Skip to content

How does Gemini preprocess images and videos? #250

Open
@Lanbai-eleven

Description

@Lanbai-eleven

Description of the feature request:

Is there any documentation explaining how Gimini preprocesses input images or videos before generating tokens? For instance, how does it crop images of arbitrary resolutions, or how does it sample frames from videos of arbitrary lengths?

What problem are you trying to solve with this feature?

No response

Any other information you'd like to share?

No response

Metadata

Metadata

Assignees

Labels

component:documentationImprovements or additions to documentationstatus:triagedIssue/PR triaged to the corresponding sub-teamtype:questionUser question

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions