1038lab/comfyui-agnes-ai — explained in plain English
Analysis updated 2026-05-18
Generate images from text or combine up to four reference images into one composition, using cloud compute instead of a local GPU.
Create text-to-video, image-to-video, or first-and-last-frame interpolation videos inside a ComfyUI workflow.
Enhance, translate, or extract the art style from a prompt or reference image using built-in text styles.
Rotate between multiple Agnes AI API keys to spread usage across accounts.
| 1038lab/comfyui-agnes-ai | andyuneducated/resolve-ai | barathgb007/upstox-python-data | |
|---|---|---|---|
| Stars | 18 | 18 | 18 |
| Language | Python | Python | Python |
| Setup difficulty | easy | hard | moderate |
| Complexity | 2/5 | 4/5 | 3/5 |
| Audience | developer | developer | developer |
Figures from each repo's GitHub metadata at analysis time.
Requires a free Agnes AI API key from platform.agnes-ai.com.
ComfyUI-Agnes-AI adds a set of custom nodes to ComfyUI, the visual node editor many people use to build AI image and video pipelines, so you can call the Agnes AI cloud service directly from a workflow. Agnes AI is a free, cloud hosted platform, so all the actual image and video generation happens on Agnes's own servers rather than on your computer, meaning you do not need a local graphics card to use these nodes. The image node can generate a picture from a text description, or combine up to four reference images into one new composed image, automatically switching between the two modes depending on whether you have connected any images. Output resolutions of 1K, 2K, and 4K are supported. The video node covers three ways of making video: turning text into a short clip, animating a single starting image, or interpolating between a first and a last frame to create the motion in between. Videos can run from two to fifteen seconds at 480p, 720p, or 1080p, with an adjustable frame rate, and the final frame of a generated video is also available on its own as a still image. There is also a text processing node with four built in styles: expanding a short prompt into a fuller one, translating a prompt into English while keeping its visual details, pulling out the art style from a reference image, and writing a detailed description of an image so it can be reused as a prompt elsewhere. Each style can be swapped out for your own custom system prompt if you want different behavior. A separate configuration node stores your Agnes AI API key, which you get for free from the Agnes AI website, and lets you set default models and edit the prompt styles as JSON. You can save more than one key separated by commas and the nodes will rotate between them. Everything persists across ComfyUI restarts, and the stored key is partially hidden when displayed. Installation has no extra Python dependencies: you can install it through ComfyUI Manager, a git clone, or by downloading a release archive. The project is released under the GPL-3.0 license.
ComfyUI nodes that call the free, cloud-based Agnes AI API to generate images and videos, enhance prompts, and analyze images without a local GPU.
Mainly Python. The stack also includes Python, ComfyUI, Agnes AI API.
GPL-3.0 license: you can use and modify it, but any distributed derivative work must also be open source under the same license.
Setup difficulty is rated easy, with roughly 5min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
double-check against the repo, no cap.