Downloads · 30 days
0
0% of all-time downloads
lcm_sdxl_full_model
Vargol/lcm_sdxl_full_model
lcm_sdxl_full_model is a text-to-image model from Vargol. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as openrail++.
This is a copy of the sdxl base (stabilityai/stable-diffusion-xl-base-1.0) with the unet replaced with the LCM distilled unet (latent-consistency/lcm-sdxl) and scheduler config set to default to the LCM Scheduler.
All-time downloads
751
Public
Parameters
2.6B
24.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors20.8 GB · 100%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- License
- openrail++
- Access
- Public
- Created
- Nov 10, 2023
- Updated
- Nov 10, 2023
- SHA
- bfabf00b
Model card
From the Hugging Face model README
This is a copy of the sdxl base (stabilityai/stable-diffusion-xl-base-1.0) with the unet replaced with the LCM distilled unet (latent-consistency/lcm-sdxl) and scheduler config set to default to the LCM Scheduler.
This makes LCM SDXL run as a standard Diffusion Pipeline
from diffusers import DiffusionPipeline
import torch
pipe = DiffusionPipeline.from_pretrained(
"Vargol/lcm_sdxl_full_model", variant='fp16', torch_dtype=torch.float16
).to("mps")
prompt = "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k"
generator = torch.manual_seed(0)
image = pipe(
prompt=prompt, num_inference_steps=4, generator=generator, guidance_scale=8.0
).images[0]
image.save('distilled.png')
- Task
- Text-to-Image
- Library
- diffusers
- License
- openrail++
- Created
- Nov 10, 2023
- Updated
- Nov 10, 2023