Diffusers documentation

Load community pipelines and components

You are viewing main version, which requires installation from source. If you'd like regular pip install, checkout the latest stable version (v0.27.1).
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

Load community pipelines and components

Community pipelines

Community pipelines are any DiffusionPipeline class that are different from the original implementation as specified in their paper (for example, the StableDiffusionControlNetPipeline corresponds to the Text-to-Image Generation with ControlNet Conditioning paper). They provide additional functionality or extend the original implementation of a pipeline.

There are many cool community pipelines like Speech to Image or Composable Stable Diffusion, and you can find all the official community pipelines here.

To load any community pipeline on the Hub, pass the repository id of the community pipeline to the custom_pipeline argument and the model repository where you’d like to load the pipeline weights and components from. For example, the example below loads a dummy pipeline from hf-internal-testing/diffusers-dummy-pipeline and the pipeline weights and components from google/ddpm-cifar10-32:

🔒 By loading a community pipeline from the Hugging Face Hub, you are trusting that the code you are loading is safe. Make sure to inspect the code online before loading and running it automatically!

from diffusers import DiffusionPipeline

pipeline = DiffusionPipeline.from_pretrained(
    "google/ddpm-cifar10-32", custom_pipeline="hf-internal-testing/diffusers-dummy-pipeline", use_safetensors=True
)

Loading an official community pipeline is similar, but you can mix loading weights from an official repository id and pass pipeline components directly. The example below loads the community CLIP Guided Stable Diffusion pipeline, and you can pass the CLIP model components directly to it:

from diffusers import DiffusionPipeline
from transformers import CLIPImageProcessor, CLIPModel

clip_model_id = "laion/CLIP-ViT-B-32-laion2B-s34B-b79K"

feature_extractor = CLIPImageProcessor.from_pretrained(clip_model_id)
clip_model = CLIPModel.from_pretrained(clip_model_id)

pipeline = DiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
    custom_pipeline="clip_guided_stable_diffusion",
    clip_model=clip_model,
    feature_extractor=feature_extractor,
    use_safetensors=True,
)

Load from a local file

Community pipelines can also be loaded from a local file if you pass a file path instead. The path to the passed directory must contain a pipeline.py file that contains the pipeline class in order to successfully load it.

pipeline = DiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
    custom_pipeline="./path/to/pipeline_directory/",
    clip_model=clip_model,
    feature_extractor=feature_extractor,
    use_safetensors=True,
)

Load from a specific version

By default, community pipelines are loaded from the latest stable version of Diffusers. To load a community pipeline from another version, use the custom_revision parameter.

main
older version

For example, to load from the main branch:

pipeline = DiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
    custom_pipeline="clip_guided_stable_diffusion",
    custom_revision="main",
    clip_model=clip_model,
    feature_extractor=feature_extractor,
    use_safetensors=True,
)

For more information about community pipelines, take a look at the Community pipelines guide for how to use them and if you’re interested in adding a community pipeline check out the How to contribute a community pipeline guide!

Community components

Community components allow users to build pipelines that may have customized components that are not a part of Diffusers. If your pipeline has custom components that Diffusers doesn’t already support, you need to provide their implementations as Python modules. These customized components could be a VAE, UNet, and scheduler. In most cases, the text encoder is imported from the Transformers library. The pipeline code itself can also be customized.

This section shows how users should use community components to build a community pipeline.

You’ll use the showlab/show-1-base pipeline checkpoint as an example. So, let’s start loading the components:

  1. Import and load the text encoder from Transformers:
from transformers import T5Tokenizer, T5EncoderModel

pipe_id = "showlab/show-1-base"
tokenizer = T5Tokenizer.from_pretrained(pipe_id, subfolder="tokenizer")
text_encoder = T5EncoderModel.from_pretrained(pipe_id, subfolder="text_encoder")
  1. Load a scheduler:
from diffusers import DPMSolverMultistepScheduler

scheduler = DPMSolverMultistepScheduler.from_pretrained(pipe_id, subfolder="scheduler")
  1. Load an image processor:
from transformers import CLIPFeatureExtractor

feature_extractor = CLIPFeatureExtractor.from_pretrained(pipe_id, subfolder="feature_extractor")

In steps 4 and 5, the custom UNet and pipeline implementation must match the format shown in their files for this example to work.

  1. Now you’ll load a custom UNet, which in this example, has already been implemented in the showone_unet_3d_condition.py script for your convenience. You’ll notice the UNet3DConditionModel class name is changed to ShowOneUNet3DConditionModel because UNet3DConditionModel already exists in Diffusers. Any components needed for the ShowOneUNet3DConditionModel class should be placed in the showone_unet_3d_condition.py script.

Once this is done, you can initialize the UNet:

from showone_unet_3d_condition import ShowOneUNet3DConditionModel

unet = ShowOneUNet3DConditionModel.from_pretrained(pipe_id, subfolder="unet")
  1. Finally, you’ll load the custom pipeline code. For this example, it has already been created for you in the pipeline_t2v_base_pixel.py script. This script contains a custom TextToVideoIFPipeline class for generating videos from text. Just like the custom UNet, any code needed for the custom pipeline to work should go in the pipeline_t2v_base_pixel.py script.

Once everything is in place, you can initialize the TextToVideoIFPipeline with the ShowOneUNet3DConditionModel:

from pipeline_t2v_base_pixel import TextToVideoIFPipeline
import torch

pipeline = TextToVideoIFPipeline(
    unet=unet,
    text_encoder=text_encoder,
    tokenizer=tokenizer,
    scheduler=scheduler,
    feature_extractor=feature_extractor
)
pipeline = pipeline.to(device="cuda")
pipeline.torch_dtype = torch.float16

Push the pipeline to the Hub to share with the community!

pipeline.push_to_hub("custom-t2v-pipeline")

After the pipeline is successfully pushed, you need a couple of changes:

  1. Change the _class_name attribute in model_index.json to "pipeline_t2v_base_pixel" and "TextToVideoIFPipeline".
  2. Upload showone_unet_3d_condition.py to the unet directory.
  3. Upload pipeline_t2v_base_pixel.py to the pipeline base directory.

To run inference, simply add the trust_remote_code argument while initializing the pipeline to handle all the “magic” behind the scenes.

from diffusers import DiffusionPipeline
import torch

pipeline = DiffusionPipeline.from_pretrained(
    "<change-username>/<change-id>", trust_remote_code=True, torch_dtype=torch.float16
).to("cuda")

prompt = "hello"

# Text embeds
prompt_embeds, negative_embeds = pipeline.encode_prompt(prompt)

# Keyframes generation (8x64x40, 2fps)
video_frames = pipeline(
    prompt_embeds=prompt_embeds,
    negative_prompt_embeds=negative_embeds,
    num_frames=8,
    height=40,
    width=64,
    num_inference_steps=2,
    guidance_scale=9.0,
    output_type="pt"
).frames

As an additional reference example, you can refer to the repository structure of stabilityai/japanese-stable-diffusion-xl, that makes use of the trust_remote_code feature:


from diffusers import DiffusionPipeline
import torch

pipeline = DiffusionPipeline.from_pretrained(
    "stabilityai/japanese-stable-diffusion-xl", trust_remote_code=True
)
pipeline.to("cuda")

# if using torch < 2.0
# pipeline.enable_xformers_memory_efficient_attention()

prompt = "柴犬、カラフルアート"

image = pipeline(prompt=prompt).images[0]