# Multi-Concept T2I-Zero: Tweaking Only The Text Embeddings and Nothing Else

arXiv: https://arxiv.org/abs/2310.07419 · HTML: https://mlsanity.com/paper/2310.07419/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 37 of its 38 references that are in the map.
- First posted on arXiv 11 Oct 2023.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 30 of 37)

- [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)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [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)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (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)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [Variational Diffusion Models](https://mlsanity.com/paper/2107.00630/) (2021)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers](https://mlsanity.com/paper/2211.01324/) (2022)
- [GLIGEN: Open-Set Grounded Text-to-Image Generation](https://mlsanity.com/paper/2301.07093/) (2023)
- [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2301.13826/) (2023)
- [Score-based Generative Modeling in Latent Space](https://mlsanity.com/paper/2106.05931/) (2021)
- [Compositional Visual Generation with Composable Diffusion Models](https://mlsanity.com/paper/2206.01714/) (2022)
- [Zero-shot Image-to-Image Translation](https://mlsanity.com/paper/2302.03027/) (2023)
- [ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation](https://mlsanity.com/paper/2302.13848/) (2023)
- [Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis](https://mlsanity.com/paper/2212.05032/) (2022)
- [SVDiff: Compact Parameter Space for Diffusion Fine-Tuning](https://mlsanity.com/paper/2303.11305/) (2023)
- [Diffusion Self-Guidance for Controllable Image Generation](https://mlsanity.com/paper/2306.00986/) (2023)
- [P+: Extended Textual Conditioning in Text-to-Image Generation](https://mlsanity.com/paper/2303.09522/) (2023)
- [Break-A-Scene: Extracting Multiple Concepts from a Single Image](https://mlsanity.com/paper/2305.16311/) (2023)
- [Subject-driven Text-to-Image Generation via Apprenticeship Learning](https://mlsanity.com/paper/2304.00186/) (2023)

## Built on by (most cited first, 13 of 13)

- [Be Yourself: Bounded Attention for Multi-Subject Text-to-Image Generation](https://mlsanity.com/paper/2403.16990/) (2024)
- [OMG: Occlusion-friendly Personalized Multi-concept Generation in Diffusion Models](https://mlsanity.com/paper/2403.10983/) (2024)
- [Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions](https://mlsanity.com/paper/2403.17064/) (2024)
- [Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis](https://mlsanity.com/paper/2411.07132/) (2024)
- [Identity Decoupling for Multi-Subject Personalization of Text-to-Image Models](https://mlsanity.com/paper/2404.04243/) (2024)
- [Local Conditional Controlling for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2312.08768/) (2023)
- [Be Decisive: Noise-Induced Layouts for Multi-Subject Generation](https://mlsanity.com/paper/2505.21488/) (2025)
- [Infusion: Preventing Customized Text-to-Image Diffusion from Overfitting](https://mlsanity.com/paper/2404.14007/) (2024)
- [Image Generation from Contextually-Contradictory Prompts](https://mlsanity.com/paper/2506.01929/) (2025)
- [Not All Parameters Matter: Masking Diffusion Models for Enhancing Generation Ability](https://mlsanity.com/paper/2505.03097/) (2025)
- [Color Bind: Exploring Color Perception in Text-to-Image Models](https://mlsanity.com/paper/2508.19791/) (2025)
- [Composing People Together: Iterative Pose-Image Generation for Multi-Person Interaction Scenes](https://mlsanity.com/paper/2605.23178/) (2026)
- [MIFO: Learning and Synthesizing Multi-Instance from One Image](https://mlsanity.com/paper/2511.00542/) (2025)

## Abstract (arXiv)

Recent advances in text-to-image diffusion models have enabled the photorealistic generation of images from text prompts. Despite the great progress, existing models still struggle to generate compositional multi-concept images naturally, limiting their ability to visualize human imagination. While several recent works have attempted to address this issue, they either introduce additional training or adopt guidance at inference time. In this work, we consider a more ambitious goal: natural multi-concept generation using a pre-trained diffusion model, and with almost no extra cost. To achieve this goal, we identify the limitations in the text embeddings used for the pre-trained text-to-image diffusion models. Specifically, we observe concept dominance and non-localized contribution that severely degrade multi-concept generation performance. We further design a minimal low-cost solution that overcomes the above issues by tweaking (not re-training) the text embeddings for more realistic multi-concept text-to-image generation. Our Correction by Similarities method tweaks the embedding of concepts by collecting semantic features from most similar tokens to localize the contribution. To avoid mixing features of concepts, we also apply Cross-Token Non-Maximum Suppression, which excludes the overlap of contributions from different concepts. Experiments show that our approach outperforms previous methods in text-to-image, image manipulation, and personalization tasks, despite not introducing additional training or inference costs to the diffusion steps.