Global radar

针对 RTX 3060 6GB 优化的 SDXL / Illustrious 风格 LoRA 训练脚本，纯 diffusers + peft，一键输出 ComfyUI 通用格式

[NVIDIA ONLY] Stable Video Diffusion Streamlit App. Currently supports Nvidia GPU machines only.

DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior

Free & open source AI video platform — Clip Generator, AI Shorts (UGC with AI actors) & YouTube Studio. Self-hosted, no watermarks.

Locally colorize black-and-white public domain movies and historical photos with DDColor. Runs on CPU, Intel Graphics, Apple Silicon, or NVIDIA CUDA.

Unified Image Understanding and Generation. Text-to-Image Generation, In-context Generation, Instruction-guided Image Editing, Visual Understanding (Minimum Requirements 12GBV RAM / 48GB RAM, Recommended Requirements 24GB VRAM / 32GB RAM)

High-quality image generation and editing powered by SenseNova-U1-8B-MoT (NEO-Unify architecture). Supports text-to-image, image-to-image editing, and reasoning mode.

Local AI YouTube video generator: script, scenes, voiceover, thumbnail and MP4 export.

NVIDIA's Audio Flamingo 3 - Large Audio-Language Model for speech, sound, and music understanding with Gradio web interface

Opal — The open-source everything media player & browser. Jellyfin/Stremio/Kodi alternative for macOS, Linux & Windows.

FLUX.2 Klein 4B studio (Apache 2.0, 4 steps), Fooocus-style, 100% local: txt2img, multi-reference editing in the SAME pipeline (up to 4 refs, no second model), inpaint/outpaint, ESRGAN+refine upscale, LoRA, styles, Describe/Improve & Vision Mix (Ollama), Remove BG, Face Swap. ~15 GB VRAM for everything. Note: klein is distilled, so negative prompts and CFG have no effect. Fork of crispz-qwen-edit. https://github.com/mikecastrodemaria/crispz-klein

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Open-source Seedance 2.0 video generator — production-ready Next.js SaaS for text-to-video and multi-image reference editing. Stripe billing, credits, NextAuth, and Prisma out of the box.

DALL·E Mini - Generate images from a text prompt

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Open-source alternative to Opus Clip, Vidyo.ai, Klap & SubMagic. Turn long-form YouTube videos into viral 9:16 shorts using LLM highlight detection, Whisper transcription, and auto vertical cropping — free, no watermarks, no per-clip credits.

Contribute to MultiSet-AI/multiset-unity-sdk development by creating an account on GitHub.

Native Windows music studio for YuE2-3B, with local model downloads, song editing, lyrics, covers and video tools.

[AAAI 2025] Official implementation of "OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on"