Introducing
Model Fine-tuning
From entertainment to robotics, education, life sciences and beyond, our next generation of models will unlock entirely new use cases with the introduction of model fine-tuning.
Generative video models will soon serve as general-purpose simulators of reality. But getting there requires solving a key problem: today's video models, while versatile, are inherently opinionated.
Every model makes tradeoffs in areas like aesthetics, motion dynamics and domain coverage, shaped by post-training assumptions about the average use case.
This works for impressive demos, but can fall short when deployed for real customer problems. Our goal with Model Fine-tuning is to make post-training accessible to everyone. Allowing users to fine-tune our models for their specific use cases and allowing for new input and outputs with minimal compute and data requirements.
Model Fine-tuning is available now for select pilot partners and coming soon to everyone. Submit your interest below to be considered for early access and to be kept up to date on general release.
This works for impressive demos, but can fall short when deployed for real customer problems. Our goal with Model Fine-tuning is to make post-training accessible to everyone. Allowing users to fine-tune our models for their specific use cases and allowing for new input and outputs with minimal compute and data requirements.
Model Fine-tuning is available now for select pilot partners and coming soon to everyone. Submit your interest below to be considered for early access and to be kept up to date on general release.
Key industries working with Model Fine-tuning
- Robotics
- Life Sciences
- Education
- Architecture
- Design
- Brands
Fill out the form if you are interested in Model Fine-tuning