/latent-consistency-model

Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference

Primary LanguagePythonMIT LicenseMIT

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

LCM Community: Join our LCM discord channels for discussions. Coders are welcome to contribute.

Breaking News 🔥🔥!!

  • (❤️New) 2023/11/10 Training Scripts are released!! Check here.
  • (🤯New) 2023/11/10 Training-free acceleration LCM-LoRA is born! See our technical report here and Hugging Face blog here.
  • (⚡️New) 2023/11/10 LCM has a major update! We release 3 LCM-LoRA (SD-XL, SSD-1B, SD-V1.5), see here.
  • (🚀New) 2023/11/10 LCM has a major update! We release 2 Full Param-tuned LCM (SD-XL, SSD-1B), see here.

News

  • (🔥New) 2023/11/10 We support LCM Inference with C# and ONNX Runtime now! Thanks to @saddam213! Check the link here.
  • (🔥New) 2023/11/01 Real-Time Latent Consistency Models is out!! Github link here. Thanks @radames for the really cool Huggingface🤗 demo Real-Time Image-to-Image, Real-Time Text-to-Image. Twitter/X Link.
  • (🔥New) 2023/10/28 We support Img2Img for LCM! Please refer to "🔥 Image2Image Demos".
  • (🔥New) 2023/10/25 We have official LCM Pipeline and LCM Scheduler in 🧨 Diffusers library now! Check the new "Usage".
  • (🔥New) 2023/10/24 Simple Streamlit UI for local use: See the link Thanks for @akx.
  • (🔥New) 2023/10/24 We support SD-Webui and ComfyUI now!! Thanks for @0xbitches. See the link: SD-Webui and ComfyUI.
  • (🔥New) 2023/10/23 Running on Windows/Linux CPU is also supported! Thanks for @rupeshs See the link.
  • (🔥New) 2023/10/22 Google Colab is supported now. Thanks for @camenduru See the link: Colab
  • (🔥New) 2023/10/21 We support local gradio demo now. LCM can run locally!! Please refer to the "Local gradio Demos".
  • (🔥New) 2023/10/19 We provide a demo of LCM in 🤗 Hugging Face Space. Try it here.
  • (🔥New) 2023/10/19 We provide the LCM model (Dreamshaper_v7) in 🤗 Hugging Face. Download here.
  • (🔥New) 2023/10/19 LCM is integrated in 🧨 Diffusers library. Please refer to the "Usage".

🔥 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!

🔥 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

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

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.

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 :

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}
}