bcmi/F2GAN-Few-Shot-Image-Generation
Fusing-and-Filling GAN (F2GAN) for few-shot image generation, ACM MM2020
This project helps generate new, realistic images for a specific category when you only have a few example images available. You provide a handful of images from a new category, and it outputs many diverse, high-quality synthetic images belonging to that same category. This is useful for researchers and practitioners in computer vision who need to expand limited datasets.
No commits in the last 6 months.
Use this if you need to create more training data for image-related tasks like classification, but you only have a very small number of example images for certain categories.
Not ideal if you already have large datasets for your image categories or if you need to generate images from scratch without any category examples.
Stars
79
Forks
11
Language
Python
License
—
Category
Last pushed
Apr 30, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/bcmi/F2GAN-Few-Shot-Image-Generation"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Vchitect/VBench
[CVPR2024 Highlight] VBench - We Evaluate Video Generation
VectorSpaceLab/OmniGen
OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340
EndlessSora/focal-frequency-loss
[ICCV 2021] Focal Frequency Loss for Image Reconstruction and Synthesis
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