Downloads · 30 days
0
0% of all-time downloads
stable-diffusion-xl-base-1.0-lcm
qiacheng/stable-diffusion-xl-base-1.0-lcm
stable-diffusion-xl-base-1.0-lcm is a text-to-image model from qiacheng. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as apache-2.0.
SDXL-base-1.0 LDM: https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0
All-time downloads
31
Public
Parameters
2.6B
13.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors13.9 GB · 100%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- License
- apache-2.0
- Access
- Public
- Created
- Nov 14, 2023
- Updated
- Nov 14, 2023
- SHA
- 334cf6a0
Model card
From the Hugging Face model README
SDXL-base-1.0 LDM: https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0
SDXL-base-1.0 LCM-Lora: https://huggingface.co/latent-consistency/lcm-lora-sdxl
SDXL model fused with LCM Lora, saved using diffusers .save_pretrained()
Sample usage:
import torch
from diffusers import StableDiffusionXLPipeline
pipe = StableDiffusionXLPipeline.from_pretrained("qiacheng/stable-diffusion-xl-base-1.0-lcm")
prompt = "a cat"
height = 1024
width = 1024
steps = 6
guidance_scale = 1
output = pipe(prompt=prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=guidance_scale, output_type="pil")
- Task
- Text-to-Image
- Library
- diffusers
- License
- apache-2.0
- Created
- Nov 14, 2023
- Updated
- Nov 14, 2023