You're looking at a specific version of this model. Jump to the model overview.

ramene /mae-video-ingestion:063d1d23

Input schema

The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.

Field Type Default value Description
video_url
string
YouTube URL or direct https .mp4 URL
profile
None
ai-systems-research
Prompt profile (archetype). Determines extraction schema.
chunk_duration_sec
integer
300

Min: 60

Max: 600

Seconds per video chunk (smaller = more chunks, more memory headroom)
video_fps
number
0.5

Min: 0.1

Max: 2

Sample fps per chunk (higher = denser visual capture, more memory)
video_max_pixels
integer
151200

Min: 10000

Max: 500000

Per-frame pixel budget (360*420=151200 default)
max_new_tokens
integer
2048

Min: 512

Max: 8192

Per-chunk LLM output cap
prompt_override
string
Optional: paste custom prompt to bypass PROFILE entirely

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{'additionalProperties': True, 'title': 'Output', 'type': 'object'}