{"id":50619192,"url":"https://github.com/light-and-ray/image-edit-bot-open-webui","last_synced_at":"2026-06-06T09:30:20.561Z","repository":{"id":359919040,"uuid":"1049535718","full_name":"light-and-ray/image-edit-bot-open-webui","owner":"light-and-ray","description":"An closedwebui bot-wrapper around comfyui api, for simple image + prompt workflows","archived":false,"fork":false,"pushed_at":"2026-05-24T04:27:25.000Z","size":1184,"stargazers_count":7,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"master","last_synced_at":"2026-05-24T06:32:55.742Z","etag":null,"topics":["ai-image-editing","bot","comfyui","flux-kontext-dev","image-editing","openwebui","qwen-image-edit"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/light-and-ray.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-09-03T06:01:30.000Z","updated_at":"2026-05-24T04:27:29.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/light-and-ray/image-edit-bot-open-webui","commit_stats":null,"previous_names":["light-and-ray/image-edit-bot-open-webui"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/light-and-ray/image-edit-bot-open-webui","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/light-and-ray%2Fimage-edit-bot-open-webui","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/light-and-ray%2Fimage-edit-bot-open-webui/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/light-and-ray%2Fimage-edit-bot-open-webui/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/light-and-ray%2Fimage-edit-bot-open-webui/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/light-and-ray","download_url":"https://codeload.github.com/light-and-ray/image-edit-bot-open-webui/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/light-and-ray%2Fimage-edit-bot-open-webui/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33977371,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-06T02:00:07.033Z","response_time":107,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-image-editing","bot","comfyui","flux-kontext-dev","image-editing","openwebui","qwen-image-edit"],"created_at":"2026-06-06T09:30:19.983Z","updated_at":"2026-06-06T09:30:20.547Z","avatar_url":"https://github.com/light-and-ray.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Qwen/Flux Kontext Image edit (and not only) bot for Openwebui\n\nThis is a simple bot for [\u003cs\u003eopen\u003c/s\u003eclosedwebui](https://github.com/open-webui/open-webui) that allows you to create a channel-wrapper around any [ComfyUI](https://github.com/comfyanonymous/ComfyUI) workflow that has one prompt or one image input, and one image output\n\nThis repo is based on two examples: [open-webui/bot](https://github.com/open-webui/bot) and [websockets_api_example.py](https://github.com/comfyanonymous/ComfyUI/blob/master/script_examples/websockets_api_example.py)\n\n## Requirements\nYou can use the same environment that openwebui uses (it already has all dependencies), or create your own. Dependencies are `pip install dotenv pillow websocket-client python-socketio`\n\n![](screenshot.png)\n\n## How to set it up:\n- enable channels in openwebui's admin setting\n- create an account with admin rights for your bot\n- create a channel with your desired name, e.g. `qwen-image-edit`. Make it public or private for the same group where both you and bot are\n- have a working comfy ui with your workflow. I assume you already have it\n- put text `prompt here` as a prompt (the bot will find the node by this text and replace it with proper prompt)\n- delete all preview image nodes and similar, you need to have only one image out\n- export it for API, and put the json file inside bot's `workflows/` directory. For example, `workflows/qwen_image_edit.json`\n- set up `.env` file: the most important are bot's token and mapping *channel name* -\u003e *workflow name*\n- run the bot (`main.py`), openwebui and comfyui\n\n## .env structure\n```bash\nWEBUI_URL=\"...\" # default http://localhost:8080\nTOKEN=\"...\" # see below\nCOMFY_ADDRESS=\"...\" # default localhost:8188\nMAP_CHANNEL_NAME_WORKFLOW=\"...\" #  see below\nLAZY_IMAGE_URLS=0 # default 0, see below\n```\n\n### TOKEN\nTo get it, log into bot's openwebui profile, go to `Settings` -\u003e `Account` -\u003e `API keys` -\u003e `JWT Token`\n\nAuthentication and secure for ComfyUI connection is not supported. If you do it, please make a PR\n\n### MAP_CHANNEL_NAME_WORKFLOW\nThis is a dictionary in json format that maps workflow and channel name. For example and by default `\"{\"qwen-image-edit\": \"qwen_image_edit.json\"}\"` means the bot will handle all messages from *\"qwen-image-edit\"* channel, send all user's requests there into *\"workflows/qwen_image_edit.json\"*. You can add channels and workflows how many you want\n\n### LAZY_IMAGE_URLS\n`0` means the bot will send images in base 64 format, `1` - will send url from Comfy's `/view?filename=...`. For the second choice comfy's address should be available from a client and Comfy server should be turned on\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flight-and-ray%2Fimage-edit-bot-open-webui","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flight-and-ray%2Fimage-edit-bot-open-webui","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flight-and-ray%2Fimage-edit-bot-open-webui/lists"}