Diffusers documentation

Model files and layouts

You are viewing main version, which requires installation from source. If you'd like regular pip install, checkout the latest stable version (v0.30.3).
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

Model files and layouts

Diffusion models are saved in various file types and organized in different layouts. Diffusers stores model weights as safetensors files in Diffusers-multifolder layout and it also supports loading files (like safetensors and ckpt files) from a single-file layout which is commonly used in the diffusion ecosystem.

Each layout has its own benefits and use cases, and this guide will show you how to load the different files and layouts, and how to convert them.

Files

PyTorch model weights are typically saved with Python’s pickle utility as ckpt or bin files. However, pickle is not secure and pickled files may contain malicious code that can be executed. This vulnerability is a serious concern given the popularity of model sharing. To address this security issue, the Safetensors library was developed as a secure alternative to pickle, which saves models as safetensors files.

safetensors

Learn more about the design decisions and why safetensor files are preferred for saving and loading model weights in the Safetensors audited as really safe and becoming the default blog post.

Safetensors is a safe and fast file format for securely storing and loading tensors. Safetensors restricts the header size to limit certain types of attacks, supports lazy loading (useful for distributed setups), and has generally faster loading speeds.

Make sure you have the Safetensors library installed.

!pip install safetensors

Safetensors stores weights in a safetensors file. Diffusers loads safetensors files by default if they’re available and the Safetensors library is installed. There are two ways safetensors files can be organized:

  1. Diffusers-multifolder layout: there may be several separate safetensors files, one for each pipeline component (text encoder, UNet, VAE), organized in subfolders (check out the stable-diffusion-v1-5/stable-diffusion-v1-5 repository as an example)
  2. single-file layout: all the model weights may be saved in a single file (check out the WarriorMama777/OrangeMixs repository as an example)
multifolder
single file

Use the from_pretrained() method to load a model with safetensors files stored in multiple folders.

from diffusers import DiffusionPipeline

pipeline = DiffusionPipeline.from_pretrained(
    "stable-diffusion-v1-5/stable-diffusion-v1-5",
    use_safetensors=True
)

LoRA files

LoRA is a lightweight adapter that is fast and easy to train, making them especially popular for generating images in a certain way or style. These adapters are commonly stored in a safetensors file, and are widely popular on model sharing platforms like civitai.

LoRAs are loaded into a base model with the load_lora_weights() method.

from diffusers import StableDiffusionXLPipeline
import torch

# base model
pipeline = StableDiffusionXLPipeline.from_pretrained(
    "Lykon/dreamshaper-xl-1-0", torch_dtype=torch.float16, variant="fp16"
).to("cuda")

# download LoRA weights
!wget https://civitai.com/api/download/models/168776 -O blueprintify.safetensors

# load LoRA weights
pipeline.load_lora_weights(".", weight_name="blueprintify.safetensors")
prompt = "bl3uprint, a highly detailed blueprint of the empire state building, explaining how to build all parts, many txt, blueprint grid backdrop"
negative_prompt = "lowres, cropped, worst quality, low quality, normal quality, artifacts, signature, watermark, username, blurry, more than one bridge, bad architecture"

image = pipeline(
    prompt=prompt,
    negative_prompt=negative_prompt,
    generator=torch.manual_seed(0),
).images[0]
image

ckpt

Pickled files may be unsafe because they can be exploited to execute malicious code. It is recommended to use safetensors files instead where possible, or convert the weights to safetensors files.

PyTorch’s torch.save function uses Python’s pickle utility to serialize and save models. These files are saved as a ckpt file and they contain the entire model’s weights.

Use the from_single_file() method to directly load a ckpt file.

from diffusers import StableDiffusionPipeline

pipeline = StableDiffusionPipeline.from_single_file(
    "https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5/blob/main/v1-5-pruned.ckpt"
)

Storage layout

There are two ways model files are organized, either in a Diffusers-multifolder layout or in a single-file layout. The Diffusers-multifolder layout is the default, and each component file (text encoder, UNet, VAE) is stored in a separate subfolder. Diffusers also supports loading models from a single-file layout where all the components are bundled together.

