates peeking out from the lush, pancake-like foliage in the background, a towering pepper mill standing in for a tree.  As the sun rises in this fantastical world, it casts a warm, buttery glow over the scene. The creature, content in its butter river, lets out a yawn. Nearby, a flock of birds take flight"

image = pipe(
    prompt=prompt,
    negative_prompt="",
    num_inference_steps=28,
    guidance_scale=4.5,
    max_sequence_length=512,
).images[0]

Sending a different prompt to the T5 Text Encoder

You can send a different prompt to the CLIP Text Encoders and the T5 Text Encoder to prevent the prompt from being truncated by the CLIP Text Encoders and to improve generation.

The prompt with the CLIP Text Encoders is still truncated to the 77 token limit.

prompt = "A whimsical and creative image depicting a hybrid creature that is a mix of a waffle and a hippopotamus, basking in a river of melted butter amidst a breakfast-themed landscape. A river of warm, melted butter, pancake-like foliage in the background, a towering pepper mill standing in for a tree."

prompt_3 = "A whimsical and creative image depicting a hybrid creature that is a mix of a waffle and a hippopotamus, basking in a river of melted butter amidst a breakfast-themed landscape. It features the distinctive, bulky body shape of a hippo. However, instead of the usual grey skin, the creature’s body resembles a golden-brown, crispy waffle fresh off the griddle. The skin is textured with the familiar grid pattern of a waffle, each square filled with a glistening sheen of syrup. The environment combines the natural habitat of a hippo with elements of a breakfast table setting, a river of warm, melted butter, with oversized utensils or plates peeking out from the lush, pancake-like foliage in the background, a towering pepper mill standing in for a tree.  As the sun rises in this fantastical world, it casts a warm, buttery glow over the scene. The creature, content in its butter river, lets out a yawn. Nearby, a flock of birds take flight"

image = pipe(
    prompt=prompt,
    prompt_3=prompt_3,
    negative_prompt="",
    num_inference_steps=28,
    guidance_scale=4.5,
    max_sequence_length=512,
).images[0]

Tiny AutoEncoder for Stable Diffusion 3

Tiny AutoEncoder for Stable Diffusion (TAESD3) is a tiny distilled version of Stable Diffusion 3’s VAE by Ollin Boer Bohan that can decode StableDiffusion3Pipeline latents almost instantly.

To use with Stable Diffusion 3:

import torch
from diffusers import StableDiffusion3Pipeline, AutoencoderTiny

pipe = StableDiffusion3Pipeline.from_pretrained(
    "stabilityai/stable-diffusion-3-medium-diffusers", torch_dtype=torch.float16
)
pipe.vae = AutoencoderTiny.from_pretrained("madebyollin/taesd3", torch_dtype=torch.float16)
pipe = pipe.to("cuda")

prompt = "slice of delicious New York-style berry cheesecake"
image = pipe(prompt, num_inference_steps=25).images[0]
image.save("cheesecake.png")

Loading the original checkpoints via from_single_file

The SD3Transformer2DModel and StableDiffusion3Pipeline classes support loading the original checkpoints via the from_single_file method. This method allows you to load the original checkpoint files that were used to train the models.

Loading the original checkpoints for the SD3Transformer2DModel

from diffusers import SD3Transformer2DModel

model = SD3Transformer2DModel.from_single_file("https://huggingface.co/stabilityai/stable-diffusion-3-medium/blob/main/sd3_medium.safetensors")

Loading the single checkpoint for the StableDiffusion3Pipeline

Loading the single file checkpoint without T5

import torch
from diffusers import StableDiffusion3Pipeline

pipe = StableDiffusion3Pipeline.from_single_file(
    "https://huggingface.co/stabilityai/stable-diffusion-3-medium/blob/main/sd3_medium_incl_clips.safetensors",
    torch_dtype=torch.float16,
    text_encoder_3=None
)
pipe.enable_model_cpu_offload()

image = pipe("a picture of a cat holding a sign that says hello world").images[0]
image.save('sd3-single-file.png')

Loading the single file checkpoint with T5

The following example loads a checkpoint stored in a 8-bit floating point format which requires PyTorch 2.3 or later.

import torch
from diffusers import StableDiffusion3Pipeline

pipe = StableDiffusion3Pipeline.from_single_file(
    "https://huggingface.co/stabilityai/stable-diffusion-3-medium/blob/main/sd3_medium_incl_clips_t5xxlfp8.safetensors",
    torch_dtype=torch.float16,
)
pipe.enable_model_cpu_offload()

image = pipe("a picture of a cat holding a sign that says hello world").images[0]
image.save('sd3-single-file-t5-fp8.png')

StableDiffusion3Pipeline

class diffusers.StableDiffusion3Pipeline

< >

( transformer: SD3Transformer2DModel scheduler: FlowMatchEulerDiscreteScheduler vae: AutoencoderKL text_encoder: CLIPTextModelWithProjection tokenizer: CLIPTokenizer text_encoder_2: CLIPTextModelWithProjection tokenizer_2: CLIPTokenizer text_encoder_3: T5EncoderModel tokenizer_3: T5TokenizerFast )

Parameters

  • transformer (SD3Transformer2DModel) — Conditional Transformer (MMDiT) architecture to denoise the encoded image latents.
  • scheduler (FlowMatchEulerDiscreteScheduler) — A scheduler to be used in combination with transformer to denoise the encoded image latents.
  • vae (AutoencoderKL) — Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.
  • text_encoder (CLIPTextModelWithProjection) — CLIP, specifically the clip-vit-large-patch14 variant, with an additional added projection layer that is initialized with a diagonal matrix with the hidden_size as its dimension.
  • text_encoder_2 (CLIPTextModelWithProjection) — CLIP, specifically the laion/CLIP-ViT-bigG-14-laion2B-39B-b160k variant.
  • text_encoder_3 (T5EncoderModel) — Frozen text-encoder. Stable Diffusion 3 uses T5, specifically the t5-v1_1-xxl variant.
  • tokenizer (CLIPTokenizer) — Tokenizer of class CLIPTokenizer.
  • tokenizer_2 (CLIPTokenizer) — Second Tokenizer of class CLIPTokenizer.
  • tokenizer_3 (T5TokenizerFast) — Tokenizer of class T5Tokenizer.

