# Instruct-Imagen: Image Generation with Multi-modal Instruction

arXiv: https://arxiv.org/abs/2401.01952 · HTML: https://mlsanity.com/paper/2401.01952/

## Key facts

- Cited by 65 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 54 references that are in the map.
- First posted on arXiv 3 Jan 2024.

## Builds on (most cited first, 30 of 47)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge](https://mlsanity.com/paper/1906.00067/) (2019)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [Adafactor: Adaptive Learning Rates with Sublinear Memory Cost](https://mlsanity.com/paper/1804.04235/) (2018)
- [PaLI: A Jointly-Scaled Multilingual Language-Image Model](https://mlsanity.com/paper/2209.06794/) (2022)
- [Vector-quantized Image Modeling with Improved VQGAN](https://mlsanity.com/paper/2110.04627/) (2021)
- [Muse: Text-To-Image Generation via Masked Generative Transformers](https://mlsanity.com/paper/2301.00704/) (2023)
- [MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing](https://mlsanity.com/paper/2306.10012/) (2023)

## Built on by (most cited first, 30 of 65)

- [Step1X-Edit: A Practical Framework for General Image Editing](https://mlsanity.com/paper/2504.17761/) (2025)
- [Transfer between Modalities with MetaQueries](https://mlsanity.com/paper/2504.06256/) (2025)
- [MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance](https://mlsanity.com/paper/2406.07209/) (2024)
- [DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation](https://mlsanity.com/paper/2406.16855/) (2024)
- [UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics](https://mlsanity.com/paper/2412.07774/) (2024)
- [UniVideo: Unified Understanding, Generation, and Editing for Videos](https://mlsanity.com/paper/2510.08377/) (2025)
- [Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2412.02104/) (2024)
- [Diffusion Feedback Helps CLIP See Better](https://mlsanity.com/paper/2407.20171/) (2024)
- [CreatiDesign: A Unified Multi-Conditional Diffusion Transformer for Creative Graphic Design](https://mlsanity.com/paper/2505.19114/) (2025)
- [Reward Guided Latent Consistency Distillation](https://mlsanity.com/paper/2403.11027/) (2024)
- [MusicMagus: Zero-Shot Text-to-Music Editing via Diffusion Models](https://mlsanity.com/paper/2402.06178/) (2024)
- [PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructions](https://mlsanity.com/paper/2409.15278/) (2024)
- [ImageRAG: Dynamic Image Retrieval for Reference-Guided Image Generation](https://mlsanity.com/paper/2502.09411/) (2025)
- [Enhance Image-to-Image Generation with LLaVA-generated Prompts](https://mlsanity.com/paper/2406.01956/) (2024)
- [Personalized Image Generation with Deep Generative Models: A Decade Survey](https://mlsanity.com/paper/2502.13081/) (2025)
- [RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models](https://mlsanity.com/paper/2402.12908/) (2024)
- [ObjectMate: A Recurrence Prior for Object Insertion and Subject-Driven Generation](https://mlsanity.com/paper/2412.08645/) (2024)
- [Mod-Adapter: Tuning-Free and Versatile Multi-concept Personalization via Modulation Adapter](https://mlsanity.com/paper/2505.18612/) (2025)
- [PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion Preimage](https://mlsanity.com/paper/2409.09144/) (2024)
- [AttnDreamBooth: Towards Text-Aligned Personalized Text-to-Image Generation](https://mlsanity.com/paper/2406.05000/) (2024)
- [MIGE: Mutually Enhanced Multimodal Instruction-Based Image Generation and Editing](https://mlsanity.com/paper/2502.21291/) (2025)
- [Modality-Specialized Synergizers for Interleaved Vision-Language Generalists](https://mlsanity.com/paper/2407.03604/) (2024)
- [UNIC-Adapter: Unified Image-instruction Adapter with Multi-modal Transformer for Image Generation](https://mlsanity.com/paper/2412.18928/) (2024)
- [MultiRef: Controllable Image Generation with Multiple Visual References](https://mlsanity.com/paper/2508.06905/) (2025)
- [VIMI: Grounding Video Generation through Multi-modal Instruction](https://mlsanity.com/paper/2407.06304/) (2024)
- [DreamStruct: Understanding Slides and User Interfaces via Synthetic Data Generation](https://mlsanity.com/paper/2410.00201/) (2024)
- [Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation](https://mlsanity.com/paper/2607.05382/) (2026)
- [Visual Persona: Foundation Model for Full-Body Human Customization](https://mlsanity.com/paper/2503.15406/) (2025)
- [BlenderFusion: 3D-Grounded Visual Editing and Generative Compositing](https://mlsanity.com/paper/2506.17450/) (2025)
- [ShoulderShot: Generating Over-the-Shoulder Dialogue Videos](https://mlsanity.com/paper/2508.07597/) (2025)

## Abstract (arXiv)

This paper presents instruct-imagen, a model that tackles heterogeneous image generation tasks and generalizes across unseen tasks. We introduce *multi-modal instruction* for image generation, a task representation articulating a range of generation intents with precision. It uses natural language to amalgamate disparate modalities (e.g., text, edge, style, subject, etc.), such that abundant generation intents can be standardized in a uniform format. We then build instruct-imagen by fine-tuning a pre-trained text-to-image diffusion model with a two-stage framework. First, we adapt the model using the retrieval-augmented training, to enhance model's capabilities to ground its generation on external multimodal context. Subsequently, we fine-tune the adapted model on diverse image generation tasks that requires vision-language understanding (e.g., subject-driven generation, etc.), each paired with a multi-modal instruction encapsulating the task's essence. Human evaluation on various image generation datasets reveals that instruct-imagen matches or surpasses prior task-specific models in-domain and demonstrates promising generalization to unseen and more complex tasks.