text2video 开源项目推荐（46 个）

huggingface /diffusers

Diffusers：用于在 PyTorch 中进行图像、视频和音频生成的最先进扩散模型。

camenduru /stable-diffusion-webui-colab

稳定扩散webui colab

PKU-YuanGroup /Helios

[TPAMI 2026🔥] Helios: Real Real-Time Long Video Generation Model

tin2tin /Pallaidium

PALLAIDIUM -一家生成式人工智能电影工作室，无缝集成到Blender Video Editor（VSE）中，实现从剧本到屏幕和返回的端到端制作。

kabachuha /sd-webui-text2video

Auto 1111扩展仅使用Auto 111 webui依赖项来实现text2 video扩散模型（例如Model Scope或VideoCrafter）

bravekingzhang /text2video

半个神器👉一键文本转视频的工具

Sxela /WarpFusion

WarpFusion

ExponentialML /Text-To-Video-Finetuning

Finetune ModelScope's Text To Video model using Diffusers 🧨

VisActor /skills

Agent skills for the VisActor visualization ecosystem.

G-U-N /Gen-L-Video

The official implementation for "Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising".

diffusion-motion-transfer /diffusion-motion-transfer

Official Pytorch Implementation for "Space-Time Diffusion Features for Zero-Shot Text-Driven Motion Transfer""

JiaqiLi404 /IAmDirector-Text2Video-NextJS-Client

本项目开源基于NextJS的前端， 希望能够提供一个用于生成式AI的文字转视频， 尤其是电影从编剧到视频生成的Web前端平台参考。Everyone can become a director. The Nextjs front-end of an AI driven platform for automatic movie/video generation (form GPT script generation to text2video movie generation).这是一个免费试用AI视频创作平台，集成了基于GPT的视频剧本生成和视频生成功能。 我们的理想是让每个人都能成为导演，以最快的方式将日常中的任何创意转化为高质量的视频， 无论是电影、营销视频、还是自媒体视频。

diStyApps /VisionCrafter

Craft your visions

AndrewAltimit /template-repo

Agent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanistic interpretability on sleeper agents, and agent integration via CLI wrappers

UmiMarch /OpenVideo

OpenVideo specializes in the domain of text-to-video generation, with the goal of providing high-quality and diverse video datasets to AI researchers globally.

QuanjianSong /T2I-Metrics

Inference pipeline for some Text-to-Image metrics.

v8hid /infinite-zoom-stable-diffusion

resources for creating Ininite zoom video using Stable Diffiusion, you can use multiple prompts and it is easy to use.

kabachuha /InfiNet

在NUWA-XL中实现了基于ModelScope text2video模型的ControlNet类模块，实现了极长视频生成的跨度。

cuinjune /text2video

A software tool that converts text to video for more engaging learning experience

michaelzhang-ai /vid2vid

A modified version of vid2vid for Speech2Video, Text2Video Paper