Communication in Human–AI Co-Creation: Perceptual Analysis of Paintings Generated by Text-to-Image System

Lyu, Yanru; Wang, Xinxin; Lin, Rungtai; Wu, Jun

doi:10.3390/app122211312

Cited by 44 publications

(45 citation statements)

References 35 publications

(57 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study visually compares our diffusion model with other popular diffusion models (i.e., Disco Diffusion [43], Midjourney [21], DALL E2 [13], and Stable Diffusion [22]). Herein, we discuss the most mainstream and influential models.…”

Section: Visual Assessmentmentioning

confidence: 99%

See 1 more Smart Citation

Generating Interior Design from Text: A New Diffusion Model-Based Method for Efficient Creative Design

2023

View full text Add to dashboard Cite

Because interior design is subject to inefficiency, more creativity is imperative. Due to the development of artificial intelligence diffusion models, the utilization of text descriptions for the generation of creative designs has become a novel method for solving the aforementioned problem. Herein, we build a unique interior decoration style dataset. Thus, we solve the problem pertaining to the need for datasets, propose a new loss function that considers the decoration style, and retrain the diffusion model using this dataset. The trained model learns interior design knowledge and can generate an interior design through text. The proposed method replaces the designer’s drawing with computer-generated creative design, thereby enhancing the design efficiency and creative generation. Specifically, the proposed diffusion model can generate interior design images of specific decoration styles and spatial functions end to end from text descriptions, and the generated designs are easy to modify. This novel and creative design method can efficiently generate various interior designs, promote the generation of creative designs, and enhance the design and decision-making efficiency.

show abstract

Section: Visual Assessmentmentioning

confidence: 99%

“…Figure 7 shows that Disco Diffusion [43] could not generate the interior design. The model needed help understanding the spatial-positional relationship of each component element in interior design, and the combined effect of each component element was inferior.…”

Section: Visual Assessmentmentioning

confidence: 99%

Generating Interior Design from Text: A New Diffusion Model-Based Method for Efficient Creative Design

2023

View full text Add to dashboard Cite

show abstract

“…The model has recently gained widespread public interest due to its ability to create photorealistic images solely from short written inputs [3][4][5]. Trained on billions of text-image pairs extracted from the internet, DALL-E 2 learned a wide range of representations that it can recombine to create novel images, thereby exceeding the variability it has seen in the training data, even when given implausible prompts (eg, "a painting of a pelvic X-ray by Claude Monet") [2,[6][7][8].…”

Section: The Potential Impact Of Generative Models In Radiologymentioning

confidence: 99%

What Does DALL-E 2 Know About Radiology?

Adams¹,

Busch²,

Truhn³

et al. 2023

J Med Internet Res

View full text Add to dashboard Cite

Generative models, such as DALL-E 2 (OpenAI), could represent promising future tools for image generation, augmentation, and manipulation for artificial intelligence research in radiology, provided that these models have sufficient medical domain knowledge. Herein, we show that DALL-E 2 has learned relevant representations of x-ray images, with promising capabilities in terms of zero-shot text-to-image generation of new images, the continuation of an image beyond its original boundaries, and the removal of elements; however, its capabilities for the generation of images with pathological abnormalities (eg, tumors, fractures, and inflammation) or computed tomography, magnetic resonance imaging, or ultrasound images are still limited. The use of generative models for augmenting and generating radiological data thus seems feasible, even if the further fine-tuning and adaptation of these models to their respective domains are required first.

show abstract

“…Previous scholars have explored the relationship between AI and painting, such as creativity in AI painting [38], reflections on AI painting techniques [13], attitudes of art and non-art majors towards AI painting [17], comparing human and AI painting [39], and applying AI painting techniques to cultural and creative products [40]. The Art of AI Painting incorporates a wide range of techniques and styles, using machine learning to improve the user's painting ability.…”

Section: Overview Of Artificial Intelligence In Paintingmentioning

confidence: 99%

“…The Art of AI Painting incorporates a wide range of techniques and styles, using machine learning to improve the user's painting ability. Whether or not they have or specialize in painting skills, with the help of AIBPS, art majors and non-art majors users can easily be able to create impressive works [17]. The intervention of AI in the creation of painting art not only brings more possibilities, but also overturns the paradigm of art creation and changes the way we think about viewing and evaluating artworks [39].…”

Section: Overview Of Artificial Intelligence In Paintingmentioning

confidence: 99%

Everyone's an Artist? Exploring User Acceptance of AI-Based Painting Systems

Xu¹,

Zhang²,

Li³

et al. 2023

Preprint

View full text Add to dashboard Cite

Artificial intelligence (AI) applications in different fields are developing rapidly, among which AI painting technology, as an emerging technology, has received wide attention from users for its creativity and efficiency. This study aimed to investigate the factors that influence user acceptance of the use of AIBPS by proposing an extended model that combines the Extended Technology Acceptance Model (ETAM) with the AI-based Painting System (AIBPS).A questionnaire was administered to 528 Chinese participants, using validated factor analysis data and Structural Equation Modeling (SEM) was used to test the hypotheses. The findings showed that hedonic motivation (HM) and perceived trust (PE) had a positive effect (+) on users' perceived usefulness (PU) and perceived ease of use (PEOU), while previous experience (PE) and technical features (TF) had no effect (-) on users' perceived usefulness (PU). This study provides an important contribution to the literature on AIBPS and the evaluation of systems of the same type, which helps to promote the sustainable development of AI in different domains and provides a possible space for further extension of TAM, thus helping to improve the user experience of AIBPS. The results of the study provide insights for system developers and enterprises to better motivate users to use AIBPS.

show abstract

Communication in Human–AI Co-Creation: Perceptual Analysis of Paintings Generated by Text-to-Image System

Cited by 44 publications

References 35 publications

Generating Interior Design from Text: A New Diffusion Model-Based Method for Efficient Creative Design

Generating Interior Design from Text: A New Diffusion Model-Based Method for Efficient Creative Design

What Does DALL-E 2 Know About Radiology?

Everyone's an Artist? Exploring User Acceptance of AI-Based Painting Systems

Contact Info

Product

Resources

About