使用 Diffuser 运行 Fluxn Mac

亲爱的编程学习爱好者，如果你点开了这篇文章，说明你对《使用 Diffuser 运行 Fluxn Mac》很感兴趣。本篇文章就来给大家详细解析一下，主要介绍一下，希望所有认真读完的童鞋们，都有实质性的提高。

什么是扩散器？

什么是助焊剂

https://blackforestlabs.ai/announcing-black-forest-labs/

1. 创建虚拟环境

python3 -m venv fluxtest
source fluxtest/bin/activate

2. 通过 cli 登录 hugging face

https://huggingface.co/docs/huggingface_hub/main/en/guides/cli

pip install -u "huggingface_hub[cli]"
huggingface-cli login

3.安装包

pip install torch==2.3.1
pip install git+https://github.com/huggingface/diffusers.git
pip install transformers==4.43.3 sentencepiece==0.2.0 accelerate==0.33.0 protobuf==5

4. 运行python脚本

图像.py

import torch
from diffusers import  fluxpipeline
import diffusers

_flux_rope = diffusers.models.transformers.transformer_flux.rope
def new_flux_rope(pos: torch.tensor, dim: int, theta: int) -> torch.tensor:
    assert dim % 2 == 0, "the dimension must be even."
    if pos.device.type == "mps":
        return _flux_rope(pos.to("cpu"), dim, theta).to(device=pos.device)
    else:
        return _flux_rope(pos, dim, theta)

diffusers.models.transformers.transformer_flux.rope = new_flux_rope

pipe = fluxpipeline.from_pretrained("black-forest-labs/flux.1-schnell", revision='refs/pr/1',  torch_dtype=torch.bfloat16).to("mps")

prompt = "japanese girl, photo-realistic"
out = pipe(
     prompt=prompt,
     guidance_scale=0.,
     height=1024,
     width=1024,
     num_inference_steps=4,
     max_sequence_length=256,
).images[0]
out.save("image.png")

最后，运行python脚本生成图像。

python image.py

输出

以上就是本文的全部内容了，是否有顺利帮助你解决问题？若是能给你带来学习上的帮助，请大家多多支持golang学习网！更多关于文章的相关知识，也可关注golang学习网公众号。