Locally Uncensored：桌面本地 AI 工作室

The all-in-one local AI studio for your desktop: chat, image and video generation and a coding agent in one free, open source app. Window…

Locally Uncensored The all-in-one local AI studio for your desktop. Chat, images, video and a coding agent in one app. Install it, pick a model, go. Free and open source. In local mode everything runs on your own machine. No Docker, no terminal, no config files. The platforms are listed under Download. Download · Three steps · What is in the box · How it compares · Models · FAQ Chat that draws your images Images and video in the same window The coding agent shows the diff first Agent mode does the legwork Download Take the latest build from Releases. Platform File Status Windows 10 and 11 Locally.Uncensored_3.0.7_x64-setup.exe (NSIS, recommended) or Locally.Uncensored_3.0.7_x64_en-US.msi Tested every release, signed auto update channel Linux Locally.Uncensored_3.0.7_amd64.AppImage, Locally.Uncensored_3.0.7_amd64.deb or Locally.Uncensored-3.0.7-1.x86_64.rpm Built on every release macOS 14 or newer, Apple Silicon (Beta) LU_3.0.7_aarch64.dmg Signed with an Apple Developer ID and notarized by Apple. Intel Macs are not supported. The app has run on one Mac so far. Voice has been tried by hand in the app on a Mac and works. Computer control is in the Mac app but not fully tested yet on macOS. Remote Access and the automatic update are not confirmed on macOS Android 7.0 or newer (arm64) LU-3.0.7-Android.apk The phone app. Not in the Play Store yet: install the file from this page. SHA-256 2f4e2c60f2edde2705c31ca324b5ba952a84efa8eec3075f4f45f2a29a806fb6 Some antivirus engines flag unsigned NSIS installers that download other binaries, which is a false positive. The installer is built by GitHub Actions from the public source on master, and the update channel is signed against a public minisign key, so you can verify both: see SECURITY.md. Code signing for the Windows installers: free code signing provided by SignPath.io, certificate by SignPath Foundation. SignPath Foundation has accepted the project. The production certificate is not in place yet, and until it is the installers ship unsigned. Current release: v3.0.7 (October 2026). Every change since 1.0.0 is in CHANGELOG.md. 3.0.7 brings REA (Reverse Engineer Anything) as a plugin: switch it on under Plugins in the desktop app, and Agent and Code can take apart apps and files (it needs Node.js and works best with a model of about 27B and 64K context; a full analysis has run on one Mac so far, and on Windows it has started from the built app). LU Cloud now has DeepSeek V4.1 Flash 1017, ready to pick in Chat. A chat can be duplicated or branched from any message, character cards turn into personas with their greeting, a persona can carry a reminder, group chats got a round of fixes, and auto compact is on by default. A character you trained works in every part of Create and in chat, and a Mac can train one too. ComfyUI workflows import the way ComfyUI saves them, a whole folder at once, with the node packs they need, and LU now uses the shared model folders set in ComfyUI. In Create, Edit takes as many reference images as the graphics memory holds (up to ten on a Mac), Enhance Image runs on your own machine, and on a Mac Talking Character, Motion Control, Music, Enhance Image, Remove Background and masks in Edit run locally. There is an Android app now, see Mobile app below. The iPhone app is in review at the App Store. Some of it has only been checked in tests so far; the CHANGELOG says which. 3.0.5 was about Create: LTX 2.5, FastH3 and YuE2 run on your own machine, Qwen-Image 2.1 gets a transparent background and its prompt enhancer, Edit, Remove Background and Enhance Image take up to 50 images in one go, and LU Cloud adds Qwen Image 2.1, LTX 2.5, MiniMax H3 and Wan 3.0 Reference. Chat takes any file, each model in a group chat can have its own persona, dropdowns stay inside the window (issue 149), and the speech install works again on Ubuntu 24.04. 3.0.4 fixed the Code agent and the agent in chat on LU Cloud: writing a long file no longer ends the run, "continue" picks up where a run stopped instead of starting over, the agent keeps a plan only when you ask for one, and cloud context is 32K by default and can be set per model. It also fixed the bugs reported on GitHub and Discord since 3.0.3 (issues 144 to 147): MiniMax H3 runs as a video model with sound, Edit takes up to three extra images with Qwen-Image 2.1, a missing encoder or VAE is named and offered as a download instead of ending in "Value not in list", the LoRA stack follows the loras folder, and group chat works with every LU Engine model. 3.0.3 was a hotfix: chats with many images no longer run the app out of memory, Create reads a model's family from the file instead of its name, and the five bugs reported on GitHub since 3.0.2 are fixed (issues 139 to 143). 3.0.2 was a hotfix: the Code tab lost its scrollbar and its input box once a conversation grew taller than the window (issue 138, a regression in 3.0.1) and is held to the window height again, and the count of open cloud models now takes the Create Studio endpoints in, which makes it fourteen video models and seven image models. What is new in 3.0.1 Qwen-Image 2.1 runs locally on Windows and Linux. One model generates a picture from a prompt and edits one from a reference image, with no mask to paint. About 16 GB of files, ComfyUI 0.37.0 or newer, and a research license that does not allow commercial use. Models has a LoRAs tab of its own. Search CivitAI, download into ComfyUI's models/loras folder, see what is installed with its size and trigger word, and delete what you no longer want. A GPU whose free memory could not be measured is planned more carefully, and the log now says total capacity instead of calling it free. The Linux AppImage stops handing its own runtime to every program LU starts, so a healthy system Python, pip, git or ffmpeg keeps working, and a distribution that blocks pip in the system Python keeps the isolated environment LU built. The local model runs one conversation at a time and says so, with a line