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.
TypeScript ai-photo-editorcomfyui-alternativegenerative-fillimage-editingimage-generationinpaintinglinuxlocal-aimacosmcpmcp-servernano-banana-alternativeofflinephoto-editorprivacyqwen-imageqwen-image-2-1stable-diffusion-cppvulkanwindows
# Kokon on an NVIDIA GPU, used from a browser: http://<this computer's address>:39152
# Needs the NVIDIA Container Toolkit. In the folder with this file, start it, then set the
# password once:
#
# docker compose up -d
# docker exec -it kokon kokon-service --set-password
#
# Update to a new version: docker compose pull && docker compose up -d
# Guide: docs/docker.md. For access from outside your home use Tailscale or another VPN
# (docs/remote-access.md), never port forwarding on your router.
services:
kokon:
# Published by each release; ":0.11" stays on 0.11.x instead of following new versions.
image: ghcr.io/gabrielelozupone/kokon:latest
container_name: kokon
restart: unless-stopped
ports:
# Every network interface of this computer. Docker's published ports skip host firewalls
# such as ufw; to reach Kokon only from this computer use "127.0.0.1:39152:39152".
- "39152:39152"
volumes:
- kokon-data:/data # engine, models (~13 GB), gallery database
- kokon-config:/config # settings
- kokon-gallery:/gallery # the images you save
# A folder of your own instead (Kokon runs as uid 1000, so it must own it):
# mkdir -p ~/kokon-gallery && sudo chown 1000:1000 ~/kokon-gallery
# - ~/kokon-gallery:/gallery
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]
volumes:
kokon-data:
kokon-config:
kokon-gallery: