# Inspiration Seeds: Learning Non-Literal Visual Combinations for Generative Exploration

arXiv: https://arxiv.org/abs/2602.08615 · HTML: https://mlsanity.com/paper/2602.08615/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 74 references that are in the map.
- First posted on arXiv 9 Feb 2026.

## Builds on (most cited first, 30 of 32)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [A Neural Algorithm of Artistic Style](https://mlsanity.com/paper/1508.06576/) (2015)
- [DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data](https://mlsanity.com/paper/2306.09344/) (2023)
- [Seedream 4.0: Toward Next-generation Multimodal Image Generation](https://mlsanity.com/paper/2509.20427/) (2025)
- [Break-A-Scene: Extracting Multiple Concepts from a Single Image](https://mlsanity.com/paper/2305.16311/) (2023)
- [ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs](https://mlsanity.com/paper/2311.13600/) (2023)
- [Cross-Image Attention for Zero-Shot Appearance Transfer](https://mlsanity.com/paper/2311.03335/) (2023)
- [Implicit Style-Content Separation using B-LoRA](https://mlsanity.com/paper/2403.14572/) (2024)
- [Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion](https://mlsanity.com/paper/2310.03502/) (2023)
- [Art and the science of generative AI: A deeper dive](https://mlsanity.com/paper/2306.04141/) (2023)
- [The Creativity of Text-to-Image Generation](https://mlsanity.com/paper/2206.02904/) (2022)
- [Concept Decomposition for Visual Exploration and Inspiration](https://mlsanity.com/paper/2305.18203/) (2023)
- [Interpreting CLIP with Hierarchical Sparse Autoencoders](https://mlsanity.com/paper/2502.20578/) (2025)
- [TokenVerse: Versatile Multi-concept Personalization in Token Modulation Space](https://mlsanity.com/paper/2501.12224/) (2025)
- [Creativity Inspired Zero-Shot Learning](https://mlsanity.com/paper/1904.01109/) (2019)
- [ConceptLab: Creative Concept Generation using VLM-Guided Diffusion Prior Constraints](https://mlsanity.com/paper/2308.02669/) (2023)
- [Can Computers Create Art?](https://mlsanity.com/paper/1801.04486/) (2018)
- [IP-Composer: Semantic Composition of Visual Concepts](https://mlsanity.com/paper/2502.13951/) (2025)
- [Generating an Image From 1,000 Words: Enhancing Text-to-Image With Structured Captions](https://mlsanity.com/paper/2511.06876/) (2025)
- [Simple Disentanglement of Style and Content in Visual Representations](https://mlsanity.com/paper/2302.09795/) (2023)
- [CusConcept: Customized Visual Concept Decomposition with Diffusion Models](https://mlsanity.com/paper/2410.00398/) (2024)

## Built on by (most cited first, 1 of 1)

- [Semantic Browsing: Controllable Diversity for Image Generation](https://mlsanity.com/paper/2606.23679/) (2026)

## Abstract (arXiv)

While generative models have become powerful tools for image synthesis, they are typically optimized for executing carefully crafted textual prompts, offering limited support for the open-ended visual exploration that often precedes idea formation. In contrast, designers frequently draw inspiration from loosely connected visual references, seeking emergent connections that spark new ideas. We propose Inspiration Seeds, a generative framework that shifts image generation from final execution to exploratory ideation. Given two input images, our model produces diverse, visually coherent compositions that reveal latent relationships between inputs, without relying on user-specified text prompts. Our approach is feed-forward, trained on synthetic triplets of decomposed visual aspects derived entirely through visual means: we use CLIP Sparse Autoencoders to extract editing directions in CLIP latent space and isolate concept pairs. By removing the reliance on language and enabling fast, intuitive recombination, our method supports visual ideation at the early and ambiguous stages of creative work.