Diffusers-multifolder

The Diffusers-multifolder layout is the default storage layout for Diffusers. Each component’s (text encoder, UNet, VAE) weights are stored in a separate subfolder. The weights can be stored as safetensors or ckpt files.

multifolder layout
UNet subfolder

To load from Diffusers-multifolder layout, use the from_pretrained() method.

from diffusers import DiffusionPipeline

pipeline = DiffusionPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0",
    torch_dtype=torch.float16,
    variant="fp16",
    use_safetensors=True,
).to("cuda")

Benefits of using the Diffusers-multifolder layout include:

  1. Faster to load each component file individually or in parallel.

  2. Reduced memory usage because you only load the components you need. For example, models like SDXL Turbo, SDXL Lightning, and Hyper-SD have the same components except for the UNet. You can reuse their shared components with the from_pipe() method without consuming any additional memory (take a look at the Reuse a pipeline guide) and only load the UNet. This way, you don’t need to download redundant components and unnecessarily use more memory.

    import torch
    from diffusers import StableDiffusionXLPipeline, UNet2DConditionModel, EulerDiscreteScheduler
    
    # download one model
    sdxl_pipeline = StableDiffusionXLPipeline.from_pretrained(
        "stabilityai/stable-diffusion-xl-base-1.0",
        torch_dtype=torch.float16,
        variant="fp16",
        use_safetensors=True,
    ).to("cuda")
    
    # switch UNet for another model
    unet = UNet2DConditionModel.from_pretrained(
        "stabilityai/sdxl-turbo",
        subfolder="unet",
        torch_dtype=torch.float16,
        variant="fp16",
        use_safetensors=True
    )
    # reuse all the same components in new model except for the UNet
    turbo_pipeline = StableDiffusionXLPipeline.from_pipe(
        sdxl_pipeline, unet=unet,
    ).to("cuda")
    turbo_pipeline.scheduler = EulerDiscreteScheduler.from_config(
        turbo_pipeline.scheduler.config,
        timestep+spacing="trailing"
    )
    image = turbo_pipeline(
        "an astronaut riding a unicorn on mars",
        num_inference_steps=1,
        guidance_scale=0.0,
    ).images[0]
    image
  3. Reduced storage requirements because if a component, such as the SDXL VAE, is shared across multiple models, you only need to download and store a single copy of it instead of downloading and storing it multiple times. For 10 SDXL models, this can save ~3.5GB of storage. The storage savings is even greater for newer models like PixArt Sigma, where the text encoder alone is ~19GB!

  4. Flexibility to replace a component in the model with a newer or better version.

    from diffusers import DiffusionPipeline, AutoencoderKL
    
    vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16, use_safetensors=True)
    pipeline = DiffusionPipeline.from_pretrained(
        "stabilityai/stable-diffusion-xl-base-1.0",
        vae=vae,
        torch_dtype=torch.float16,
        variant="fp16",
        use_safetensors=True,
    ).to("cuda")
  5. More visibility and information about a model’s components, which are stored in a config.json file in each component subfolder.

Single-file

The single-file layout stores all the model weights in a single file. All the model components (text encoder, UNet, VAE) weights are kept together instead of separately in subfolders. This can be a safetensors or ckpt file.

To load from a single-file layout, use the from_single_file() method.

import torch
from diffusers import StableDiffusionXLPipeline

pipeline = StableDiffusionXLPipeline.from_single_file(
    "https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/sd_xl_base_1.0.safetensors",
    torch_dtype=torch.float16,
    variant="fp16",
    use_safetensors=True,
).to("cuda")

Benefits of using a single-file layout include:

  1. Easy compatibility with diffusion interfaces such as ComfyUI or Automatic1111 which commonly use a single-file layout.
  2. Easier to manage (download and share) a single file.

Convert layout and files

Diffusers provides many scripts and methods to convert storage layouts and file formats to enable broader support across the diffusion ecosystem.

Take a look at the diffusers/scripts collection to find a script that fits your conversion needs.

Scripts that have ”to_diffusers” appended at the end mean they convert a model to the Diffusers-multifolder layout. Each script has their own specific set of arguments for configuring the conversion, so make sure you check what arguments are available!

For example, to convert a Stable Diffusion XL model stored in Diffusers-multifolder layout to a single-file layout, run the convert_diffusers_to_original_sdxl.py script. Provide the path to the model to convert, and the path to save the converted model to. You can optionally specify whether you want to save the model as a safetensors file and whether to save the model in half-precision.

python convert_diffusers_to_original_sdxl.py --model_path path/to/model/to/convert --checkpoint_path path/to/save/model/to --use_safetensors

You can also save a model to Diffusers-multifolder layout with the save_pretrained() method. This creates a directory for you if it doesn’t already exist, and it also saves the files as a safetensors file by default.

from diffusers import StableDiffusionXLPipeline

pipeline = StableDiffusionXLPipeline.from_single_file(
    "https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/sd_xl_base_1.0.safetensors",
)
pipeline.save_pretrained()

Lastly, there are also Spaces, such as SD To Diffusers and SD-XL To Diffusers, that provide a more user-friendly interface for converting models to Diffusers-multifolder layout. This is the easiest and most convenient option for converting layouts, and it’ll open a PR on your model repository with the converted files. However, this option is not as reliable as running a script, and the Space may fail for more complicated models.

Single-file layout usage

Now that you’re familiar with the differences between the Diffusers-multifolder and single-file layout, this section shows you how to load models and pipeline components, customize configuration options for loading, and load local files with the from_single_file() method.

Load a pipeline or model

Pass the file path of the pipeline or model to the from_single_file() method to load it.

pipeline
model
from diffusers import StableDiffusionXLPipeline

ckpt_path = "https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/sd_xl_base_1.0_0.9vae.safetensors"
pipeline = StableDiffusionXLPipeline.from_single_file(ckpt_path)

Customize components in the pipeline by passing them directly to the from_single_file() method. For example, you can use a different scheduler in a pipeline.

from diffusers import StableDiffusionXLPipeline, DDIMScheduler

ckpt_path = "https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/sd_xl_base_1.0_0.9vae.safetensors"
scheduler = DDIMScheduler()
pipeline = StableDiffusionXLPipeline.from_single_file(ckpt_path, scheduler=scheduler)

Or you could use a ControlNet model in the pipeline.

from diffusers import StableDiffusionControlNetPipeline, ControlNetModel

ckpt_path = "https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5/blob/main/v1-5-pruned-emaonly.safetensors"
controlnet = ControlNetModel.from_pretrained("lllyasviel/control_v11p_sd15_canny")
pipeline = StableDiffusionControlNetPipeline.from_single_file(ckpt_path, controlnet=controlnet)

Customize configuration options

Models have a configuration file that define their attributes like the number of inputs in a UNet. Pipelines configuration options are available in the pipeline’s class. For example, if you look at the StableDiffusionXLInstructPix2PixPipeline class, there is an option to scale the image latents with the is_cosxl_edit parameter.

These configuration files can be found in the models Hub repository or another location from which the configuration file originated (for example, a GitHub repository or locally on your device).

Hub configuration file
original configuration file

The from_single_file() method automatically maps the checkpoint to the appropriate model repository, but there are cases where it is useful to use the config parameter. For example, if the model components in the checkpoint are different from the original checkpoint or if a checkpoint doesn’t have the necessary metadata to correctly determine the configuration to use for the pipeline.

