ColorwAI: Generative Colorways of Textiles through GAN and Diffusion Disentanglement
Not on the map. Why?
Abstract (arXiv)
Colorway creation is the task of generating textile samples in alternate color variations maintaining an underlying pattern. The individuation of a suitable color palette for a colorway is a complex creative task, responding to client and market needs, stylistic and cultural specifications, and mood. We introduce a modification of this task, the "generative colorway" creation, that includes minimal shape modifications, and propose a framework, "ColorwAI", to tackle this task using color disentanglement on StyleGAN and Diffusion. We introduce a variation of the InterfaceGAN method for supervised disentanglement, ShapleyVec. We use Shapley values to subselect a few dimensions of the detected latent direction. Moreover, we introduce a general framework to adopt common disentanglement methods on any architecture with a semantic latent space and test it on Diffusion and GANs. We interpret the color representations within the models' latent space. We find StyleGAN's W space to be the most aligned with human notions of color. Finally, we suggest that disentanglement can solicit a creative system for colorway creation, and evaluate it through expert questionnaires and creativity theory.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 29 of its 52 references that are in the map. First posted on arXiv 16 Jul 2024.
Builds on
29 of 52 references.
References · 29
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
- 2020Denoising Diffusion Implicit Modelscited by 9,781
- 2023Segment Anythingcited by 8,234
- 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
- 2022Generative Adversarial Networkscited by 5,627
- 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
- 2021Alias-Free Generative Adversarial Networkscited by 1,184
17 more
- 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 991
- 2021DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulationcited by 642
- 2020GANSpace: Discovering Interpretable GAN Controlscited by 614
- 2020InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANscited by 394
- 2020StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generationcited by 332
- 2022Diffusion Models already have a Semantic Latent Spacecited by 328
- 2018Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoderscited by 264
- 2020Weakly-Supervised Disentanglement Without Compromisescited by 239
- 2019ManiGAN: Text-Guided Image Manipulationcited by 156
- 2023StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Modelscited by 155
- 2022Uncovering the Disentanglement Capability in Text-to-Image Diffusion Modelscited by 116
- 2019Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesiscited by 106
- 2013Deep Learning of Representations: Looking Forwardcited by 84
- 2021Do Not Escape From the Manifold: Discovering the Local Coordinates on the Latent Space of GANscited by 26
- 2023Boundary Guided Learning-Free Semantic Control with Diffusion Modelscited by 23
- 2022Texture Representation via Analysis and Synthesis with Generative Adversarial Networkscited by 3
- 2023Textile Pattern Generation Using Diffusion Modelscited by 1
Built on by
Citing papers per year: 2024: 1.
1 paper.
- 2024Reflections on Disentanglement and the Latent Spacecited by 2
- 2024Reflections on Disentanglement and the Latent Space8 Oct 2024