This checkpoint is a LCM distilled version of
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:
The model can be loaded with it's base pipeline
stabilityai/stable-diffusion-xl-base-1.0
. 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.
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.to("cuda")
prompt = "a close-up picture of an old man standing in the rain"
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
Runs of ckpt lcm-sdxl-unet on huggingface.co
70
Total runs
2
24-hour runs
5
3-day runs
-1
7-day runs
50
30-day runs
More Information About lcm-sdxl-unet huggingface.co Model
lcm-sdxl-unet huggingface.co is an AI model on huggingface.co that provides lcm-sdxl-unet's model effect (), which can be used instantly with this ckpt lcm-sdxl-unet model. huggingface.co supports a free trial of the lcm-sdxl-unet model, and also provides paid use of the lcm-sdxl-unet. Support call lcm-sdxl-unet model through api, including Node.js, Python, http.
lcm-sdxl-unet huggingface.co is an online trial and call api platform, which integrates lcm-sdxl-unet's modeling effects, including api services, and provides a free online trial of lcm-sdxl-unet, you can try lcm-sdxl-unet online for free by clicking the link below.
ckpt lcm-sdxl-unet online free url in huggingface.co:
lcm-sdxl-unet is an open source model from GitHub that offers a free installation service, and any user can find lcm-sdxl-unet on GitHub to install. At the same time, huggingface.co provides the effect of lcm-sdxl-unet install, users can directly use lcm-sdxl-unet installed effect in huggingface.co for debugging and trial. It also supports api for free installation.