Please have a look at the following table to get an overview of all community examples. Click on the **Code Example** to get a copy-and-paste ready code example that you can try out.
If a community doesn't work as expected, please open an issue and ping the author on it.
| CLIP Guided Stable Diffusion | Doing CLIP guidance for text to image generation with Stable Diffusion | [CLIP Guided Stable Diffusion](#clip-guided-stable-diffusion) | [](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/CLIP_Guided_Stable_diffusion_with_diffusers.ipynb) | [Suraj Patil](https://github.com/patil-suraj/) |
| One Step U-Net (Dummy) | Example showcasing of how to use Community Pipelines (see https://github.com/huggingface/diffusers/issues/841) | [One Step U-Net](#one-step-unet) | - | [Patrick von Platen](https://github.com/patrickvonplaten/) |
| Stable Diffusion Interpolation | Interpolate the latent space of Stable Diffusion between different prompts/seeds | [Stable Diffusion Interpolation](#stable-diffusion-interpolation) | - | [Nate Raw](https://github.com/nateraw/) |
| Stable Diffusion Mega | **One** Stable Diffusion Pipeline with all functionalities of [Text2Image](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py), [Image2Image](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py) and [Inpainting](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint.py) | [Stable Diffusion Mega](#stable-diffusion-mega) | - | [Patrick von Platen](https://github.com/patrickvonplaten/) |
| Long Prompt Weighting Stable Diffusion | **One** Stable Diffusion Pipeline without tokens length limit, and support parsing weighting in prompt. | [Long Prompt Weighting Stable Diffusion](#long-prompt-weighting-stable-diffusion) | - | [SkyTNT](https://github.com/SkyTNT) |
| Speech to Image | Using automatic-speech-recognition to transcribe text and Stable Diffusion to generate images | [Speech to Image](#speech-to-image) | - | [Mikail Duzenli](https://github.com/MikailINTech)
| Wild Card Stable Diffusion | Stable Diffusion Pipeline that supports prompts that contain wildcard terms (indicated by surrounding double underscores), with values instantiated randomly from a corresponding txt file or a dictionary of possible values | [Wildcard Stable Diffusion](#wildcard-stable-diffusion) | - | [Shyam Sudhakaran](https://github.com/shyamsn97) |
| [Composable Stable Diffusion](https://energy-based-model.github.io/Compositional-Visual-Generation-with-Composable-Diffusion-Models/) | Stable Diffusion Pipeline that supports prompts that contain "|" in prompts (as an AND condition) and weights (separated by "|" as well) to positively / negatively weight prompts. | [Composable Stable Diffusion](#composable-stable-diffusion) | - | [Mark Rich](https://github.com/MarkRich) |
| Seed Resizing Stable Diffusion| Stable Diffusion Pipeline that supports resizing an image and retaining the concepts of the 512 by 512 generation. | [Seed Resizing](#seed-resizing) | - | [Mark Rich](https://github.com/MarkRich) |
| Image to Image Inpainting Stable Diffusion | Stable Diffusion Pipeline that enables the overlaying of two images and subsequent inpainting| [Image to Image Inpainting Stable Diffusion](#image-to-image-inpainting-stable-diffusion) | - | [Alex McKinney](https://github.com/vvvm23) |
| Text Based Inpainting Stable Diffusion | Stable Diffusion Inpainting Pipeline that enables passing a text prompt to generate the mask for inpainting| [Text Based Inpainting Stable Diffusion](#image-to-image-inpainting-stable-diffusion) | - | [Dhruv Karan](https://github.com/unography) |
| K-Diffusion Stable Diffusion | Run Stable Diffusion with any of [K-Diffusion's samplers](https://github.com/crowsonkb/k-diffusion/blob/master/k_diffusion/sampling.py) | [Stable Diffusion with K Diffusion](#stable-diffusion-with-k-diffusion) | - | [Patrick von Platen](https://github.com/patrickvonplaten/) |
| Checkpoint Merger Pipeline | Diffusion Pipeline that enables merging of saved model checkpoints | [Checkpoint Merger Pipeline](#checkpoint-merger-pipeline) | - | [Naga Sai Abhinay Devarinti](https://github.com/Abhinay1997/) |
Stable Diffusion v1.1-1.4 Comparison | Run all 4 model checkpoints for Stable Diffusion and compare their results together | [Stable Diffusion Comparison](#stable-diffusion-comparisons) | - | [Suvaditya Mukherjee](https://github.com/suvadityamuk) |
MagicMix | Diffusion Pipeline for semantic mixing of an image and a text prompt | [MagicMix](#magic-mix) | - | [Partho Das](https://github.com/daspartho) |
| UnCLIP Text Interpolation Pipeline | Diffusion Pipeline that allows passing two prompts and produces images while interpolating between the text-embeddings of the two prompts | [UnCLIP Text Interpolation Pipeline](#unclip-text-interpolation-pipeline) | - | [Naga Sai Abhinay Devarinti](https://github.com/Abhinay1997/) |
| UnCLIP Image Interpolation Pipeline | Diffusion Pipeline that allows passing two images/image_embeddings and produces images while interpolating between their image-embeddings | [UnCLIP Image Interpolation Pipeline](#unclip-image-interpolation-pipeline) | - | [Naga Sai Abhinay Devarinti](https://github.com/Abhinay1997/) |
To load a custom pipeline you just need to pass the `custom_pipeline` argument to `DiffusionPipeline`, as one of the files in `diffusers/examples/community`. Feel free to send a PR with your own pipelines, we will merge them quickly.
