---
title: "Reconstructed Slides: Minimax M2: Building the #1 Open Model – Olive Song, MiniMax"
category: "slides"
video_id: "lY1iFbDPRlw"
sourceLabels: ["Cropped public YouTube video frames", "Local OpenCV slide-region detection", "Local RapidOCR"]
---

# Reconstructed Slides: Minimax M2: Building the #1 Open Model – Olive Song, MiniMax

## Source Video
[Minimax M2: Building the #1 Open Model – Olive Song, MiniMax](https://www.youtube.com/watch?v=lY1iFbDPRlw)

## Method
This deck is reconstructed from the existing video frame captures by detecting likely slide regions with OpenCV, cropping/upscaling those regions, deduplicating similar crops, and OCRing the cropped slide images locally. It is a cleaner companion to the full-stage frame deck.

## Reconstructed Slides
![[assets/reconstructed-slides/lY1iFbDPRlw/slide-001.jpg]]

- Source frame: `slide-001.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `173.48`
![[assets/reconstructed-slides/lY1iFbDPRlw/slide-002.jpg]]

- Source frame: `slide-002.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `177.46`
![[assets/reconstructed-slides/lY1iFbDPRlw/slide-003.jpg]]

- Source frame: `slide-003.jpg`
- Crop: `contour` `[0, 0, 960, 540]` score `176.61`
![[assets/reconstructed-slides/lY1iFbDPRlw/slide-004.jpg]]

- Source frame: `slide-004.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `166.52`
![[assets/reconstructed-slides/lY1iFbDPRlw/slide-005.jpg]]

- Source frame: `slide-005.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `154.99`
![[assets/reconstructed-slides/lY1iFbDPRlw/slide-006.jpg]]

- Source frame: `slide-006.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `170.14`
![[assets/reconstructed-slides/lY1iFbDPRlw/slide-007.jpg]]

- Source frame: `slide-007.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `166.18`
![[assets/reconstructed-slides/lY1iFbDPRlw/slide-008.jpg]]

- Source frame: `slide-008.jpg`
- Crop: `full` `[0, 0, 960, 540]` score `177.03`
## Dense Scene-Detected Slide Candidates
- [[youtube-lY1iFbDPRlw-dense-slides]]