pip install diffusers 
pip install transformers accelerate

import torch,diffusers
from diffusers import LCMScheduler,AutoPipelineForText2Image
from peft import LoraConfig, get_peft_model

model_id = "stabilityai/stable-diffusion-xl-base-1.0"
lora_path = 'path/to/the/lora'
lora_config = LoraConfig(
        r=64,
        target_modules=[
            "to_q",
            "to_k",
            "to_v",
            "to_out.0",
            "proj_in",
            "proj_out",
            "ff.net.0.proj",
            "ff.net.2",
            "conv1",
            "conv2",
            "conv_shortcut",
            "downsamplers.0.conv",
            "upsamplers.0.conv",
            "time_emb_proj",
        ],
    )

pipe = AutoPipelineForText2Image.from_pretrained(model_id,torch_dtype=torch.float16, variant="fp16")
pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
unet=pipe.unet
unet = get_peft_model(unet, lora_config)
unet.load_adapter(lora_path, adapter_name="default")
pipe.unet=unet
pipe.to('cuda')

eval_step=4 # the step can be changed within 2-8 steps

prompt = "An astronaut riding a horse in the jungle"
# disable guidance_scale by passing 0
image = pipe(prompt=prompt, num_inference_steps=eval_step, guidance_scale=0).images[0]

import os,torch
from diffusers import FluxPipeline
from scheduling_flow_match_tlcm import FlowMatchEulerTLCMScheduler
from peft import LoraConfig, get_peft_model

model_id = "black-forest-labs/FLUX.1-dev"
lora_path = "path/to/the/lora/folder"
lora_config = LoraConfig(
    r=64,
    target_modules=[
        "to_k", "to_q", "to_v", "to_out.0",
        "proj_in",
        "proj_out",
        "ff.net.0.proj",
        "ff.net.2",
        "context_embedder", "x_embedder",
        "linear", "linear_1", "linear_2",
        "proj_mlp",
        "add_k_proj", "add_q_proj", "add_v_proj", "to_add_out",
        "ff_context.net.0.proj", "ff_context.net.2"
        ],
        )

pipe = FluxPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
pipe.scheduler = FlowMatchEulerTLCMScheduler.from_config(pipe.scheduler.config)
pipe.to('cuda:0')
transformer = pipe.transformer
transformer = get_peft_model(transformer, lora_config)
transformer.load_adapter(lora_path, adapter_name="default", is_trainable=False)
pipe.transformer=transformer

eval_step=4 # the step can be changed within 2-8 steps

prompt = "An astronaut riding a horse in the jungle"
image = pipe(prompt=prompt, num_inference_steps=eval_step, guidance_scale=7).images[0]

@article{xie2024tlcm,
  title={TLCM: Training-efficient Latent Consistency Model for Image Generation with 2-8 Steps},
  author={Xie, Qingsong and Liao, Zhenyi and Deng, Zhijie and Lu, Haonan},
  journal={arXiv preprint arXiv:2406.05768},
  year={2024}
}