Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Open paper

Benchmark	Model	Rank	Results
text-to-image-generation-on-dpg-bench	Tuna-2 7B	#37	DPG-Bench Score: 86.54
text-to-image-generation-on-geneval	Tuna-2 7B	#49	Overall: 0.87