Video Generation Python Packages

sageattention

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

cd-fvd

[CVPR 2024] On the Content Bias in Fréchet Video Distance

vsa

A unified inference and post-training framework for accelerated video generation.

st-attn

A unified inference and post-training framework for accelerated video generation.

vllm-omni

A framework for efficient model inference with omni-modality models

gflow-cli

Drive Google Flow from the command line: Veo video and Imagen images, scripted, batched and pipeline-ready. Ships an MCP server so coding agents can drive it too, giving you and your agents full programmatic control over generation. Unofficial, alpha, not affiliated with Google.

mcp-kling

MCP server for Kling AI video generation via AceDataCloud API

mcp-luma

MCP server for Luma AI video generation via Ace Data Cloud.

mcp-seedance

MCP server for ByteDance Seedance video generation via Ace Data Cloud.

hydracept

Execution infrastructure for AI agents. Run text, reasoning, image, audio, video, 3D, domains, DNS, and more through one capability API—with durable jobs, transparent pricing, receipts, budgets, and BYOK.

mcp-wan

MCP server for Wan AI video generation via AceDataCloud API

mcp-sora

MCP server for OpenAI Sora video generation via Ace Data Cloud.

vbench

[CVPR2024 Highlight] VBench - We Evaluate Video Generation

mcp-veo

MCP server for Google Veo video generation via Ace Data Cloud.

mcp-hailuo

MCP server for Hailuo (MiniMax) AI video generation via AceDataCloud API

videopython

Python video editing with JSON plans, local AI, and MCP tools.

imagine-mcp

Image and video understanding + generation for AI agents -- across Gemini, OpenAI, and Grok.

mcp-maestro

MCP server for end-to-end AI video production with Maestro through Ace Data Cloud.

mlx-gen

Generative image and video runtimes for Apple Silicon (MLX): text/image-to-image, instruction editing, masked edit, text/image/reference-to-video, video editing, and restoration.

aquiles-image

A high-performance, memory-efficient inference server for diffusion models (image/video generation), compatible with the OpenAI client

mcp-happyhorse

Synced from AceDataCloud monorepo. Do not edit directly.

fastvideo-kernel

A unified inference and post-training framework for accelerated video generation.

xaikit-py

Unofficial Python kit for the xAI (Grok) API — typed client, model catalog, usage metering, image/video, and realtime voice

videogen

Python SDK for the VideoGen API (https://videogen.io)