datalab-to/chandra
Image-Text-to-Text β’ 9B β’ Updated β’ 2k β’ 533
Open the Vision Arena interface for image tasks
VLMEvalKit Evaluation Results Collection
Ask questions about documents and images with OCRβfree AI
Generate personalized images that keep your face identity
Generate a story of consistent images from text and photos
Generate stunning high quality illusion artwork
Generate speech in a cloned voice from a short audio clip