KEEP
KEEP copied to clipboard
[ECCV'24] Kalman-Inspired Feature Propagation for Video Face Super-Resolution
This commit introduces the necessary files and modifications to enable the KEEP model to run on RunPod Serverless. Key changes: - Added `handler.py`: Contains the serverless handler function to process...
Hello, it seems this is a really great high-definition upscaling model. May I ask if it can be used as a model for loading in ComfyUI?
(venv) F:\K\KEEP>python inference_keep.py -i=./assets/examples/synthetic_1.mp4 -o=results/ --has_aligned --save_video -s=1 Traceback (most recent call last): File "F:\K\KEEP\inference_keep.py", line 10, in from basicsr.utils import imwrite, img2tensor, tensor2img File "F:\K\KEEP\basicsr\__init__.py", line 3, in from...
Hi, Niels here from the open-source team at Hugging Face. I discovered your work through the paper page: https://huggingface.co/papers/2408.05205 (feel free to claim the paper so that it appears under...
Looking forward to it I can make tutorial of your model and it can get a lot of attraction I got 37k subscribers https://www.youtube.com/SECourses
Could you share the opt file? Or share the detail opt of degradations in vfhq_real_degradation2_dataset.py
Hi, Thank you for sharing this great work and for providing the inference code and models. I was wondering if you have any plans to release the training code as...
raise KeyError(f"No object named '{name}' found in '{self._name}' registry!") KeyError: "No object named 'KEEP' found in 'arch' registry!"
I couldn't find the configuration file in the folder, how can I get it
Hi, thank you for your dedication to this amazing project. @jnjaby When resizing images, dimensions that are not even numbers can cause errors when passed to FFmpeg, as it requires...