datalab-to/chandra
Image-Text-to-Text β’ 9B β’ Updated
β’ 135k β’ 493
Analyze images with multiple vision models for labels and boxes
VLMEvalKit Evaluation Results Collection
Interact with documents and images to get explanations and answers
Generate personalized photos with your face
Generate consistent story images from prompts and reference photos
Generate stunning high quality illusion artwork
Clone a voice and generate speech from your text