microsoft/OmniParser
			Image-Text-to-Text
			• 
		
	
				Updated
					
				
				• 
					
					339
				
	
				• 
					
					1.69k
				
Generate text based on input prompts
Chat with a bilingual AI assistant
Analyze images to generate descriptive prompts
Transcribe audio to text with speaker diarization
Chat with AI using text input