ComfyUIa startup that helps creators control image, video and audio outputs from diffusion models with a node-based workflow has raised a $30 million funding round at a $500 million valuation.
The round was led by Craft Ventures, with participation from other investors including Pace Capital, Chemistry and TruArrow.
ComfyUI started as an open source project in 2023, shortly after diffusion models were introduced. At the time, models like Midjourney and OpenAI’s DALL-E were barely functional, often making big mistakes like adding extra fingers to hands.
To address these limitations, the project’s founders developed a modular framework that gives creators detailed control over every step of the production process.
Their tool gained so much traction among creative professionals that it eventually grew into an official startup. In late 2024, ComfyUI raised $19 million in Series A funding from investors including Chemistry Ventures, Cursor Capital and Guillermo Rauch, founder of Vercel.
Although the latest diffusion models have come a long way from adding a sixth digit to the hands, the need for the pinpoint accuracy that ComfyUI offers has grown.
“If you’re thinking about the typical prompt-based solution like Midjourney or ChatGPT, you’re asking for something, this [gets only] 60% – 80% there,” Yoland Yan, co-founder and CEO of ComfyUI, told TechCrunch. “But to change that remaining 20%, you have to try this slot.”
Yan (pictured left) compared the process to playing in a casino, because prompting the model to make a small change can lead to a completely different result, including replacing parts that were already perfect.
ComfyUI’s node-based interface allows creators to connect specific elements of the production process, giving them full control over the quality of their final output.
“You cannot easily transfer this message to the prompt box [of a foundational model]Jan said.
The creators seem to agree, as ComfyUI claims to have over 4 million users.
The tool is used by creative professionals for visual effects, animation, advertising and even industrial design.
The startup says its offering has become such an essential tool of the trade for technical artists and other creatives that it’s not uncommon to see “ComfyUI artist or engineer” is listed as a job title on studio job boards.
Although the basic video and image models continue to improve, Yan claims that they are not perfect and that a tool like ComfyUI will continue to be in high demand.
“In the world where artificial intelligence will be everywhere, Comfy’s version of the human-in-the-loop approach will win the most eyeballs in the end,” he said.
ComfyUI’s competitors include Weavy, a startup acquired by Figma last year.
When you purchase through links in our articles, we may earn a small commission. This does not affect our editorial independence.
