InvokeAI
Open-source app for AI image generation with a canvas and node workflows
A layered canvas for drawing, inpainting and outpainting, next to node workflows.
ComfyUI
Open-source node-based app for AI images, video, audio and 3D
Open-source node-based app for AI images, video, audio and 3D
ComfyUI is an open-source app for making images, video, audio and 3D with AI models. You build a workflow by connecting nodes on a canvas: models, inputs, processing steps and outputs. You can start from a template: the workflow library on comfy.org lists 661 templates. App Mode shows a workflow as a simple interface.
It runs on your own computer or in the cloud. Comfy Desktop is for Windows 10 or later, macOS 13 or later on Apple Silicon, and Linux. There is also a portable build for Windows and a command-line install (comfy-cli). Run locally, it works offline. Comfy Cloud runs ComfyUI in the browser on cloud GPUs.
ComfyUI is free under the GPL-3.0 licence. Comfy Cloud gives new users 5 free runs. Its monthly plans are Standard $20, Creator $35, Pro $100 and Team $700 (up to 20% less when paid yearly). Credits are used only while a workflow runs.
The maker states that more than 5,000 community extensions add over 60,000 nodes.
Visual professionals, creators, teams and studios who want control over every model and step, for example in VFX and animation, advertising, gaming, and e-commerce and fashion.
Makes video, audio and 3D as well as images, and has new releases in 2026; the last AUTOMATIC1111 release was 1.10.1 in February 2025.
Makes video, audio and 3D as well as images. A desktop app for Windows, macOS and Linux, and Comfy Cloud for computers without a GPU.
Makes video, audio and 3D as well as images, with 661 ready-made templates. Comfy Cloud runs it in the browser; InvokeAI's hosted platform has shut down.
Free and open source, and runs on your own graphics card or offline; Midjourney is a paid cloud subscription from $10 a month.
Free and open source, and runs on your own graphics card; cloud models are optional, paid per run. Higgsfield's paid plans start at $19 a month.
Open-source app for AI image generation with a canvas and node workflows
A layered canvas for drawing, inpainting and outpainting, next to node workflows.
AI service that makes images and short videos from text prompts
Runs in the browser with nothing to install and no graphics card needed; one prompt gives four images.
Browser interface to run Stable Diffusion image models on your own computer
One page of settings (txt2img, img2img, inpaint) instead of a node graph.
Local web interface for AI image generation, built on Stable Diffusion WebUI
One page of settings instead of a node graph, with ControlNet and IP-Adapters built in.
Local web interface for AI image, video and audio generation, built on ComfyUI
Puts a simple Generate tab of settings on top of the ComfyUI backend, with the full node graph one tab away, and splits work across several GPUs or machines.
Perbincangan
Log masuk untuk menyertai perbincangan