ComfyUI, a 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.
ComfyUI, a startup focused on enhancing the creative process through advanced AI tools, has secured $30 million in a funding round led by Craft Ventures, bringing its valuation to $500 million. Other participating investors include Pace Capital, Chemistry, and TruArrow. Founded in 2023 as an open-source project, ComfyUI emerged in response to the early limitations of diffusion models, which struggled with accuracy in generating images and videos.
At its inception, models like Midjourney and OpenAI’s DALL-E were notorious for producing errors, such as adding extra fingers to hands. To combat these issues, ComfyUI’s founders created a modular framework that provides creators with granular control over every aspect of the image generation process. This innovative approach quickly gained traction within creative communities, prompting the evolution of the project into a formal startup.
In late 2024, ComfyUI successfully raised $19 million in Series A financing from notable investors including Chemistry Ventures, Cursor Capital, and Guillermo Rauch, founder of Vercel. Despite the advancements in diffusion models, the demand for precision offered by ComfyUI has only intensified. “If you think about your typical prompt-based solution, like Midjourney or ChatGPT, you ask for something, it [gets only] 60% – 80% there,” said Yoland Yan, ComfyUI’s co-founder and CEO. “But to change that remaining 20%, you have to try this slot machine.”
Yan likened modifying prompts in these models to gambling, emphasizing that a small adjustment could lead to unexpected results, often overwriting previously satisfactory outputs. ComfyUI’s node-based interface allows users to connect specific components of the generation process, enabling them to maintain control over the quality of their final creations. “You cannot easily convey that message in the prompt box [of a foundational model],” Yan noted.
With over 4 million users, ComfyUI has become an essential tool for creative professionals across various industries, including visual effects, animation, advertising, and industrial design. The increasing reliance on this platform is reflected in job postings, where titles such as “ComfyUI artist” or “ComfyUI engineer” are becoming common. As foundational models improve, Yan asserts that the imperfections remain, ensuring ongoing demand for ComfyUI’s capabilities.
“In the world where AI slop is going to be everywhere, the Comfy version of human-in-the-loop approach is going to win out most of the eyeballs in the end,” he stated. ComfyUI faces competition from various companies, including Weavy, which was acquired by Figma last year. However, the startup’s unique offering positions it well in a rapidly evolving market, where the intersection of AI and creativity continues to capture attention and investment.
See also
Sam Altman Praises ChatGPT for Improved Em Dash Handling
AI Country Song Fails to Top Billboard Chart Amid Viral Buzz
GPT-5.1 and Claude 4.5 Sonnet Personality Showdown: A Comprehensive Test
Rethink Your Presentations with OnlyOffice: A Free PowerPoint Alternative
OpenAI Enhances ChatGPT with Em-Dash Personalization Feature
