ComfyUI with a real card behind it
Node-based image/video gen: SDXL, Flux and workflows
- Video memory
- 12 GB
- Setup
- ~10 min
- Access
- port 8188
- Billing
- hourly, in BRL
ComfyUI is where new models land first: you build the pipeline out of nodes, save it and repeat. The bottleneck is never the program, it is the card — and here you rent the card for as long as you need it.
ComfyUI is the most powerful node-based editor for diffusion models: Stable Diffusion 1.5/SDXL, Flux and video workflows (image-to-video). Includes ComfyUI-Manager to install custom nodes and download models from the UI. Ideal for advanced, reproducible pipelines.
What it is for
- Repeatable pipelines to produce campaign art in series
- New image and video models as soon as they ship
- High-resolution refinement without exhausting your own machine
- Workflows and models stored on your own instance
How to deploy
- Create your account and add balance (card or Pix, no subscription).
- In the console, pick the ComfyUI template and a machine — the console hides the ones that do not meet the requirement.
- In about 10 minutes the setup finishes and the access address shows up in the panel, on port 8188.
Done? Just destroy the machine and billing stops with it. No contract, no minimum commitment.
FAQ
Which card for the newest models?
Current image models want 16 GB to be comfortable; for video, aim for 24 GB or more.
Can I install community nodes?
Yes, the node manager is available in the interface itself.
Can it generate video?
It can, with today's open video models. Budget more video memory and more time per clip.