image2video 开源项目推荐（17 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。

TMElyralab /MuseV

MuseV: Infinite-length and High Fidelity Virtual Human Video Generation with Visual Conditioned Parallel Denoising

PKU-YuanGroup /Helios

[TPAMI 2026] Helios：真正的实时长视频生成模型

MyNiuuu /MOFA-Video

[ECCV 2024] MOFA-Video：通过冻结图像到视频扩散模型中的生成运动场适应实现可控图像动画。

SkyworkAI /SkyReels-A2

SkyReels-A2: Compose anything in video diffusion transformers

chenwr727 /Stock-Insight-AI

Stock-Insight-AI 一键生成股票与期货分析视频

PKU-YuanGroup /Helios-Page

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

Haoke98 /FrameDiffusion

A frame2frame, video2video Video Editor based on the stable-diffusion

Jonnnty /Wan2.2-Animate-14B-Quant-Compression

Mixed-precision quantization scheme (16/8/4bit mixed quantization) for the Wan2.2-Animate-14B model. Compresses the original 35GB base model to 17GB, balancing inference performance and model size.

B3o /Image2Video-Plugin-for-ChatGPT-on-WeChat

将图片转换为视频的插件，支持自定义动画效果。

SpikeStatesman /claude-generation-model-latest-version

The latest generation of Claude is Anthropic's state-of-the-art AI model series (headlined by Claude 5 / Claude Opus 5 and Claude Sonnet 5), engineered for advanced reasoning, agentic coding, multi-step problem solving, and complex enterprise workflows with an expanded 1-million-token context window.

Abdelhameed123 /DiffWind

🌬️ Model wind-driven object dynamics using a physics-informed, differentiable framework for accurate video-based reconstruction and interaction analysis.

wasuletter /DiffExplorer

该项目在 GitHub 上没有填写描述

topduke963 /AIFacefy_API

The API for AI Facefy Service.

6Morpheus6 /SkyReels

[NVIDIA ONLY] Compose anything in video diffusion transformers. (Requires 24GB VRAM)

Apriori-ronaldwilsonreagan190 /DiffVax

Enhance image resilience against diffusion-based edits with DiffVax, an optimization-free method designed for robust image immunization.

Nkosingiphile18 /ReelFlix

🎥 Discover and explore a sleek online film platform that aggregates and showcases personal video content with fast, responsive browsing and playback.