A collection of text-to-video generation studies.

✨ Hotshot-XL: State-of-the-art AI text-to-GIF model trained to work alongside Stable Diffusion XL

Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions.

A curated list of Text-to-Video Generation papers and BibTeX entries

Sora AI Video Generator by Get Sora App

[Arxiv 2024] Official pytorch implementation of "VideoElevator: Elevating Video Generation Quality with Versatile Text-to-Image Diffusion Models"

A pipeline to generate long videos according to text prompt

Zero-Shot Text to Video Generation

[ICLR 2024] LLM-grounded Video Diffusion Models (LVD): official implementation for the LVD paper

A benchmark for evaluating hallucination of text-to-video models

SafeSora is a human preference dataset designed to support safety alignment research in the text-to-video generation field, aiming to enhance the helpfulness and harmlessness of Large Vision Models (LVMs).

[ECCV 2024 Oral] MotionDirector: Motion Customization of Text-to-Video Diffusion Models.

Generate a video script, voice and a talking face completely with AI

Script that generates TikTok style videos using ffmpeg, moviepy, chatGPT, and SDXL api within a minute

Text to Video API generation documentation

A python tool that uses GPT-4, FFmpeg, and OpenCV to automatically analyze videos, extract the most interesting sections, and crop them for an improved viewing experience.

[NeurIPS 2024] VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models

Clip any moment from any video with prompts

Faceless Video Engine

Implementation of "SAVE: Spectral-Shift-Aware Adaptation of Image Diffusion Models for Text-guided Video Editing" Paper