Thread is paint, the needle a brush, and AI the canvas | Kiyomi Osawa
Overview This pilot project focuses on the digitization and AI generation of Kiyomi Osawa’s embroidery artwork. By leveraging generative AI models trained on artisanal style and tools built with artisan-centric UI, we aim to create digital canvases for artisans. The goal is to integrate AI into artisans’ existing practices so they can harness its power without needing technical expertise.
People
Kiyomi Osawa – Master Embroidery Artist (Ministry of Health, Labor and Welfare Outstanding Craftsman Award, Yellow Ribbon Medal)
Awu Chen – AI & Digital Media Researcher (CEO, Founder of SOOOUL Inc.)
Collaborators – Artisans and Technologists (Individual Contributors)
Historical Innovation of Yokoburi Embroidery
Yokoburi (horizontal swing embroidery) emerged as a crucial innovation in Kiryu's embroidery industry. During the “Japanese Economic Miracle” in 1960s, demand for kimono grew and craftsmen struggled to keep up with orders through hand embroidery. To address this challenge, artisans began modifying sewing machines to perform embroidery, leading to the invention of the yokoburi embroidery machine.
At its peak, Kiryu had over 10,000 craftsmen engaged in yokoburi embroidery. However, as this mechanized technique advanced, a challenge arose: craftsmen operating the embroidery machines were no longer recognized as craftsmen but were instead treated as mere technicians. Their intricate work, once highly valued as a craft, was increasingly categorized as an industrial product.
Kiyomi Osawa
Trained as a painter, Kiyomi Osawa discovered a passion for Yokoburi embroidery at the age of 17 and swiftly rose to prominence thanks to her technical knowhow and artistry. However, she soon realized the stark inequalities in the industry—while company presidents gained wealth and recognition, the craftsmen behind the intricate embroidery were treated as mere technicians, underpaid and unacknowledged.
Determined to change this, Kiyomi challenged the status quo by making art and advocating for yokoburi craftsmen as artisans. Her collaboration with fashion designers such as Kansai Yamamoto and Yoshiyuki Konishi elevated the status of yokoburi embroidery. At age 70, she founded her company, Osawa Shokai, to ensure fair value is distribution to the artisans.
Kiyomi Osawa’s life’s work revolves around innovation and she is never afraid of adopting new technology. She is proud that the person who invented the yokoburi embroidery machine came from Kiryu.
Digitization of Embroidery Artworks
The first step in the project involved digitizing and processing of Kiyomi Osawa’s embroidery artworks. The digitization process was crucial in capturing the intricate details of her needle painting technique, which blends color and texture seamlessly.
LoRA Model Training with Kohya_ss
To accurately replicate Kiyomi Osawa’s embroidery style in AI-generated images, we trained a Low-Rank Adaptation (LoRA) model using the Kohya_ss fine-tuning framework. This involved:
Compiling a high-quality dataset from digitized embroidery samples.
Training a LoRA model based on these samples, ensuring output fidelity to Osawa’s unique style.
Evaluating and refining the model through iterative testing and validation.
Stable Diffusion XL Integration via ComfyUI
The trained LoRA model was integrated with Stable Diffusion XL, using VAE Fix to maintain color accuracy and fine detail. This allowed us to generate high-resolution artworks that faithfully adhered to the original embroidery aesthetics.
Artisan-Centric UI
A custom UI wrapper was developed on top of ComfyUI making generative AI accessible to artisans without technical expertise. The key features of the UI include:
Prompt-Based Input System – Simplified controls where artisans describe their desired output using natural language.
Craftsmanship-Informed Controls – Custom parameters derived from artistic process, such as thread density, stroke direction, and color blending.
Open-Source Framework - Our technology is built on top of two important open-source frameworks ComfyUI, Kohya_SS and Flow.
Digitizing Tacit Knowledge
Beyond training the gen-AI model, we are also working on preserving Kiyomi’s tacit knowledge, including:
Needle Threading – Documenting and digitizing her method of threading the embroidery machine, originally adapted from a modified sewing machine in Kiryu.
Control Translation – Translating machine adjustments and artistic decisions into digital UI elements, providing artisans with familiar tools in a new medium.
Future Directions
Expanding the Model – Incorporating additional embroidery styles and historical techniques.
Refining Artisan Feedback Loops – Allowing direct iterative refinement through interaction with the AI system.
Integration into Broader Creative Platforms – Exploring applications in textiles, digital art, and interactive installations.
Through this pilot, we aim to establish a new paradigm where traditional craftsmanship and AI coalesce, enabling artisans to extend their artistic expression while preserving cultural heritage in the digital age.
Access our growing collection of artworks, crafts, and exclusive products. Be invited to upcoming exhibitions, events, and artist collaborations (20% of your subscription goes directly into funding future artists' exhibitions)
We are grateful to have the mentorship and support from Koichi Saito and the Kiryu government officials. Thank you to the team behind ComfyUI, Kohya_SS and FlowUI for developing open-source tools and AI frameworks.
We would like to extend our heartfelt gratitude to Kiyomi Osawa and to the artisans of Osawa Shokai.
For more information, visit Osawa Shokai's website.
