Orpheus Music Transformer
[2026] SOTA 8k music transformer trained on 2.31M+ HQ MIDIs
Expressive Zeroshot TTS
Extreme Super-Resolution via Scale Autoregression
ultra-fast video model, LTX 0.9.8 13B distilled
Generate custom captions, tags, or prompts for any image
A Step Towards Music Generation Foundation Model
Arena for HiDream-I1-dev / -full and FLUX-dev
Long-form Speech Synthesis with Zonos
New Ghibli EasyControl model is now released!!
Generate images from text prompts with customizable aspect ratio
Generate speech from text using a reference audio