Cryofm V2
Cryofm V 2 is a flow-based generative foundation model for cryo-EM density maps developed by ByteDance, exceling at learning general priors of high-quality cryo-EM densities and adaptable for downstream tasks such as density map enhancement. Its 3D UNet architecture enables stable generation and flexible adaptation, with a notable technical trait being its use of positional encoding for time embedding.
Input
Output
Context
-
Max Output
-
Parameters
-
Technical Specifications
Model TypeImage
Context WindowNot available
Max Output TokensNot available
ParametersNot available
Release DateDec 24, 2025
Training CutoffNot available
Licenseapache-2.0
Open SourceYes
Input Modalities
Image
Output Modalities
Image
Capabilities
More Models by ByteDance
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Aug 28, 2026
Your AI stack shouldn't stand still.
Every month new models become cheaper, faster, and more capable. Inferbase ensures your application automatically benefits without changing a single API call.