Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generation
Open paper
Benchmark
Model
Rank
Results
image-editing-on-imgedit-data
LaViDa-O
#18
Overall: 3.71
Add: 4.04
Adjust: 3.62
Extract: 2.01
Replace: 4.39
…
Rank counts only results with a code link.