Edit photos by describing the change, on your own GPU. A free, open-source alternative to Nano Banana and ChatGPT image editing: photos stay on your computer, no daily limit. One installer for Windows, Mac and Linux sets up the best open model (Qwen-Image 2.1). MCP server for AI agents.
Linux: plan, status and engine upkeep
Kokon supports Linux from 0.9.4 (x86_64, .deb + .rpm, NVIDIA CUDA and Vulkan for AMD/Intel),
next to Windows and macOS. Every release from now on ships all three.
The plan (decided 2026-10-16)
The app is already client/server: the UI talks to kokon-service only over HTTP (base URL + token,
src/lib/api.ts); the desktop shell just starts the service and hands the UI 127.0.0.1 + token
(src-tauri/src/lib.rs connect). So the three steps are one product started three ways:
- Native Linux app (this document, 0.9.4). Same app as Windows/Mac: local service on 127.0.0.1.
- Headless server + browser UI, then Docker.
kokon-serviceserves the built UI itself; network access is opt-in, off by default, with a real password (rate-limited) before anything listens beyond localhost; recommend Tailscale/VPN over exposing it. Docker = the same Linux build without a window, model folders mounted as volumes. Planned as 0.11.0. - Kokon as a client: the desktop app (Windows/Mac/Linux) connects to a Kokon server elsewhere.
"Connect to a server" in Setup/Settings (address + password);
connectreturns the remote URL. Needs: copy-image by bytes instead of a local path (Stage.tsx→copy_image), hide "Show in folder"/"Open logs", import/export by upload/download instead of paths (api.tsimportPath,exportGeneration), setup's "Use models I already have" picks a folder on the server, and a client/server version check.
Rough effort for one person: 1 = days, 2 = 3–5 days, 3 = about a week. Order: 1 → 2 (+Docker) → 3. Public promise: issue #15 comment (2026-10-16). #22 closed as its duplicate.
Decided (2026-10-22) for 0.11.0: the first remote client is the browser UI served by kokon-service
(the desktop app connecting to a server, step 3, comes later). Access is local network only, off by default,
behind a password with a limit on attempts; for access from outside, a guide to Tailscale or another VPN, never
direct exposure. Docker: an NVIDIA (CUDA) image first; a Vulkan image for AMD/Intel follows once it can be tested.
Why Kokon builds its own Linux engine
Upstream stable-diffusion.cpp publishes Linux zips for Vulkan, ROCm and CPU only, no CUDA, built on
Ubuntu 24.04: they need glibc 2.38, so they don't run on Ubuntu 22.04 or Debian 12. Kokon builds its
engine on Ubuntu 22.04 (glibc 2.35; the Vulkan build needs ≤ 2.34) with upstream's own flags and CUDA
architectures (61;70;75;80;86;89;90;100;120, CUDA 12.8).
Since 0.10 (current): one workflow builds every platform's engine.
- Fork:
GabrieleLozupone/stable-diffusion.cpp, branchkokon= upstream (UPSTREAM_BASE, now fd21ecf) + the text-generation commits for Prompt+ + workflowkokon.yml. ggml comes from Kokon's ggml fork (branchsdcpp-cuda-graphs-opt-in, CUDA graphs only for reused graphs). - A push to
kokonthat passes every job ofkokon.yml(or a manual run withcreate_release) publisheskokon-<n>-<commit>(nowkokon-1013-1814814):sd-kokon-<commit>-bin-Linux-Ubuntu-22.04-x86_64-{cuda12,vulkan,cpu,rocm-10.1.0}.zip, the Windows and macOS 15 zips,cudart-sd-bin-{linux,win}-cu12-x64.zipandSHA256SUMS.txt. A published release is never replaced (rebuilds aren't byte-identical and the app pins SHA-256). - The app pins it in
crates/qls-core/src/catalog.rs(ENGINE_TAG, LinuxENGINE_CUDA/ENGINE_VULKAN), andengine.jsonlists it under thekokonkey (linux_cuda,linux_vulkan), so Linux gets engine updates without an app release. The Linux CUDA runtime (CUDA_RUNTIME) stays pinned tokokon-linux-1d0a58a; it is only downloaded once.
Up to 0.9.4 (history; these releases still serve old apps, don't delete them): branch kokon-linux
(upstream commit + kokon-linux.yml) published kokon-linux-<commit>, and kokon-macos.yml published
kokon-macos-<commit> for macOS 15. First build: run 38885751650 (2026-10-16): Vulkan 12 min, CUDA
1 h 32 min. Its CUDA smoke test was wrong (sd-server links libcuda.so.1, which only the NVIDIA driver
provides, so it can't start in CI); the release was published by hand after a real check in WSL. The
workflows now only check libraries for CUDA.
