Z-Magic: Zero-shot Multiple Attributes Guided Image Creator
The customization of multiple attributes has gained increasing popularity with the rising demand for personalized content creation. Despite promising empirical results, the contextual coherence between different attributes has been largely overlooked. In this paper, we argue that subsequent attributes should follow the multivariable conditional distribution introduced by former attributes creation. In light of this, we reformulate multi-attribute creation from a conditional probability theory perspective and tackle the challenging zero-shot setting. By explicitly modeling the dependencies between attributes, we further enhance the coherence of generated images across diverse attribute combinations. Furthermore, we identify connections between multi-attribute customization and multi-task learning, effectively addressing the high computing cost encountered in multi-attribute synthesis. Extensive experiments demonstrate that Z-Magic outperforms existing models in zero-shot image generation, with broad implications for AI-driven design and creative applications.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeImage GenerationMulti-Task LearningSimilar Papers 제목 키워드 기반
MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing
Text-guided image editing is widely needed in daily life, ranging from personal use to professional applications such as Photoshop. However, existing methods are either zero-shot or trained on an automatically synthesize…
Image Editingtext-guided-image-editingLanguage Models Can See: Plugging Visual Controls in Text Generation
Generative language models (LMs) such as GPT-2/3 can be prompted to generate text with remarkable quality. While they are designed for text-prompted generation, it remains an open question how the generation process coul…
Image CaptioningImage-text matchingOpen-Ended Question AnsweringStory Generation+2Multi-Aspect Controllable Text Generation with Disentangled Counterfactual Augmentation
Multi-aspect controllable text generation aims to control the generated texts in attributes from multiple aspects (e.g., "positive" from sentiment and "sport" from topic). For ease of obtaining training samples, existing…
AttributecounterfactualDisentanglementText GenerationMAGIC: Few-Shot Mask-Guided Anomaly Inpainting with Prompt Perturbation, Spatially Adaptive Guidance, and Context Awareness
Few-shot anomaly generation is a key challenge in industrial quality control. Although diffusion models are promising, existing methods struggle: global prompt-guided approaches corrupt normal regions, and existing inpai…
Super-class guided Transformer for Zero-Shot Attribute Classification
Attribute classification is crucial for identifying specific characteristics within image regions. Vision-Language Models (VLMs) have been effective in zero-shot tasks by leveraging their general knowledge from large-sca…
AttributeClassificationGeneral KnowledgeMulti-Label Classification+2