Home

Awesome

Latent Consistency Models

Official Repository of the paper: Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference.

Official Repository of the paper: LCM-LoRA: A Universal Stable-Diffusion Acceleration Module.

Project Page: https://latent-consistency-models.github.io

Try our Demos:

🤗 Hugging Face Demo: Hugging Face Spaces 🔥🔥🔥

Replicate Demo: Replicate

OpenXLab Demo: Open in OpenXLab

<img src="./lcm_logo.png" width="4%" alt="" /> LCM Community: Join our LCM discord channels <a href="https://discord.gg/KM6aeW6CgD" style="text-decoration:none;"> <img src="https://user-images.githubusercontent.com/25839884/218347213-c080267f-cbb6-443e-8532-8e1ed9a58ea9.png" width="3%" alt="" /></a> for discussions. Coders are welcome to contribute.

Breaking News 🔥🔥!!

News

🔥 Image2Image Demos (Image-to-Image):

We support Img2Img now! Try the impressive img2img demos here: Replicate, SD-webui, ComfyUI, Colab

Local gradio for img2img is on the way!

<p align="center"> <img src="/img2img_demo/taylor.png", width="50%"><img src="/img2img_demo/elon.png", width="49%"> </p>

🔥 Local gradio Demos (Text-to-Image):

To run the model locally, you can download the "local_gradio" folder:

  1. Install Pytorch (CUDA). MacOS system can download the "MPS" version of Pytorch. Please refer to: https://pytorch.org. Install Intel Extension for Pytorch as well if you're using Intel GPUs.
  2. Install the main library:
pip install diffusers transformers accelerate gradio==3.48.0
  1. Launch the gradio: (For MacOS users, need to set the device="mps" in app.py; For Intel GPU users, set device="xpu" in app.py)
python app.py

Demos & Models Released

Ours Hugging Face Demo and Model are released ! Latent Consistency Models are supported in 🧨 diffusers.

LCM Model Download: LCM_Dreamshaper_v7

LCM模型已上传到始智AI(wisemodel) 中文用户可在此下载，下载链接.

For Chinese users, download LCM here: (中文用户可以在此下载LCM模型) Open in OpenXLab

Hugging Face Demo: Hugging Face Spaces

Replicate Demo: Replicate

OpenXLab Demo: Open in OpenXLab

Tungsten Demo: Tungsten

Novita.AI Demo: Novita.AI Latent Consistency Playground

<p align="center"> <img src="teaser.png"> </p>

By distilling classifier-free guidance into the model's input, LCM can generate high-quality images in very short inference time. We compare the inference time at the setting of 768 x 768 resolution, CFG scale w=8, batchsize=4, using a A800 GPU.

<p align="center"> <img src="speed_fid.png"> </p>

Usage

We have official LCM Pipeline and LCM Scheduler in 🧨 Diffusers library now! The older usages will be deprecated.

You can try out Latency Consistency Models directly on: Hugging Face Spaces

To run the model yourself, you can leverage the 🧨 Diffusers library:

  1. Install the library:
pip install --upgrade diffusers  # make sure to use at least diffusers >= 0.22
pip install transformers accelerate
  1. Run the model:
from diffusers import DiffusionPipeline
import torch

pipe = DiffusionPipeline.from_pretrained("SimianLuo/LCM_Dreamshaper_v7")

# To save GPU memory, torch.float16 can be used, but it may compromise image quality.
pipe.to(torch_device="cuda", torch_dtype=torch.float32)

prompt = "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k"

# Can be set to 1~50 steps. LCM support fast inference even <= 4 steps. Recommend: 1~8 steps.
num_inference_steps = 4 

images = pipe(prompt=prompt, num_inference_steps=num_inference_steps, guidance_scale=8.0, lcm_origin_steps=50, output_type="pil").images

For more information, please have a look at the official docs: 👉 https://huggingface.co/docs/diffusers/api/pipelines/latent_consistency_models#latent-consistency-models

Usage (Deprecated)

We have official LCM Pipeline and LCM Scheduler in 🧨 Diffusers library now! The older usages will be deprecated. But you can still use the older usages by adding revision="fb9c5d1" from from_pretrained(...)

To run the model yourself, you can leverage the 🧨 Diffusers library:

  1. Install the library:
pip install diffusers transformers accelerate
  1. Run the model:
from diffusers import DiffusionPipeline
import torch

pipe = DiffusionPipeline.from_pretrained("SimianLuo/LCM_Dreamshaper_v7", custom_pipeline="latent_consistency_txt2img", custom_revision="main", revision="fb9c5d")

# To save GPU memory, torch.float16 can be used, but it may compromise image quality.
pipe.to(torch_device="cuda", torch_dtype=torch.float32)

prompt = "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k"

# Can be set to 1~50 steps. LCM support fast inference even <= 4 steps. Recommend: 1~8 steps.
num_inference_steps = 4 

images = pipe(prompt=prompt, num_inference_steps=num_inference_steps, guidance_scale=8.0, lcm_origin_steps=50, output_type="pil").images

Our Contributors :

<a href="https://github.com/luosiallen/latent-consistency-model/graphs/contributors"> <img src="https://contrib.rocks/image?repo=luosiallen/latent-consistency-model" /> </a>

BibTeX

LCM:
@misc{luo2023latent,
      title={Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference}, 
      author={Simian Luo and Yiqin Tan and Longbo Huang and Jian Li and Hang Zhao},
      year={2023},
      eprint={2310.04378},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

LCM-LoRA:
@article{luo2023lcm,
  title={LCM-LoRA: A Universal Stable-Diffusion Acceleration Module},
  author={Luo, Simian and Tan, Yiqin and Patil, Suraj and Gu, Daniel and von Platen, Patrick and Passos, Apolin{\'a}rio and Huang, Longbo and Li, Jian and Zhao, Hang},
  journal={arXiv preprint arXiv:2311.05556},
  year={2023}
}