library_name: diffusers
base_model: runwayml/stable-diffusion-v1-5
tags:
- lora
- text-to-image
license: openrail++
inference: false
Latent Consistency Model (LCM) LoRA: SDv1-5
Latent Consistency Model (LCM) LoRA was proposed in LCM-LoRA: A universal Stable-Diffusion Acceleration Module by Simian Luo, Yiqin Tan, Suraj Patil, Daniel Gu et al.
It is a distilled consistency adapter for runwayml/stable-diffusion-v1-5 that allows
to reduce the number of inference steps to only between 2 - 8 steps.
| Model | Params / M |
|---|---|
| lcm-lora-sdv1-5 | 67.5 |
| lcm-lora-ssd-1b | 105 |
| lcm-lora-sdxl | 197M |
Usage
LCM-LoRA 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.
audio dataset from the Hugging Face Hub:
pip install --upgrade pip
pip install --upgrade diffusers transformers accelerate peft
Text-to-Image
The adapter can be loaded with SDv1-5 or deviratives. Here we use Lykon/dreamshaper-7. Next, the scheduler needs to be changed to LCMScheduler and we can reduce the number of inference steps to just 2 to 8 steps.
Please make sure to either disable guidance_scale or use values between 1.0 and 2.0.
import torch
from diffusers import LCMScheduler, AutoPipelineForText2Image
model_id = "Lykon/dreamshaper-7"
adapter_id = "latent-consistency/lcm-lora-sdv1-5"
pipe = AutoPipelineForText2Image.from_pretrained(model_id, torch_dtype=torch.float16, variant="fp16")
pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
pipe.to("cuda")
# load and fuse lcm lora
pipe.load_lora_weights(adapter_id)
pipe.fuse_lora()
prompt = "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k"
# disable guidance_scale by passing 0
image = pipe(prompt=prompt, num_inference_steps=4, guidance_scale=0).images[0]
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
Training
TODO