[{"data":1,"prerenderedAt":156},["ShallowReactive",2],{"seo-verification":3,"blog-heberger-comfyui-vps-en":6},{"google":4,"bing":5},"EycwPY2XMyTkVzas3n1ygeNJFGAH513qrMjfDljzsMQ","",{"id":7,"slug":8,"title":9,"excerpt":10,"readTime":11,"views":12,"isPinned":13,"publishedAt":14,"category":15,"categories":21,"featuredImage":23,"bgImage":24,"posterImage":25,"relatedSolution":26,"intro":28,"sections":29,"ctaTitle":112,"ctaBody":113,"ctaButton":114,"ctaUrl":115,"relatedPosts":116},19,"heberger-comfyui-vps","How to host ComfyUI on a VPS","Host ComfyUI on a VPS to generate Stable Diffusion images via node-based workflows, accessible remotely and automatable via API.",8,303,false,"2026-06-01T00:00:00+00:00",{"id":16,"name":17,"slug":18,"color":19,"icon":20},1,"Artificial Intelligence","intelligence-artificielle","bg-purple-500\u002F10 text-purple-400","ia",[22],{"id":16,"name":17,"slug":18,"color":19,"icon":20},null,"\u002Fblog\u002Fcovers\u002Fbg.svg","\u002Fblog\u002Fcovers\u002Fheberger-comfyui-vps-poster.svg",{"categorySlug":20,"appSlug":27},"comfyui","ComfyUI is the reference node-based interface for driving Stable Diffusion and diffusion models through reproducible visual workflows. Hosting it on a VPS, ideally with a GPU, turns it into an image-generation studio accessible remotely and automatable. Here is how to deploy it cleanly.",[30,34,44,47,87,109],{"type":31,"title":32,"body":33},"h2","Why self-host ComfyUI on a VPS","ComfyUI organizes image generation into node graphs: each step (model loading, prompt encoding, sampling, VAE) is a linkable, reusable block, which makes workflows reproducible and shareable in JSON format. Unlike an online generation service, self-hosting gives you control over the checkpoint models, the LoRAs, the ControlNets and the extensions, without censorship or quota. On a GPU VPS, you get a studio available 24\u002F7 that an entire creative team can use remotely, and whose API lets you industrialize generation from your own scripts or pipelines.",{"type":35,"title":36,"items":37},"ul","Concrete benefits of self-hosting",[38,39,40,41,42,43],"Reproducible node-based workflows, exportable as JSON and shareable within the team","Free library of checkpoints, LoRAs and ControlNets with no quota or censorship","HTTP API to automate generation from your scripts and pipelines","Remote GPU accessible 24\u002F7 without tying up a local workstation","Installation of custom nodes (community extensions) without restriction","Cost control: a GPU VPS by the hour or the month rather than paying per image",{"type":31,"title":45,"body":46},"Hardware and software prerequisites","ComfyUI leverages a GPU for reasonable generation times. Aim for a VPS with an NVIDIA GPU with at least 8 GB of VRAM for SDXL (12 to 16 GB recommended for recent models like Flux), accompanied by 4 vCPUs, 16 GB of system RAM and 50 GB of disk or more, since checkpoints each weigh several gigabytes. CPU execution remains possible but very slow, to be reserved for testing. On the software side: NVIDIA drivers and the NVIDIA Container Toolkit for Docker, Docker and Docker Compose, and a domain pointing to the VPS to expose the interface.",{"type":48,"title":49,"headers":50,"rows":54},"comparison","ComfyUI versus AUTOMATIC1111 (Stable Diffusion WebUI)",[51,52,53],"Criterion","ComfyUI","AUTOMATIC1111",[55,59,63,67,71,75,79,83],[56,57,58],"Approach","Visual node-based workflows","Classic tabbed interface",[60,61,62],"Reproducibility","Excellent (workflow exported as JSON)","Limited to the entered parameters",[64,65,66],"VRAM consumption","Optimized, handles small GPUs better","More demanding at equal configuration",[68,69,70],"Learning curve","Steeper (graph logic)","More approachable for beginners",[72,73,74],"API automation","Native and granular","API present but less flexible",[76,77,78],"Recent models (Flux, SD3)","Fast, reference-grade support","Often later support",[80,81,82],"Custom nodes \u002F extensions","Very rich node ecosystem","Large extension catalog",[84,85,86],"Ideal use case","Advanced pipelines and automation","Fast interactive generation",{"type":88,"title":89,"steps":90},"steps","Deploying ComfyUI with a GPU",[91,94,97,100,103,106],{"title":92,"body":93},"Prepare