# Chimera: Compositional Image Generation using Part-based Concepting

arXiv: https://arxiv.org/abs/2510.18083 · HTML: https://mlsanity.com/paper/2510.18083/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 32 references that are in the map.
- First posted on arXiv 20 Oct 2025.

## Builds on (most cited first, 27 of 27)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2301.13826/) (2023)
- [Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks](https://mlsanity.com/paper/2311.06242/) (2023)
- [OmniGen2: Towards Instruction-Aligned Multimodal Generation](https://mlsanity.com/paper/2506.18871/) (2025)
- [Break-A-Scene: Extracting Multiple Concepts from a Single Image](https://mlsanity.com/paper/2305.16311/) (2023)
- [Less-to-More Generalization: Unlocking More Controllability by In-Context Generation](https://mlsanity.com/paper/2504.02160/) (2025)
- [PACO: Parts and Attributes of Common Objects](https://mlsanity.com/paper/2301.01795/) (2023)
- [Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection](https://mlsanity.com/paper/2405.10300/) (2024)
- [PartImageNet: A Large, High-Quality Dataset of Parts](https://mlsanity.com/paper/2112.00933/) (2021)
- [Concept Decomposition for Visual Exploration and Inspiration](https://mlsanity.com/paper/2305.18203/) (2023)
- [ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty](https://mlsanity.com/paper/2408.14339/) (2024)
- [λ-ECLIPSE: Multi-Concept Personalized Text-to-Image Diffusion Models by Leveraging CLIP Latent Space](https://mlsanity.com/paper/2402.05195/) (2024)
- [ConceptLab: Creative Concept Generation using VLM-Guided Diffusion Prior Constraints](https://mlsanity.com/paper/2308.02669/) (2023)
- [ConceptExpress: Harnessing Diffusion Models for Single-image Unsupervised Concept Extraction](https://mlsanity.com/paper/2407.07077/) (2024)
- [PartCraft: Crafting Creative Objects by Parts](https://mlsanity.com/paper/2407.04604/) (2024)
- [DreamCreature: Crafting Photorealistic Virtual Creatures from Imagination](https://mlsanity.com/paper/2311.15477/) (2023)
- [pOps: Photo-Inspired Diffusion Operators](https://mlsanity.com/paper/2406.01300/) (2024)
- [How to Blend Concepts in Diffusion Models](https://mlsanity.com/paper/2407.14280/) (2024)
- [Piece it Together: Part-Based Concepting with IP-Priors](https://mlsanity.com/paper/2503.10365/) (2025)
- [Generative Photomontage](https://mlsanity.com/paper/2408.07116/) (2024)
- [PartComposer: Learning and Composing Part-Level Concepts from Single-Image Examples](https://mlsanity.com/paper/2506.03004/) (2025)

## Built on by (most cited first, 2 of 2)

- [Muses: Designing, Composing, Generating Nonexistent Fantasy 3D Creatures without Training](https://mlsanity.com/paper/2601.03256/) (2026)
- [Concrete Jungle: Towards Concreteness Paved Contrastive Negative Mining for Compositional Understanding](https://mlsanity.com/paper/2604.13313/) (2026)

## Abstract (arXiv)

Personalized image generative models are highly proficient at synthesizing images from text or a single image, yet they lack explicit control for composing objects from specific parts of multiple source images without user specified masks or annotations. To address this, we introduce Chimera, a personalized image generation model that generates novel objects by combining specified parts from different source images according to textual instructions. To train our model, we first construct a dataset from a taxonomy built on 464 unique (part, subject) pairs, which we term semantic atoms. From this, we generate 37k prompts and synthesize the corresponding images with a high-fidelity text-to-image model. We train a custom diffusion prior model with part-conditional guidance, which steers the image-conditioning features to enforce both semantic identity and spatial layout. We also introduce an objective metric PartEval to assess the fidelity and compositional accuracy of generation pipelines. Human evaluations and our proposed metric show that Chimera outperforms other baselines by 14% in part alignment and compositional accuracy and 21% in visual quality.