This is a copy of the SSD-1B model (https://huggingface.co/segmind/SSD-1B) with the unet replaced with the LCM distilled unet (https://huggingface.co/latent-consistency/lcm-ssd-1b) and scheduler config set to default to the LCM Scheduler.

This makes LCM SSD-1B run as a standard Diffusion Pipeline

from diffusers import DiffusionPipeline
import torch

pipe = DiffusionPipeline.from_pretrained(
    "Vargol/lcm-ssd-1b-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')
Downloads last month
12
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.