shim0114/T2V-Diffusion-Search

[NeurIPS 2025] Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search

31
/ 100
Emerging

This helps researchers improve the quality of text-to-video generation, making the generated videos better match the input text description. It takes a text prompt and an existing video generation model, and produces a higher-quality video output. This tool is for AI researchers or machine learning engineers focused on advancing text-to-video capabilities.

Use this if you are a researcher working with text-to-video generation models like Latte, CogVideoX, or Wan 2.1 and want to enhance the alignment between your input text and the resulting video.

Not ideal if you are looking for an end-user application to generate videos without deep technical setup, as this requires familiarity with machine learning environments and model configurations.

AI-research video-generation generative-AI deep-learning text-to-video
No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

14

Forks

Language

Python

License

Apache-2.0

Last pushed

Feb 24, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/shim0114/T2V-Diffusion-Search"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.