F5-TTS
π£
2.89k
F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)
Ask questions about images and get detailed answers
Generate new images from a photo using text and style prompts
Create AI images with FLUX LoRA styles
More advanced and challenging multi-task evaluation
Annotate and describe images with text prompts
Analyze images to detect objects, generate captions, or perform OCR
Generate captions, detections, and segmentations from images
Chat with an AI that understands images and text
a tiny vision language model
Transcribe audio with emotions and sound events