VA

mihirp1998/VADER

Video Diffusion Alignment via Reward Gradients. We improve a variety of video diffusion models such as VideoCrafter, OpenSora, ModelScope and StableVideoDiffusion by finetuning them using various reward models such as HPS, PickScore, VideoMAE, VJEPA, YOLO, Aesthetics etc.

312 15 +0/wk
GitHub
alignment diffusion reinforcement-learning reinforcement-learning-human-feedback rl rlhf vader video-diffusion video-diffusion-alignment
Trend 0

Star & Fork Trend (19 data points)

Stars
Forks

Multi-Source Signals

Growth Velocity

mihirp1998/VADER has +0 stars this period . Velocity data will be available after more historical data is collected.

Deep analysis is being generated for this repository.

Signal-backed technical analysis will be available soon.

Metric VADER three-man-team hud-python tiledesk-dashboard
Stars 312 312312311
Forks 15 3654131
Weekly Growth +0 +0-7+0
Language Python ShellPythonTypeScript
Sources 1 111
License N/A MITMITMIT

Capability Radar vs three-man-team

VADER
three-man-team
Maintenance Activity 0

Last code push 393 days ago.

Community Engagement 69

Fork-to-star ratio: 4.8%. Lower fork ratio may indicate passive usage.

Issue Burden 70

Issue data not yet available.

Growth Momentum 30

No measurable growth in the current period (first-day cold start expected).

License Clarity 30

No clear license detected — proceed with caution.

Risk scores are computed from real-time repository data. Higher scores indicate healthier metrics.