The from_single_file() method automatically determines the configuration to use from the configuration file in the model repository. You could also explicitly specify the configuration to use by providing the repository id to the config parameter.

from diffusers import StableDiffusionXLPipeline

ckpt_path = "https://huggingface.co/segmind/SSD-1B/blob/main/SSD-1B.safetensors"
repo_id = "segmind/SSD-1B"

pipeline = StableDiffusionXLPipeline.from_single_file(ckpt_path, config=repo_id)

The model loads the configuration file for the UNet, VAE, and text encoder from their respective subfolders in the repository.

While the configuration files specify the pipeline or models default parameters, you can override them by providing the parameters directly to the from_single_file() method. Any parameter supported by the model or pipeline class can be configured in this way.

pipeline
model

For example, to scale the image latents in StableDiffusionXLInstructPix2PixPipeline pass the is_cosxl_edit parameter.

from diffusers import StableDiffusionXLInstructPix2PixPipeline

ckpt_path = "https://huggingface.co/stabilityai/cosxl/blob/main/cosxl_edit.safetensors"
pipeline = StableDiffusionXLInstructPix2PixPipeline.from_single_file(ckpt_path, config="diffusers/sdxl-instructpix2pix-768", is_cosxl_edit=True)

Local files

In Diffusers>=v0.28.0, the from_single_file() method attempts to configure a pipeline or model by inferring the model type from the keys in the checkpoint file. The inferred model type is used to determine the appropriate model repository on the Hugging Face Hub to configure the model or pipeline.

For example, any single file checkpoint based on the Stable Diffusion XL base model will use the stabilityai/stable-diffusion-xl-base-1.0 model repository to configure the pipeline.

But if you’re working in an environment with restricted internet access, you should download the configuration files with the snapshot_download function, and the model checkpoint with the hf_hub_download function. By default, these files are downloaded to the Hugging Face Hub cache directory, but you can specify a preferred directory to download the files to with the local_dir parameter.

Pass the configuration and checkpoint paths to the from_single_file() method to load locally.

Hub cache directory
specific local directory
from huggingface_hub import hf_hub_download, snapshot_download

my_local_checkpoint_path = hf_hub_download(
    repo_id="segmind/SSD-1B",
    filename="SSD-1B.safetensors"
)

my_local_config_path = snapshot_download(
    repo_id="segmind/SSD-1B",
    allow_patterns=["*.json", "**/*.json", "*.txt", "**/*.txt"]
)

pipeline = StableDiffusionXLPipeline.from_single_file(my_local_checkpoint_path, config=my_local_config_path, local_files_only=True)

Local files without symlink

In huggingface_hub>=v0.23.0, the local_dir_use_symlinks argument isn’t necessary for the hf_hub_download and snapshot_download functions.

The from_single_file() method relies on the huggingface_hub caching mechanism to fetch and store checkpoints and configuration files for models and pipelines. If you’re working with a file system that does not support symlinking, you should download the checkpoint file to a local directory first, and disable symlinking with the local_dir_use_symlink=False parameter in the hf_hub_download function and snapshot_download functions.

from huggingface_hub import hf_hub_download, snapshot_download

my_local_checkpoint_path = hf_hub_download(
    repo_id="segmind/SSD-1B",
    filename="SSD-1B.safetensors"
    local_dir="my_local_checkpoints",
    local_dir_use_symlinks=False
)
print("My local checkpoint: ", my_local_checkpoint_path)

my_local_config_path = snapshot_download(
    repo_id="segmind/SSD-1B",
    allow_patterns=["*.json", "**/*.json", "*.txt", "**/*.txt"]
    local_dir_use_symlinks=False,
)
print("My local config: ", my_local_config_path)

Then you can pass the local paths to the pretrained_model_link_or_path and config parameters.

pipeline = StableDiffusionXLPipeline.from_single_file(my_local_checkpoint_path, config=my_local_config_path, local_files_only=True)
< > Update on GitHub