prompt = "fantasy book cover, full moon, fantasy forest landscape, golden vector elements, fantasy magic, dark light night, intricate, elegant, sharp focus, illustration, highly detailed, digital painting, concept art, matte, art by WLOP and Artgerm and Albert Bierstadt, masterpiece"
**Note**: This community pipeline is not useful as a feature, but rather just serves as an example of how community pipelines can be added (see https://github.com/huggingface/diffusers/issues/841).
### Stable Diffusion Interpolation
The following code can be run on a GPU of at least 8GB VRAM and should take approximately 5 minutes.
```python
from diffusers import DiffusionPipeline
import torch
pipe = DiffusionPipeline.from_pretrained(
"CompVis/stable-diffusion-v1-4",
revision='fp16',
torch_dtype=torch.float16,
safety_checker=None, # Very important for videos...lots of false positives while interpolating
custom_pipeline="interpolate_stable_diffusion",
).to('cuda')
pipe.enable_attention_slicing()
frame_filepaths = pipe.walk(
prompts=['a dog', 'a cat', 'a horse'],
seeds=[42, 1337, 1234],
num_interpolation_steps=16,
output_dir='./dreams',
batch_size=4,
height=512,
width=512,
guidance_scale=8.5,
num_inference_steps=50,
)
```
The output of the `walk(...)` function returns a list of images saved under the folder as defined in `output_dir`. You can use these images to create videos of stable diffusion.
> **Please have a look at https://github.com/nateraw/stable-diffusion-videos for more in-detail information on how to create videos using stable diffusion as well as more feature-complete functionality.**
if you see `Token indices sequence length is longer than the specified maximum sequence length for this model ( *** > 77 ) . Running this sequence through the model will result in indexing errors`. Do not worry, it is normal.
Following the great examples from https://github.com/jtkelm2/stable-diffusion-webui-1/blob/master/scripts/wildcards.py and https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Custom-Scripts#wildcards, here's a minimal implementation that allows for users to add "wildcards", denoted by `__wildcard__` to prompts that are used as placeholders for randomly sampled values given by either a dictionary or a `.txt` file. For example:
Say we have a prompt:
```
prompt = "__animal__ sitting on a __object__ wearing a __clothing__"
```
We can then define possible values to be sampled for `animal`, `object`, and `clothing`. These can either be from a `.txt` with the same name as the category.
The possible values can also be defined / combined by using a dictionary like: `{"animal":["dog", "cat", mouse"]}`.
The actual pipeline works just like `StableDiffusionPipeline`, except the `__call__` method takes in:
`wildcard_files`: list of file paths for wild card replacement
`wildcard_option_dict`: dict with key as `wildcard` and values as a list of possible replacements
`num_prompt_samples`: number of prompts to sample, uniformly sampling wildcards
Test seed resizing. Originally generate an image in 512 by 512, then generate image with same seed at 512 by 592 using seed resizing. Finally, generate 512 by 592 using original stable diffusion pipeline.
```python
import torch as th
import numpy as np
from diffusers import DiffusionPipeline
has_cuda = th.cuda.is_available()
device = th.device('cpu' if not has_cuda else 'cuda')
The following code can generate an images from texts in different languages using the pre-trained [mBART-50 many-to-one multilingual machine translation model](https://huggingface.co/facebook/mbart-large-50-many-to-one-mmt) and Stable Diffusion.
```python
from PIL import Image
import torch
from diffusers import DiffusionPipeline
from transformers import (
pipeline,
MBart50TokenizerFast,
MBartForConditionalGeneration,
)
device = "cuda" if torch.cuda.is_available() else "cpu"
device_dict = {"cuda": 0, "cpu": -1}
# helper function taken from: https://huggingface.co/blog/stable_diffusion
Similar to the standard stable diffusion inpainting example, except with the addition of an `inner_image` argument.
`image`, `inner_image`, and `mask` should have the same dimensions. `inner_image` should have an alpha (transparency) channel.
