EndlessSora/focal-frequency-loss
[ICCV 2021] Focal Frequency Loss for Image Reconstruction and Synthesis
This project helps improve the quality of generated or reconstructed images, like those used in digital art, virtual try-on, or visual effects. It takes an image generation model's output and a target image, then refines the output to better match the fine details and textures of real images. This is for researchers and practitioners working with image synthesis and reconstruction models.
706 stars. No commits in the last 6 months. Available on PyPI.
Use this if you are developing or training image generation models (like VAE, pix2pix, or StyleGAN2) and want to enhance the realism, sharpness, or textural quality of the output images.
Not ideal if you are looking for a tool to perform basic image editing, object detection, or classification, as this is specifically designed to refine the output of generative models.
Stars
706
Forks
63
Language
Python
License
MIT
Category
Last pushed
Aug 21, 2024
Commits (30d)
0
Dependencies
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/EndlessSora/focal-frequency-loss"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
Vchitect/VBench
[CVPR2024 Highlight] VBench - We Evaluate Video Generation
VectorSpaceLab/OmniGen
OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340
JIA-Lab-research/DreamOmni2
This project is the official implementation of 'DreamOmni2: Multimodal Instruction-based Editing...
SkyworkAI/UniPic
Open-source SOTA multi-image editing model
PKU-YuanGroup/ChronoMagic-Bench
[NeurIPS 2024 D&B Spotlightš„] ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of...