lxa9867/ImageFolder
High-performance Image Tokenizers for VAR and AR
This project helps researchers and developers working with image generation models to create high-quality images efficiently. It takes various image datasets (like ImageNet or medical images) and processes them into 'tokens' for use in autoregressive image generation models, resulting in more robust and visually appealing generated images. Researchers in computer vision and generative AI would be the primary users.
303 stars. No commits in the last 6 months.
Use this if you need to transform large image datasets into a tokenized format for autoregressive image generation, especially if you prioritize robust and high-fidelity output.
Not ideal if your primary focus is on other image processing tasks like classification, object detection, or non-generative image editing.
Stars
303
Forks
7
Language
Python
License
—
Category
Last pushed
Apr 25, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/lxa9867/ImageFolder"
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