The aim is to overlay two images, then mask out the boundary between `image` and `inner_image` to allow stable diffusion to make the connection more seamless.
For example, this could be used to place a logo on a shirt and make it blend seamlessly.
Based https://arxiv.org/abs/2208.04202, this is used for diffusion on discrete data - eg, discreate image data, DNA sequence data. An unconditional discreate image can be generated like this:
Based on the AUTOMATIC1111/webui for checkpoint merging. This is a custom pipeline that merges upto 3 pretrained model checkpoints as long as they are in the HuggingFace model_index.json format.
The checkpoint merging is currently memory intensive as it modifies the weights of a DiffusionPipeline object in place. Expect atleast 13GB RAM Usage on Kaggle GPU kernels and
on colab you might run out of the 12GB memory even while merging two checkpoints.
Usage:-
```python
from diffusers import DiffusionPipeline
#Return a CheckpointMergerPipeline class that allows you to merge checkpoints.
#The checkpoint passed here is ignored. But still pass one of the checkpoints you plan to
#The pipeline with the merged checkpoints is returned in all the scenarios
#Compatible checkpoints a.k.a matched model_index.json files. Ignores the meta attributes in model_index.json during comparision.( attrs with _ as prefix )
#Three checkpoint merging. Only "add_difference" method actually works on all three checkpoints. Using any other options will ignore the 3rd checkpoint.
This Community Pipeline enables the comparison between the 4 checkpoints that exist for Stable Diffusion. They can be found through the following links:
As a result, you can look at a grid of all 4 generated images being shown together, that captures a difference the advancement of the training between the 4 checkpoints.
### Magic Mix
Implementation of the [MagicMix: Semantic Mixing with Diffusion Models](https://arxiv.org/abs/2210.16056) paper. This is a Diffusion Pipeline for semantic mixing of an image and a text prompt to create a new concept while preserving the spatial layout and geometry of the subject in the image. The pipeline takes an image that provides the layout semantics and a prompt that provides the content semantics for the mixing process.
There are 3 parameters for the method-
-`mix_factor`: It is the interpolation constant used in the layout generation phase. The greater the value of `mix_factor`, the greater the influence of the prompt on the layout generation process.
-`kmax` and `kmin`: These determine the range for the layout and content generation process. A higher value of kmax results in loss of more information about the layout of the original image and a higher value of kmin results in more steps for content generation process.
The `mix_img` is a PIL image that can be saved locally or displayed directly in a google colab. Generated image is a mix of the layout semantics of the given image and the content semantics of the prompt.
E.g. the above script generates the following image:
UnCLIPPipeline("kakaobrain/karlo-v1-alpha") provide a prior model that can generate clip image embedding from text.
StableDiffusionImageVariationPipeline("lambdalabs/sd-image-variations-diffusers") provide a decoder model than can generate images from clip image embedding.
```python
import torch
from diffusers import DiffusionPipeline
device = torch.device("cpu" if not torch.cuda.is_available() else "cuda")
pipeline = DiffusionPipeline.from_pretrained(
"kakaobrain/karlo-v1-alpha",
torch_dtype=torch.float16,
custom_pipeline="stable_unclip",
decoder_pipe_kwargs=dict(
image_encoder=None,
),
)
pipeline.to(device)
prompt = "a shiba inu wearing a beret and black turtleneck"
This Diffusion Pipeline takes two prompts and interpolates between the two input prompts using spherical interpolation ( slerp ). The input prompts are converted to text embeddings by the pipeline's text_encoder and the interpolation is done on the resulting text_embeddings over the number of steps specified. Defaults to 5 steps.
```python
import torch
from diffusers import DiffusionPipeline
device = torch.device("cpu" if not torch.cuda.is_available() else "cuda")
pipe = DiffusionPipeline.from_pretrained(
"kakaobrain/karlo-v1-alpha",
torch_dtype=torch.float16,
custom_pipeline="unclip_text_interpolation"
)
pipe.to(device)
start_prompt = "A photograph of an adult lion"
end_prompt = "A photograph of a lion cub"
#For best results keep the prompts close in length to each other. Of course, feel free to try out with differing lengths.
This Diffusion Pipeline takes two images or an image_embeddings tensor of size 2 and interpolates between their embeddings using spherical interpolation ( slerp ). The input images/image_embeddings are converted to image embeddings by the pipeline's image_encoder and the interpolation is done on the resulting image_embeddings over the number of steps specified. Defaults to 5 steps.
```python
import torch
from diffusers import DiffusionPipeline
from PIL import Image
device = torch.device("cpu" if not torch.cuda.is_available() else "cuda")
dtype = torch.float16 if torch.cuda.is_available() else torch.bfloat16
