# Loom: Diffusion-Transformer for Interleaved Generation

arXiv: https://arxiv.org/abs/2512.18254 · HTML: https://mlsanity.com/paper/2512.18254/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 51 references that are in the map.
- First posted on arXiv 20 Dec 2025.

## Builds on (most cited first, 30 of 39)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Emerging Properties in Unified Multimodal Pretraining](https://mlsanity.com/paper/2505.14683/) (2025)
- [Emu3: Next-Token Prediction is All You Need](https://mlsanity.com/paper/2409.18869/) (2024)
- [Show-o: One Single Transformer to Unify Multimodal Understanding and Generation](https://mlsanity.com/paper/2408.12528/) (2024)
- [MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing](https://mlsanity.com/paper/2306.10012/) (2023)
- [TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers](https://mlsanity.com/paper/2203.11496/) (2022)
- [OmniGen: Unified Image Generation](https://mlsanity.com/paper/2409.11340/) (2024)
- [BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset](https://mlsanity.com/paper/2505.09568/) (2025)
- [Rectified Flow: A Marginal Preserving Approach to Optimal Transport](https://mlsanity.com/paper/2209.14577/) (2022)
- [Style Aligned Image Generation via Shared Attention](https://mlsanity.com/paper/2312.02133/) (2023)
- [Less-to-More Generalization: Unlocking More Controllability by In-Context Generation](https://mlsanity.com/paper/2504.02160/) (2025)
- [SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation](https://mlsanity.com/paper/2312.16272/) (2023)
- [EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer](https://mlsanity.com/paper/2503.07027/) (2025)
- [ANOLE: An Open, Autoregressive, Native Large Multimodal Models for Interleaved Image-Text Generation](https://mlsanity.com/paper/2407.06135/) (2024)
- [Improving Diffusion Models for Authentic Virtual Try-on in the Wild](https://mlsanity.com/paper/2403.05139/) (2024)
- [Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation](https://mlsanity.com/paper/2505.05472/) (2025)
- [CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion Models](https://mlsanity.com/paper/2407.15886/) (2024)
- [Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation](https://mlsanity.com/paper/2508.09987/) (2025)
- [MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer](https://mlsanity.com/paper/2401.10208/) (2024)
- [Any2AnyTryon: Leveraging Adaptive Position Embeddings for Versatile Virtual Clothing Tasks](https://mlsanity.com/paper/2501.15891/) (2025)
- [InstantStyle-Plus: Style Transfer with Content-Preserving in Text-to-Image Generation](https://mlsanity.com/paper/2407.00788/) (2024)
- [Stable-Makeup: When Real-World Makeup Transfer Meets Diffusion Model](https://mlsanity.com/paper/2403.07764/) (2024)
- [MakeAnything: Harnessing Diffusion Transformers for Multi-Domain Procedural Sequence Generation](https://mlsanity.com/paper/2502.01572/) (2025)
- [Orthus: Autoregressive Interleaved Image-Text Generation with Modality-Specific Heads](https://mlsanity.com/paper/2412.00127/) (2024)
- [LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer](https://mlsanity.com/paper/2502.01105/) (2025)

## Built on by (most cited first, 4 of 4)

- [OmniHumanoid: Streaming Cross-Embodiment Video Generation with Paired-Free Adaptation](https://mlsanity.com/paper/2605.12038/) (2026)
- [SIGMA: Selective-Interleaved Generation with Multi-Attribute Tokens](https://mlsanity.com/paper/2602.07564/) (2026)
- [Unlocking Complex Visual Generation via Closed-Loop Verified Reasoning](https://mlsanity.com/paper/2605.14876/) (2026)
- [Scaling Unified Multimodal Models to Long-Horizon Interleaved Generation](https://mlsanity.com/paper/2610.17080/) (2026)

## Abstract (arXiv)

Interleaved text-image generation aims to jointly produce coherent visual frames and aligned textual descriptions within a single sequence, enabling tasks such as style transfer, compositional synthesis, and procedural tutorials. We present Loom, a unified diffusion-transformer framework for interleaved text-image generation. Loom extends the Bagel unified model via full-parameter fine-tuning and an interleaved architecture that alternates textual and visual embeddings for multi-condition reasoning and sequential planning. A language planning strategy first decomposes a user instruction into stepwise prompts and frame embeddings, which guide temporally consistent synthesis. For each frame, Loom conditions on a small set of sampled prior frames together with the global textual context, rather than concatenating all history, yielding controllable and efficient long-horizon generation. Across style transfer, compositional generation, and tutorial-like procedures, Loom delivers superior compositionality, temporal coherence, and text-image alignment. Experiments demonstrate that Loom substantially outperforms the open-source baseline Anole, achieving an average gain of 2.6 points (on a 5-point scale) across temporal and semantic metrics in text-to-interleaved tasks. We also curate a 50K interleaved tutorial dataset and demonstrate strong improvements over unified and diffusion editing baselines.