Introducing RL with Neural Feedback (RLNF). We have found reliable ways to train AI models to respond to human preferences purely from brain signals.
The example below is a picture of a face that self-transforms into a more attractive version for the subject as they are looking at it.
A good creative workflow should help you move forward without limiting where you can go. Flova 1.5 brings multiple Skills into one conversation, so you can continue working toward your goal while exploring different approaches. It's a practical improvement for anyone whose best ideas tend to appear during the process itself. https://t.co/qXqAjG1I4M
Flova 1.5 | One Chat with Multiple Skills
One project. Multiple Skills.
Bring different Skills together in one creation!
- You set the goal. Agent plans the workflow.
- Mix and match Skills to explore different stories and styles.
- Refine your creations and take your ideas even further.
โจ Mix and Match Skills. Turn your ideas into videos, your way!
Flova 1.5 | One Chat with Multiple Skills
One project. Multiple Skills.
Bring different Skills together in one creation!
- You set the goal. Agent plans the workflow.
- Mix and match Skills to explore different stories and styles.
- Refine your creations and take your ideas even further.
โจ Mix and Match Skills. Turn your ideas into videos, your way!
Drop 1/15: Introducing Joy, a dual-channel conversational dataset.
Real, unscripted conversations between two people, each on their own track. Built to teach voice models how people actually talk: when to listen, when to jump in, when to say โhmmโ.
100,000 hours.
50,000 speakers.
10 languages.