창작 및 미디어 · GitHub

A cross-platform High-performance FFmpeg based Real-time Video Frames Decoder in Pure Python 🎞️⚡

• High-performance, low-overhead video frames decoding with robust error-handling.
• Flexible API with access to almost any FFmpeg specification thinkable.

독창적인 선도적 기능을 풍부하게 갖춘 고성능 크로스 플랫폼 동영상 처리 Python 프레임워크 :fire:

Modded version of shellphish. Mod Features are Colourized Text, Animations, In built setup for Termux, Extra features, More improvements, Bugs cleared, Fixed URL not showing.

• Colourized Text
• In-built Setup for Termux

Veo 3.1 Lite API (`veo-3.1-lite`): model id, pricing, parameters and copy-paste examples for the OpenAI-compatible APIMart endpoint.

Veo 3.1 Lite prompts: tested image prompt recipes with example renders, aspect ratios, the model id (`veo-3.1-lite`) and the cost per image.

MiniMax H3 API (`MiniMax-H3-Context-IR`): model id, pricing, parameters and copy-paste examples for the OpenAI-compatible APIMart endpoint.

MiniMax H3 prompts: tested image prompt recipes with example renders, aspect ratios, the model id (`MiniMax-H3-Context-IR`) and the cost per image.

A native Application , With Agentic Support (MCP) for ultra fast AI image generation using a highly optimized Z-Image-Turbo model with SDNQ quantization. Supports Text-to-Image, Image-to-Image transformation, and Inpainting with mask-based editing. Optimized for Nvidia/AMD devices.

• Model Selection: Choose between speed-optimized, quality-optimized, or base models
• LoRA Support: Drop .safetensors files into models/loras/ to dynamically load styles (Experimental)

On-device, ComfyUI-style node graph for image/video diffusion on Android. Run MiniMax H3 and WAN 2.2 14B on the Qualcomm Hexagon NPU. SD1.5, SDXL, Flux, Z-Image, Anima, Qwen Image 2.1, Krea 2 & MOSS Image. Inpainting, outpainting, ControlNet, LoRA, IP-Adapter & LivePortrait. Fully offline, no server, no account.

:smiley_cat: A tool designed to shorten steps needed to import and optimize models into VRChat. Compatible models are: MMD, XNALara, Mixamo, DAZ/Poser, Blender Rigify, Sims 2, Motion Builder, 3DS Max and potentially more

• Optimizing model with one click!
• Creating lip syncing

Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal isolation, and multilingual translation.

에이전트를 위한 애니메이션 엔진입니다. Manim의 Python API와 Rust GPU 코어를 기반으로 수학 및 3D 동영상을 놀라울 정도로 빠르게 제작합니다.

A color management framework for visual effects and animation.

Open Source API and interchange format for editorial timeline information.

A Real-time ray-traced renderer based on Rust + vulkan

ACE-Step: A Step Towards Music Generation Foundation Model

거의 모든 상용 대안보다 뛰어난, 가장 강력한 로컬 음악 생성 모델입니다. Mac, AMD, Intel 및 CUDA 기기를 지원합니다.

Consumer AI app for chat, image generation, video generation, and music creation powered by Ace Data Cloud APIs.

Kling 3.0 Motion Control API (`kling-v3-motion-control`): model id, pricing, parameters and copy-paste examples for the OpenAI-compatible APIMart endpoint.

Kling 3.0 Motion Control prompts: tested image prompt recipes with example renders, aspect ratios, the model id (`kling-v3-motion-control`) and the cost per image.

Open 3D Model Viewer - A quick and powerful 3D model viewer

Blender, 이미지 생성, 서브 에이전트 평가를 활용해 인상적인 3D 비주얼을 만드는 에이전트 스킬