sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
- 39k
- Python
- Apache-2.0
- 35 min ago
SGLang is a high-performance serving framework for large language models and multimodal models.
Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,Minimax H3,...) inference in pure C/C++
Copy-ready prompts for the leading AI video and image models, each with its real output and source. Plus agent recipes for editing video.
An all-in-one, 100% local AI video, image, and music studio. Director mode plans full music videos and short films from a single prompt. Built on the WanGP pipeline. Install via Pinokio.
Local-first, agent-native control plane for ComfyUI — MCP server + sidebar agent that generates images, video & audio, authors and runs workflows, and edits your live graph in natural language on ANY LLM (Claude, ChatGPT, Gemini, offline Ollama, or any hosted model). 178 tools, 36 AI skills, 55 installer packs. Local, LAN, VPS, or Comfy Cloud.
FlashRT is a high-performance realtime inference engine for small-batch, latency-sensitive AI workloads. The flagship integration is production VLA control for Pi0, Pi0.5, GROOT N1.6, and Pi0-FAST. Also support llm e.g, qwen3.6-27B
[EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLMs, VLMs, and video generative models.
Uncensored NSFW AI video generation API & generator for adults — Seedance Spicy & Wan NSFW, AI character & companion video, 18+ text-to-video / image-to-video, async tasks, webhooks, credits billing. 成人向 AI 视频生成 API:Seedance Spicy、Wan NSFW、AI 角色/陪伴视频、文生/图生视频、异步任务、积分计费、接入指南。
AI video generation SDK — JSX for videos. One API for Kling, Flux, ElevenLabs, Veed. Built on Vercel AI SDK.
The open creative studio on ComfyUI: images, video, 3D and audio on open weights, on your own GPU or the cloud. Camera motions, effects, apps, Cinema, Layers, Image to 3D and an AI agent.
Thinking with Videos from Open-Source Priors. We reproduce chain-of-frames visual reasoning by fine-tuning open-source video models. Give it a star 🌟 if you find it useful.
all ComfyUI http/ws APIs. support NodeJS / Browser environments. and advanced programmable workflow.
ReShot — copy the shot, not the actors. Video → depth map, OpenPose skeleton or canny lines for Seedance 2.0/2.5 reference video, MiniMax H3 Fun ControlNet and Wan VACE. Apache-2.0. Open-sourced by Maosika 猫斯卡 (www.maosika.com), the AI short-drama production system.
Training-Free (Inversion-Free) methods meet WAN2.1-T2V🤗
[arXiv 2026] This is the official PyTorch implementation of "MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators".
NEW: LoRA size guard, CPU downloads & AI scene planning
Runs in the browser on Hugging Face
ComfyUI custom nodes for Seedance, Wan, and MiniMax H3 Spicy/uncensored-style video generation via MuAPI, plus 600+ image, video, audio, and enhancement models.
Self-hosted AI studio for images, video and music on your own GPU. Multi-user with logins and limits, no node graphs, drivable over MCP.
This allows you to utilize Google Colab (or other notebooks) to run wan2.2 image to video
Unified wan2gp installer for NVIDIA, AMD and Apple Mac, with Python 311, Pytorch 2.10 and NVFP4 Support for RTX50. Super Optimized Gradio UI for AI video creation (6GB+ VRAM). Wan 2.1/2.2, Qwen, Hunyuan Video, LTX Video, Flux and OVI and more. (AMD Windows supported by 7900(XT), 7800(XT), 7600(XT), Phoenix, 9070(XT) and Strix Halo)
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.
[ICLR 2026] This is the official PyTorch implementation of "QVGen: Pushing the Limit of Quantized Video Generative Models".
Turn a story into a finished film — on your own Mac, no cloud. Story Forge is a local-only generative cinema pipeline: stills, motion, voices, music, grade, and sound, start to finish. Flux · LTX-2 · Piper · ACE-Step · ffmpeg — built for and running 100% on a Mac (M5, 128GB).
Multimodal prompt generator nodes for ComfyUI, designed to generate prompts for QwenImageEdit and Wan2.2. Supports local LLM / local GGUF models (Qwen2.5-VL, Qwen3-VL, Qwen3.5, Qwen3.6 and Qwen3.8) and Qwen API for image and video prompt generation and enhancement.
ComfyUI custom nodes for Wan 3.0 — text-to-image, image edit, text-to-video, and image-to-video via MuAPI.
Uncensored AI video generator in ComfyUI: run unrestricted (spicy) video models like Seedance, Wan and MiniMax H3 with no GPU, via the Muapi nodes.
Uncensored Wan 3.0 API wrapper (Python): relaxed-moderation Alibaba video generator via MuAPI with synchronized audio and high motion.
Uncensored AI video generator API examples: Seedance 2.5/2, Wan 3.0, MiniMax H3 spicy text-to-video, image-to-video and reference-to-video endpoints compared on Muapi
Uncensored AI image generator in ComfyUI: run unrestricted, low-filter image models like Seedream, Qwen Image, Wan 2.7 and Grok Imagine with no GPU, via the Muapi nodes.
Wan 2.2 I2V with LoRA tools and scene continuation.
Runs in the browser on Hugging Face
Text to video model, used with diffusers.
Uncensored AI image generator API examples: Seedream, Qwen Image, Wan 2.7, Grok Imagine and Z-Image text-to-image and image-editing endpoints compared on Muapi
Text to video model, used with diffusers.
Autonomous music video director — Qwen plans theme, shot list, and cinematic prompts; Wan 2.1 generates the clips; output is a complete edit-ready manifest
Wan 2.7 Video API examples in cURL and Node.js for text-to-video, image-to-video, video-to-video, and reference-to-video through PoYo. From $0.06 per second.
Wan 2.2 Fast API examples in cURL and Node.js for text-to-video and image-to-video through PoYo. From $0.03 per generation.