Flux.1-dev-Controlnet-Upscaler Open-source Model - Free to Improve the Clarity of Low-resolution Images

Flux.1 Dev Controlnet Upscaler

Developed by jasperai

A ControlNet model developed by the Jasper research team for low-resolution image upscaling

Image Enhancement Open Source License:Other #Image Super-Resolution #ControlNet Enhancement #Synthetic Data Training

Downloads 11.16k

Release Time : 9/23/2024

Model Overview

This model is an image super-resolution tool based on the ControlNet architecture, specifically designed to enhance the quality of low-resolution images. It is trained using a synthetic complex data degradation scheme and can handle various image degradation scenarios.

Model Features

High-Quality Image Upscaling

Capable of upscaling low-resolution images by 4x or more while preserving image details and quality

Complex Degradation Handling

Trained with synthetic data incorporating multiple degradation methods (Gaussian noise, Poisson noise, image blur, JPEG compression, etc.), enhancing the model's robustness

ControlNet Architecture

Based on the ControlNet architecture, enabling better control over the image generation process

Model Capabilities

Image Super-Resolution Processing

Low-Resolution Image Enhancement

Image Detail Restoration

Use Cases

Image Processing

Old Photo Restoration

Improve the quality and clarity of old, low-resolution photos

4x increase in photo resolution while restoring lost details

Digital Art Enhancement

Provide high-quality upscaling for digital artworks

Increase resolution while maintaining artistic style

🚀 ⚡ Flux.1-dev: Upscaler ControlNet ⚡

This is Flux.1-dev ControlNet for low resolution images developed by Jasper research team. It enables effective upscaling of low - resolution images, offering a practical solution for image enhancement.

🚀 Quick Start

This model can be used directly with the diffusers library. The following is a step - by - step guide on how to use it:

Basic Usage

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

# Load pipeline
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")

# Load a control image
control_image = load_image(
  "https://huggingface.co/jasperai/Flux.1-dev-Controlnet-Upscaler/resolve/main/examples/input.jpg"
)

w, h = control_image.size

# Upscale x4
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

🔧 Technical Details

This model was trained with a synthetic complex data degradation scheme taking as input a real - life image and artificially degrading it by combining several degradations such as amongst other image noising (Gaussian, Poisson), image blurring and JPEG compression in a similar spirit as [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.

📄 License

This model falls under the [Flux.1 - dev model licence](https://huggingface.co/black - forest - labs/FLUX.1 - dev/blob/main/LICENSE.md).

Model Information

Property	Details
Base Model	black - forest - labs/FLUX.1 - dev
Library Name	diffusers
License	other
License Name	flux - 1 - dev - non - commercial - license
License Link	https://huggingface.co/black - forest - labs/FLUX.1 - dev/blob/main/LICENSE.md
Pipeline Tag	image - to - image
Inference	False
Tags	ControlNet, super - resolution, upscaler

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご