|
--- |
|
library_name: diffusers |
|
base_model: stabilityai/stable-diffusion-xl-base-1.0 |
|
tags: |
|
- lora |
|
- text-to-image |
|
license: openrail++ |
|
inference: false |
|
--- |
|
|
|
# Latent Consistency Model (LCM): SDXL |
|
|
|
Latent Consistency Model (LCM) was proposed in [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://arxiv.org/abs/2310.04378) |
|
by *Simian Luo, Yiqin Tan et al.* and [Simian Luo](https://huggingface.co/SimianLuo), [Suraj Patil](https://huggingface.co/valhalla), and [Daniel Gu](https://huggingface.co/dg845) |
|
succesfully applied the same approach to create LCM for SDXL. |
|
|
|
This checkpoint is a LCM distilled version of [`stable-diffusion-xl-base-1.0`](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) that allows |
|
to reduce the number of inference steps to only between **2 - 8 steps**. |
|
|
|
|
|
## Usage |
|
|
|
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`. |
|
audio dataset from the Hugging Face Hub: |
|
|
|
```bash |
|
pip install --upgrade pip |
|
pip install --upgrade diffusers transformers accelerate peft |
|
``` |
|
|
|
### Text-to-Image |
|
|
|
The adapter can be loaded with it's base model `stabilityai/stable-diffusion-xl-base-1.0`. Next, the scheduler needs to be changed to [`LCMScheduler`](https://huggingface.co/docs/diffusers/v0.22.3/en/api/schedulers/lcm#diffusers.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. |
|
|
|
```python |
|
from diffusers import UNet2DConditionModel, DiffusionPipeline, LCMScheduler |
|
|
|
unet = UNet2DConditionModel.from_pretrained("latent-consistency/lcm-sdxl", torch_dtype=torch.float16, variant="fp16") |
|
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", unet=unet, torch_dtype=torch.float16, variant="fp16") |
|
|
|
pipe.scheduler = LCMScheduler.from_config(sd_pipe.scheduler.config) |
|
pipe.set_progress_bar_config(disable=None) |
|
|
|
prompt = "a red car standing on the side of the street" |
|
|
|
image = pipe(prompt, num_inference_steps=4, guidance_scale=8.0).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 |
|
|
|
## Speed Benchmark |
|
|
|
TODO |
|
|
|
## Training |
|
|
|
TODO |
