Zoomed In, Diffused Out: Towards Local Degradation-Aware Multi-Diffusion for Extreme Image Super-Resolution

This work and repo builds upon SeeSR.

⚙️ Dependencies and Installation

## git clone this repository
git clone https://github.com/cswry/SeeSR.git
cd SeeSR

# create an environment with python >= 3.8
conda create -n seesr python=3.8
conda activate seesr
pip install -r requirements.txt

🚀 Inference

Step 1: Download the pretrained models

• Download the pretrained SD-2-base models from HuggingFace.
• Download the SeeSR and DAPE models from GoogleDrive or OneDrive.

You can put the models into preset/models.

Step 2: Prepare testing data

You can put the testing images in the preset/datasets/test_datasets.

Step 3: Running testing command

python test_multiseesr_local.py \
--pretrained_model_path preset/models/stable-diffusion-2-base \
--prompt '' \
--seesr_model_path preset/models/seesr \
--ram_ft_path preset/models/DAPE.pth \
--image_path preset/datasets/test_datasets \
--output_dir preset/datasets/output \
--start_point lr \
--num_inference_steps 50 \
--guidance_scale 5.5 \
--process_size 512 \
--upscale 4 \
--local_prompts

the tag --local_prompts activates the local prompt extraction.