Generate customized images using text and multiple images
Try Orpheus TTS here
New Ghibli EasyControl model is now released!!
Detect objects in images and get bounding boxes
Convert your face photo into anime style
Transcribe audio from microphone, files, or YouTube
Generate personalized images with a face preservation
Generate images from text descriptions
Generate edited images with prompts
Execute commands based on environment variables
Generate high-resolution images with text prompts
ocr vl
Analyze image to generate descriptive prompt
Convert PDFs/images to Markdown and zip files
Generate corrected text with reference