Prompting for Discovery: Flexible Sense-Making for AI Art-Making with Dreamsheets
SG Almeda, JD Zamfirescu-Pereira, KW Kim… - Proceedings of the CHI …, 2024 - dl.acm.org
Design space exploration (DSE) for Text-to-Image (TTI) models entails navigating a vast,
opaque space of possible image outputs, through a commensurately vast input space of …
opaque space of possible image outputs, through a commensurately vast input space of …
CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets
In the realm of digital creativity, our potential to craft intricate 3D worlds from imagination is
often hampered by the limitations of existing digital tools, which demand extensive expertise …
often hampered by the limitations of existing digital tools, which demand extensive expertise …
Investigating the Effectiveness of Cross-Attention to Unlock Zero-Shot Editing of Text-to-Video Diffusion Models
S Motamed, W Van Gansbeke… - Proceedings of the …, 2024 - openaccess.thecvf.com
With recent advances in image and video diffusion models for content creation a plethora of
techniques have been proposed for customizing their generated content. In particular …
techniques have been proposed for customizing their generated content. In particular …
Generative artificial intelligence and building design: early photorealistic render visualization of façades using local identity-trained models
H Jo, JK Lee, YC Lee, S Choo - Journal of Computational …, 2024 - academic.oup.com
This paper elucidates an approach that utilizes generative artificial intelligence (AI) to
develop alternative architectural design options based on local identity. The advancement of …
develop alternative architectural design options based on local identity. The advancement of …
Animatediff-lightning: Cross-model diffusion distillation
We present AnimateDiff-Lightning for lightning-fast video generation. Our model uses
progressive adversarial diffusion distillation to achieve new state-of-the-art in few-step video …
progressive adversarial diffusion distillation to achieve new state-of-the-art in few-step video …
DesignPrompt: Using Multimodal Interaction for Design Exploration with Generative AI
Visually oriented designers often struggle to create effective generative AI (GenAI) prompts.
A preliminary study identified specific issues in composing and fine-tuning prompts, as well …
A preliminary study identified specific issues in composing and fine-tuning prompts, as well …
Enhancing Baidu Multimodal Advertisement with Chinese Text-to-Image Generation via Bilingual Alignment and Caption Synthesis
Recent advances in generative artificial intelligence have revolutionized information
retrieval and content generation, opening up new opportunities for the e-commerce industry …
retrieval and content generation, opening up new opportunities for the e-commerce industry …
Bridging the Intent Gap: Knowledge-Enhanced Visual Generation
For visual content generation, discrepancies between user intentions and the generated
content have been a longstanding problem. This discrepancy arises from two main factors …
content have been a longstanding problem. This discrepancy arises from two main factors …
Hi5: 2D Hand Pose Estimation with Zero Human Annotation
We propose a new large synthetic hand pose estimation dataset, Hi5, and a novel
inexpensive method for collecting high-quality synthetic data that requires no human …
inexpensive method for collecting high-quality synthetic data that requires no human …
InVi: Object Insertion In Videos Using Off-the-Shelf Diffusion Models
N Saini, N Bodla, A Shrivastava… - arXiv preprint arXiv …, 2024 - arxiv.org
We introduce InVi, an approach for inserting or replacing objects within videos (referred to
as inpainting) using off-the-shelf, text-to-image latent diffusion models. InVi targets controlled …
as inpainting) using off-the-shelf, text-to-image latent diffusion models. InVi targets controlled …