【深度学习】SDXL，diffusers加载单个safetensors文件，保存单个safetensors文件_diffusers from single file

StableDiffusionXLPipeline 加载仓库：

import torch
from diffusers import StableDiffusionXLPipeline, EulerDiscreteScheduler

base = "Vargol/sdxl-lightning-4-steps"

pipe = StableDiffusionXLPipeline.from_pretrained(base, torch_dtype=torch.float16).to("cuda")

# Ensure sampler uses "trailing" timesteps.
pipe.scheduler = EulerDiscreteScheduler.from_config(pipe.scheduler.config, timestep_spacing="trailing")

# Ensure using the same inference steps as the loaded model and CFG set to 0.
pipe("A girl smiling", num_inference_steps=4, guidance_scale=0).images[0].save("output.png")

1
2
3
4
5
6
7
8
9
10
11
12
13

diffusers 从单个safetensors文件加载pipe：

import torch
from diffusers import StableDiffusionXLPipeline
pretrained_ckpt_path = "/data/xiedong/fooocus_tensorRT/Fooocus/models/checkpoints/juggernautXL_version6Rundiffusion.safetensors"
pipe = StableDiffusionXLPipeline.from_single_file(pretrained_ckpt_path, torch_dtype=torch.float16).to("cuda")
1
2
3
4

将pipe保存单个safetensors文件：

https://github.com/huggingface/diffusers/discussions/7336#discussioncomment-8796829