the GPU VPS","On a VPS with an NVIDIA GPU, install the drivers then the NVIDIA Container Toolkit so that Docker can access the GPU. Validate with `docker run --rm --gpus all nvidia\u002Fcuda:12.4.0-base-ubuntu22.04 nvidia-smi`.",{"title":95,"body":96},"Run ComfyUI in a container","Start a ComfyUI image with GPU access and persistent volumes: `docker run -d --gpus all -p 127.0.0.1:8188:8188 -v \u002Fopt\u002Fcomfyui\u002Fmodels:\u002Fapp\u002Fmodels -v \u002Fopt\u002Fcomfyui\u002Foutput:\u002Fapp\u002Foutput --name comfyui \u003Cimage-comfyui>`. Restricting to 127.0.0.1 avoids direct exposure.",{"title":98,"body":99},"Install the models","Drop your checkpoints into `\u002Fopt\u002Fcomfyui\u002Fmodels\u002Fcheckpoints` and your LoRAs into the corresponding folder. On the next interface refresh, ComfyUI automatically detects the new models.",{"title":101,"body":102},"Load a first workflow","Open the interface, load the default text-to-image workflow, select a checkpoint and launch a test generation to confirm that the GPU is indeed used (check with `nvidia-smi`).",{"title":104,"body":105},"Reverse proxy, SSL and authentication","ComfyUI has no native authentication. You absolutely must place Caddy or Nginx in front of port 8188 with Let's Encrypt HTTPS and basic auth, otherwise your GPU is open to everyone. Increase the proxy timeouts since generations can be long.",{"title":107,"body":108},"Lock down and expose","Close port 8188 at the firewall, then publish `https:\u002F\u002Fcomfy.yourdomain.com`. For automation, use the `\u002Fprompt` API to submit JSON workflows from your scripts.",{"type":110,"body":111},"tip","To industrialize generation, leverage the API: submit your workflows via POST to `\u002Fprompt` and retrieve the results through the `\u002Fws` WebSocket that notifies the end of each task. Combine this with the `--lowvram` flag at launch if your VPS has an 8 GB GPU: ComfyUI intelligently offloads the models to system RAM to avoid CUDA memory errors on large models.","Set up your remote ComfyUI studio","Image generation demands a GPU and generous storage for the checkpoints. The ServOrbit Cloud VPS offers the resources and preconfigured Docker to deploy ComfyUI and expose it securely.","Deploy on a Cloud VPS","\u002Fvps-cloud",[117,129,143],{"id":16,"slug":118,"title":119,"excerpt":120,"readTime":121,"views":122,"isPinned":13,"publishedAt":14,"category":123,"categories":124,"featuredImage":23,"bgImage":24,"posterImage":126,"relatedSolution":127},"heberger-open-webui","How to Host Open WebUI on a VPS","A complete guide to deploying Open WebUI on your own VPS. Keep control of your data, avoid cloud API costs, and access your LLMs from a clean web interface.",6,3200,{"id":16,"name":17,"slug":18,"color":19,"icon":20},[125],{"id":16,"name":17,"slug":18,"color":19,"icon":20},"\u002Fblog\u002Fcovers\u002Fheberger-open-webui-poster.svg",{"categorySlug":20,"appSlug":128},"open-webui",{"id":130,"slug":131,"title":132,"excerpt":133,"readTime":134,"views":135,"isPinned":13,"publishedAt":136,"category":137,"categories":138,"featuredImage":23,"bgImage":24,"posterImage":140,"relatedSolution":141},2,"deployer-dify-vps","Deploying Dify on a VPS: AI Workflows Under Control","Install Dify on a ServOrbit VPS to build agents, chatflows and AI apps without losing control of your data.",7,2480,"2026-02-11T00:00:00+00:00",{"id":16,"name":17,"slug":18,"color":19,"icon":20},[139],{"id":16,"name":17,"slug":18,"color":19,"icon":20},"\u002Fblog\u002Fcovers\u002Fdeployer-dify-vps-poster.svg",{"categorySlug":20,"appSlug":142},"dify",{"id":121,"slug":144,"title":145,"excerpt":146,"readTime":147,"views":148,"isPinned":13,"publishedAt":149,"category":150,"categories":151,"featuredImage":23,"bgImage":24,"posterImage":153,"relatedSolution":154},"openclaw-vps","Deploying OpenClaw on a VPS","A guide to deploying OpenClaw on your own VPS. Keep control of your AI agents and your data within your own infrastructure.",5,422,"2026-06-11T00:00:00+00:00",{"id":16,"name":17,"slug":18,"color":19,"icon":20},[152],{"id":16,"name":17,"slug":18,"color":19,"icon":20},"\u002Fblog\u002Fcovers\u002Fopenclaw-vps-poster.svg",{"categorySlug":20,"appSlug":155},"openclaw",1785628435057]