Topic Hub

Best Image-Text-to-Video Open Source Projects

This hub collects the best open source projects in Image-Text-to-Video and ranks them by both momentum and authority.

Data window: Last 7 days (with 24h tie-breakers for Trending now)

Last updated: Sep 17, 2026

Projects

5

GitHub stars

0

Hugging Face likes

6.1K

Replicate runs

967

Authority projects

Projects with the strongest long-term signal in Image-Text-to-Video, ranked by total stars, likes, or runs on their primary platform.

MiniMaxAI/MiniMax-H3

Hugging Face Model

Hugging Face Model
5.4Klikes

audio-to-video

Generate videos from audio and images or prompts in real-time.

Replicate
967runs

ByteDance/Bernini-R

Generate high-quality videos from text prompts using a unified framework.

Hugging Face Model
254likes

Phr00t/LTX2-Rapid-Merges

Generate videos from text or images using merged diffusion models.

Hugging Face Model
248likes

OpenMOSS-Team/MOVA-360p

Generate synchronized video and audio from images or text.

Hugging Face Model
195likes

Hidden gems

Smaller projects with unusually strong momentum. We look for lower total metrics plus positive 7-day growth.

OpenMOSS-Team/MOVA-360p

Generate synchronized video and audio from images or text.

Hugging Face Model
195likes
577d

audio-to-video

Generate videos from audio and images or prompts in real-time.

Replicate
967runs
1077d

ByteDance/Bernini-R

Generate high-quality videos from text prompts using a unified framework.

Hugging Face Model
254likes
277d

Phr00t/LTX2-Rapid-Merges

Generate videos from text or images using merged diffusion models.

Hugging Face Model
248likes
07d