__call__

< >

( prompt: Union = None prompt_2: Union = None prompt_3: Union = None height: Optional = None width: Optional = None num_inference_steps: int = 28 timesteps: List = None guidance_scale: float = 7.0 negative_prompt: Union = None negative_prompt_2: Union = None negative_prompt_3: Union = None num_images_per_prompt: Optional = 1 generator: Union = None latents: Optional = None prompt_embeds: Optional = None negative_prompt_embeds: Optional = None pooled_prompt_embeds: Optional = None negative_pooled_prompt_embeds: Optional = None output_type: Optional = 'pil' return_dict: bool = True joint_attention_kwargs: Optional = None clip_skip: Optional = None callback_on_step_end: Optional = None callback_on_step_end_tensor_inputs: List = ['latents'] max_sequence_length: int = 256 ) → ~pipelines.stable_diffusion_3.StableDiffusion3PipelineOutput or tuple

Parameters

  • 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.
  • prompt_2 (str or List[str], optional) — The prompt or prompts to be sent to tokenizer_2 and text_encoder_2. If not defined, prompt is will be used instead
  • prompt_3 (str or List[str], optional) — The prompt or prompts to be sent to tokenizer_3 and text_encoder_3. If not defined, prompt is will be used instead
  • height (int, optional, defaults to self.unet.config.sample_size * self.vae_scale_factor) — The height in pixels of the generated image. This is set to 1024 by default for the best results.
  • width (int, optional, defaults to self.unet.config.sample_size * self.vae_scale_factor) — The width in pixels of the generated image. This is set to 1024 by default for the best results.
  • 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.
  • 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.
  • guidance_scale (float, optional, defaults to 7.0) — 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.
  • 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).
  • negative_prompt_2 (str or List[str], optional) — 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 instead
  • negative_prompt_3 (str or List[str], optional) — The prompt or prompts not to guide the image generation to be sent to tokenizer_3 and text_encoder_3. If not defined, negative_prompt is used instead
  • num_images_per_prompt (int, optional, defaults to 1) — The number of images to generate per prompt.
  • generator (torch.Generator or List[torch.Generator], optional) — One or a list of torch generator(s) to make generation deterministic.
  • latents (torch.FloatTensor, 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 ge generated by sampling using the supplied random generator.
  • prompt_embeds (torch.FloatTensor, 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.FloatTensor, 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.
  • pooled_prompt_embeds (torch.FloatTensor, optional) — 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.
  • negative_pooled_prompt_embeds (torch.FloatTensor, optional) — 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.
  • 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_xl.StableDiffusionXLPipelineOutput instead of a plain tuple.
  • joint_attention_kwargs (dict, optional) — A kwargs dictionary that if specified is passed along to the AttentionProcessor as defined under self.processor in diffusers.models.attention_processor.
  • 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 256) — Maximum sequence length to use with the prompt.

Returns

~pipelines.stable_diffusion_3.StableDiffusion3PipelineOutput or tuple

~pipelines.stable_diffusion_3.StableDiffusion3PipelineOutput if return_dict is True, otherwise a tuple. When returning a tuple, the first element is a list with the generated images.

Function invoked when calling the pipeline for generation.

Examples:

>>> import torch
>>> from diffusers import StableDiffusion3Pipeline

>>> pipe = StableDiffusion3Pipeline.from_pretrained(
...     "stabilityai/stable-diffusion-3-medium-diffusers", torch_dtype=torch.float16
... )
>>> pipe.to("cuda")
>>> prompt = "A cat holding a sign that says hello world"
>>> image = pipe(prompt).images[0]
>>> image.save("sd3.png")

encode_prompt

< >

( prompt: Union prompt_2: Union prompt_3: Union device: Optional = None num_images_per_prompt: int = 1 do_classifier_free_guidance: bool = True negative_prompt: Union = None negative_prompt_2: Union = None negative_prompt_3: Union = None prompt_embeds: Optional = None negative_prompt_embeds: Optional = None pooled_prompt_embeds: Optional = None negative_pooled_prompt_embeds: Optional = None clip_skip: Optional = None max_sequence_length: int = 256 lora_scale: Optional = None )

Parameters

  • prompt (str or List[str], optional) — prompt to be encoded
  • prompt_2 (str or List[str], optional) — The prompt or prompts to be sent to the tokenizer_2 and text_encoder_2. If not defined, prompt is used in all text-encoders
  • prompt_3 (str or List[str], optional) — The prompt or prompts to be sent to the tokenizer_3 and text_encoder_3. If not defined, prompt is used in all text-encoders 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).
  • negative_prompt_2 (str or List[str], optional) — 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 all the text-encoders.
  • negative_prompt_2 (str or List[str], optional) — The prompt or prompts not to guide the image generation to be sent to tokenizer_3 and text_encoder_3. If not defined, negative_prompt is used in both text-encoders
  • prompt_embeds (torch.FloatTensor, 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.FloatTensor, 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.
  • pooled_prompt_embeds (torch.FloatTensor, optional) — 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.
  • negative_pooled_prompt_embeds (torch.FloatTensor, optional) — 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.
  • 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.
  • lora_scale (float, optional) — A lora scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded.
< > Update on GitHub

←Stable Diffusion 2 Stable Diffusion XL→