Lcm Ssd 1b

🚀 Latent Consistency Model (LCM): SSD-1B

Latent Consistency Model (LCM) enables high - resolution image synthesis with few - step inference, significantly enhancing efficiency in text - to - image tasks.

🚀 Quick Start

LCM SDXL is supported in 🤗 Hugging Face Diffusers library from version v0.23.0 onwards. To run the model, first install the latest version of the Diffusers library as well as peft, accelerate and transformers.

pip install --upgrade pip
pip install --upgrade diffusers transformers accelerate peft

✨ Features

Latent Consistency Model (LCM) was proposed in Latent Consistency Models: Synthesizing High - Resolution Images with Few - Step Inference by Simian Luo, Yiqin Tan et al. and Simian Luo, Suraj Patil, and Daniel Gu successfully applied the same approach to create LCM for SDXL. This checkpoint is a LCM distilled version of segmind/SSD-1B that allows to reduce the number of inference steps to only between 2 - 8 steps.

📦 Installation

To install the necessary libraries for running the model, execute the following commands:

pip install --upgrade pip
pip install --upgrade diffusers transformers accelerate peft

💻 Usage Examples

Basic Usage

The model can be loaded with its base pipeline segmind/SSD-1B. Next, the scheduler needs to be changed to LCMScheduler and we can reduce the number of inference steps to just 2 to 8 steps.

from diffusers import UNet2DConditionModel, DiffusionPipeline, LCMScheduler
import torch

unet = UNet2DConditionModel.from_pretrained("latent-consistency/lcm-ssd-1b", torch_dtype=torch.float16, variant="fp16")
pipe = DiffusionPipeline.from_pretrained("segmind/SSD-1B", unet=unet, torch_dtype=torch.float16, variant="fp16")

pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
pipe.to("cuda")

prompt = "a close-up picture of an old man standing in the rain"

image = pipe(prompt, num_inference_steps=4, guidance_scale=1.0).images[0]

Advanced Usage

• Image - to - Image: Works as well! TODO docs
• Inpainting: Works as well! TODO docs
• ControlNet: Works as well! TODO docs
• T2I Adapter: Works as well! TODO docs

📚 Documentation

Text - to - Image

The model can be loaded with its base pipeline segmind/SSD-1B. Then, change the scheduler to LCMScheduler and reduce the number of inference steps to 2 - 8 steps.

📄 License

The license for this model is openrail++.