CLIP-CLOP: CLIP-Guided Collage and Photomontage
Explore this paper's citation graph
Summary
A gradient-based generator to produce collages requires the human artist to curate libraries of image patches and to describe (with prompts) the whole image composition, with the option to manually adjust the patches' positions during generation, thereby allowing humans to reclaim some control of the process and achieve greater creative freedom.
- Type
- preprint
- Published
- 2022-05-06
- Cited by
- 19
- References
- 30
- Access
- Open access
- OpenAlex
- https://openalex.org/W4229447825
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:248562988
Keywords
Generator (circuit theory), Computer science, Ideal (ethics), Realism, Art
References
- Arcimboldo-like collage using internet images
- Empirically Studying Participatory Sense-Making in Abstract Drawing with a Co-Creative Cognitive Agent
- Creativity Versus the Perception of Creativity in Computational Systems
- Vismantic: Meaning-making with Images
- Automated Collage Generation - With Intent
- collabdraw: An Environment for Collaborative Sketching with an Artificial Agent
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- AI + Art = Human
- Novice-AI Music Co-Creation via AI-Steering Tools for Deep Generative Models
- Taming Transformers for High-Resolution Image Synthesis
- Design Guidelines for Prompt Engineering Text-to-Image Generative Models
- Hierarchical Text-Conditional Image Generation with CLIP Latents
- VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance
- High-Resolution Image Synthesis with Latent Diffusion Models
- CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders
- Modern Evolution Strategies for Creativity: Fitting Concrete Images and Abstract Concepts
- Human in the Loop for Machine Creativity
- FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space Optimization
- Learning Transferable Visual Models From Natural Language Supervision
- Generative Art Using Neural Visual Grammars and Dual Encoders
Cited by
- Stroke-based Rendering: From Heuristics to Deep Learning
- Controlled and Conditional Text to Image Generation with Diffusion Prior
- DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models
- VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models
- Neural Collage Transfer: Artistic Reconstruction via Material Manipulation
- VectorPainter: A Novel Approach to Stylized Vector Graphics Synthesis with Vectorized Strokes
- Do Generalised Classifiers really work on Human Drawn Sketches?
- SVGDreamer: Text Guided SVG Generation with Diffusion Model
- Empowering LLMs to Understand and Generate Complex Vector Graphics
- NeuralSVG: An Implicit Representation for Text-to-Vector Generation
- SVGDreamer++: Advancing Editability and Diversity in Text-Guided SVG Generation
- CLIPDraw++: Text-to-Sketch Synthesis with Simple Primitives
- MROSS: Multi-Round Region-based Optimization for Scene Sketching
- TS-CLIP: Time Series Understanding by CLIP
- CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders
- Copyright and AI-Generated Works
- Stylesteinsvg: Example-Guided Text-to-Svg Diffusion Models Via Vectorized Stein Score Distillation
- Diversity and Representation in ICCC: A review of Computational Creativity publication content and authorship trends 2017-2022
- Should we have seen the coming storm? Transformers, society, and CC
Related papers
- Photographic Text-to-Image Synthesis with a Hierarchically-Nested Adversarial Network
- Object Discovery with a Copy-Pasting GAN
- SimilarityGAN: Using Similarity to Loosen Structural Constraints in Generative Adversarial Models
- Unsupervised multi-domain image translation with domain representation learning
- GAN-based models and applications
- Adversarial Image Caption Generator Network
- GANs with Multiple Constraints for Image Translation
- B2GAN: Bidirectional-branch generative adversarial network for text image super-resolution with structure preservation
- Augmentation of Images through DCGANs