metadata

library_name: diffusers
tags:
  - text-to-image
license: apache-2.0
inference: false

Sub-path Linear Approximation Model (SLAM): DreamShaperV7

Paper: https://arxiv.org/abs/2404.13903
Project Page: https://subpath-linear-approx-model.github.io/
The checkpoint is a distilled from https://huggingface.co/Lykon/dreamshaper-7 with our proposed Sub-path Linear Approximation Model, which reduces the number of inference steps to only between 2-4 steps.

Usage

First, install the latest version of the Diffusers library as well as peft, accelerate and transformers.

pip install --upgrade pip
pip install --upgrade diffusers transformers accelerate peft

We implement SLAM to be compatible with LCMScheduler. You can use SLAM just like you use LCM, with guidance_scale set to 1 constantly.

from diffusers import DiffusionPipeline
import torch

pipe = DiffusionPipeline.from_pretrained("alimama-creative/slam-dreamshaper7")

# To save GPU memory, torch.float16 can be used, but it may compromise image quality.
pipe.to(torch_device="cuda", torch_dtype=torch.float16)

prompt = "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k"

num_inference_steps = 4

images = pipe(prompt=prompt, num_inference_steps=num_inference_steps, guidance_scale=1, lcm_origin_steps=50, output_type="pil").images