38
Dia - Text to Dialogue
🚀
Dia - 1.6B Text-to-Dialogue Model
Analyze a Spotify playlist and get recommendations
Classify music genres
Controllable Zero-Shot Voice Imitation
Generate images using selected LoRA models and prompts
Create images using prompts and control images
New Ghibli EasyControl model is now released!!
Generate high-quality images from text descriptions
Highly hackable hub w/ Flux, SD 3.5, LoRAs, no GPUs required
Chat with Kimi-VL-A3B-Thinking using text and images
Generate customized images using text and multiple images
Transcribe audio with emotions and events