

LEGENDARY
v1.0.0Taher Warzone
Detect enemy body — 3 sizes (L, M, S) included
Three model sizes (L, M, S). Optimized enemy body detection with built-in team ignore.
TeamIgnore
Available onAE
SizesL / M / S
PRICE
$35
Overview
🧪 MODEL VERSIONS
This weight ships with 3 model sizes — Large (L), Medium (M), and Small (S). All versions are trained on the same dataset but differ in size, which directly affects detection precision, inference speed, and overall responsiveness.
Multiple versions were provided intentionally because different players prefer different behaviors and performance profiles. We recommend testing all three to find what works best for your playstyle.
🎯 OPTIMIZED BOUNDING BOXES
The bounding boxes are specifically optimized so that the enemy is always centered within the box. This prevents the common problem where the aim locks to the center of the box while the actual target is offset.
Results:
• Higher headshot consistency
• More stable tracking
• Aggressive and precise aim behavior
• Better alignment between detection and aim
🧩 TEAM IGNORE SYSTEM
Built-in team ignore system. To ensure proper functionality:
• Teammates must have abbreviated names in-game
• Default in-game colors must be used
This prevents detection conflicts and avoids locking onto teammates.
⚡ RECOMMENDED BUILDS
• L & M → highly recommended on FP16
• S → recommended on FP32
• Image size → 640 × 640
🎮 AE CONFIGURATION NOTES
Different model sizes may need slight adjustments. Smaller models process faster, so aim speed may need to be increased accordingly.
Example: if ADS Aim Speed = 4 on L, you may need to set it to 5 on M.
Fine-tuning is recommended for optimal results across all three sizes.
Recommended Settings
Optimal Configuration
Image Size
640 × 640
L Precision
FP16
M Precision
FP16
S Precision
FP32
REQUIRED
Player Names
Abbreviated
REQUIRED
Team Colors
Default
L ADS Aim Speed
4 (example)
M ADS Aim Speed
5 (example)
Key Features
3 model sizes (L, M, S) included
Optimized bounding boxes (enemy always centered)
Higher headshot consistency
More stable tracking
Built-in team ignore system
Trained on identical dataset across sizes