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: 🔥🔥🔥

Replicate Demo:

OpenXLab Demo:

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

Breaking News 🔥🔥!!

(🤖New) 2023/12/1 Pixart-α X LCM is out, a high quality image generative model. see here.
(❤️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:

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.
Install the main library:

pip install diffusers transformers accelerate gradio==3.48.0

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)

Hugging Face Demo:

Replicate Demo:

OpenXLab Demo:

Tungsten Demo:

Novita.AI Demo:

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:

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

Install the library:

pip install --upgrade diffusers  # make sure to use at least diffusers >= 0.22
pip install transformers accelerate

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(...)