基础模型:

• black-forest-labs/FLUX.1-dev 库名称: diffusers 许可证: 其他 许可证名称: flux-1-dev-non-commercial-license 许可证链接: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md 管道标签: 图像到图像 标签:
  • ControlNet
  • 超分辨率
  • 放大
  • 文本到图像
  • 稳定扩散
  • lora
  • diffusers
  • fluxpipeline

⚡ Flux.1-dev: 放大控制网络 ⚡

这是由Jasper研究团队开发的用于低分辨率图像的Flux.1-dev ControlNet。

使用方法

此模型可直接与diffusers库一起使用

import torch
from diffusers.utils import load_image
from diffusers import FluxControlNetModel
from diffusers.pipelines import FluxControlNetPipeline

# 加载管道
controlnet = FluxControlNetModel.from_pretrained(
  "jasperai/Flux.1-dev-Controlnet-Upscaler",
  torch_dtype=torch.bfloat16
)
pipe = FluxControlNetPipeline.from_pretrained(
  "black-forest-labs/FLUX.1-dev",
  controlnet=controlnet,
  torch_dtype=torch.bfloat16
)
pipe.to("cuda")

# 加载控制图像
control_image = load_image(
  "https://huggingface.co/jasperai/Flux.1-dev-Controlnet-Upscaler/resolve/main/examples/input.jpg"
)

w, h = control_image.size

# 放大4倍
control_image = control_image.resize((w * 4, h * 4))

image = pipe(
    prompt="", 
    control_image=control_image,
    controlnet_conditioning_scale=0.6,
    num_inference_steps=28, 
    guidance_scale=3.5,
    height=control_image.size[1],
    width=control_image.size[0]
).images[0]
image

训练

该模型采用合成复杂数据退化方案进行训练，以真实生活图像为输入，通过结合多种退化（如高斯噪声、泊松噪声、图像模糊和JPEG压缩等）进行人工退化，其精神类似于[1]。

[1] Wang, Xintao, et al. "Real-esrgan: Training real-world blind super-resolution with pure synthetic data." Proceedings of the IEEE/CVF international conference on computer vision. 2021.

许可证

本模型遵循Flux.1-dev模型许可证。