Engine upkeep: check at every release (and when engine.json moves)
Upstream moves fast. Every platform follows the same release, so:
gh api repos/leejet/stable-diffusion.cpp/compare/<UPSTREAM_BASE>...masterand the upstream releases.- In the fork clone:
git fetch upstream,git switch kokon, rebase the Kokon commits onto the new upstream commit, setUPSTREAM_BASEinkokon.yml, push tofork. - The push runs
kokon.yml; when every job passes it publisheskokon-<n>-<new commit>. Check the glibc report in the build log. - Test on Windows (CUDA + Vulkan), Linux (WSL: engine download, one image, one Prompt+ job) and a Mac.
- Ship it: either bump
ENGINE_TAGand the pins incatalog.rswith an app release, or edit thekokonkey inengine.jsonon master (digests:gh release view <tag> -R GabrieleLozupone/stable-diffusion.cpp --json assets). Details in engineering-notes.md, "Engine updates".
Building and testing the Linux app
- Build machine: WSL Ubuntu-22.04 on the dev PC (installed 2026-10-16; sees the RTX 5070 Ti through
the Windows driver, so CUDA can be tested; windows open through WSLg). Clone on the Linux disk:
git clone -b master /mnt/c/AI/qwen-local-studio ~/kokon(never build from /mnt/c: npm would replace the Windows node_modules). Ubuntu'scargopackage is too old; use rustup (. ~/.cargo/env). - Release:
bash scripts/build-release-linux.sh --setuponce, thenbash scripts/build-release-linux.sh→dist-release/Kokon_<v>_amd64.deb,Kokon-<v>-1.x86_64.rpm,updater-linux-x86_64-{deb,rpm}.json. Signed with the same updater key as Windows/Mac (~/.tauri/kokon-updater.key, also found under /mnt/c/Users/*/.tauri). - g++-13 (ubuntu-toolchain-r PPA,
--setupinstalls it; since 0.12): the ONNX Runtime thatortdownloads (AI watermark, fast stickers) needs GCC 13's libstdc++ and Ubuntu 22.04 has GCC 11's.crates/qls-core/build.rslinks g++-13'slibstdc++.ainto kokon-service statically, so users need nothing new. The Docker image's build stage installs it too. - Quick run without packaging:
npm run build && cargo build -p kokon --release --features tauri/custom-protocol && ./target/release/kokon(without the feature the window loads the dev server and shows "Could not connect to localhost"). - In-app updates work on Linux: tauri-plugin-updater 2.13 installs
.deb/.rpmthrough pkexec;latest.jsonneedslinux-x86_64-debandlinux-x86_64-rpmentries. - Package dependencies (tauri.linux.conf.json): libssl3 / openssl-libs (reqwest native-tls), libgomp, libvulkan1 / vulkan-loader. HEIC photos can't be opened on Linux yet (message shown).
Status (2026-10-20)
- ✅ 0.9.4 (2026-10-16): first Linux release,
.deb+.rpm, enginekokon-linux-1d0a58a. - ✅ 0.10.0 (2026-10-20): Linux on Kokon's own
kokon-992-dfaab76like every platform (Prompt+ included), Linux entries inengine.json; crashed engine no longer leaves a job waiting forever (#28). - Builds: WSL Ubuntu-22.04,
build-release-linux.sh(section above). CUDA tested in WSL on the RTX 5070 Ti; LoRA (beta) not tested on Linux by us.
Later
- Real-hardware reports: AMD on Linux (swingtempo R9700, alean200), a non-WSL NVIDIA machine.
- AppImage? Not planned (large, and deb/rpm cover the main distros).
- Step 2 of the plan above (0.11.0, branch
server-0.11):kokon-serviceserves the UI it embeds (crates/qls-service/src/remote.rs); a second listener on all interfaces (remote_port, 39152) opens only with access on and a password set, and refuses the token; rules and tests inqls_core::remote. Guides: remote-access.md, docker.md. - Step 3 (the desktop app as a client). Decided 2026-10-23: when it comes, the app keeps two separate galleries, "This computer" and the server's, with a button to save a server image locally; no automatic sync (conflicts, duplicates, lost images). Away from home the server's gallery is reachable only through Tailscale or another VPN.