Two ComfyUI nodes that generate and edit images through Veida AI, the unlimited free AI image generator: no API key needed to start, and no GPU, no checkpoints, no VRAM.

Node	In	Out
Veida Generate Image	prompt, aspect ratio	`IMAGE`, url
Veida Edit Image	`IMAGE` + one-sentence instruction	`IMAGE`, url

Drop them anywhere in a workflow: generate a base image and pipe it into an upscaler, or take any IMAGE from your graph and edit it in plain language: "put the product on white marble, keep the label unchanged".

Install

ComfyUI-Manager: search for Veida and install.

Manually:

cd ComfyUI/custom_nodes
git clone https://github.com/hanshs474/ComfyUI-Veida

Restart ComfyUI. No extra Python packages: the nodes use the standard library plus the torch, numpy and Pillow that ComfyUI already ships.

Free tier, then your account

Leave api_key empty and both nodes run on Veida AI Image v1 with no account: each run is one free image or one free edit, about seven a day per machine, 1K with a small mark. Enough to wire up a workflow and see it work.

Paste a key from veida.ai/settings/apikeys (or set VEIDA_API_KEY before starting ComfyUI) and every run goes through your account instead, with any image model your plan includes via the model field: GPT Image 2.5, GPT Image 2 for pictures that carry readable text, Nano Banana 2, Seedream 5.0 Lite. On Pro and Max every model is unlimited; pricing lists the plans.

Edits that hold

Say what must not change as clearly as what should: "turn the jacket red, keep the same face, pose and lighting". The ChatGPT image editor on the site has preset prompts that make good templates. Your input image is uploaded to Veida's CDN so the model can read it.

Notes

Both nodes also output the permanent CDN url, handy for logging or passing to a web hook.
Change seed to force a fresh run on an unchanged prompt (ComfyUI caches identical inputs).

Want the same thing from code? SDKs for Python, Go, Rust, TypeScript, PHP, Ruby, Dart and .NET.

MIT