DeepAI AI Chat
Log In Sign Up

MultiFusion: Fusing Pre-Trained Models for Multi-Lingual, Multi-Modal Image Generation

by   Marco Bellagente, et al.
Technische Universität Darmstadt

The recent popularity of text-to-image diffusion models (DM) can largely be attributed to the intuitive interface they provide to users. The intended generation can be expressed in natural language, with the model producing faithful interpretations of text prompts. However, expressing complex or nuanced ideas in text alone can be difficult. To ease image generation, we propose MultiFusion that allows one to express complex and nuanced concepts with arbitrarily interleaved inputs of multiple modalities and languages. MutliFusion leverages pre-trained models and aligns them for integration into a cohesive system, thereby avoiding the need for extensive training from scratch. Our experimental results demonstrate the efficient transfer of capabilities from individual modules to the downstream model. Specifically, the fusion of all independent components allows the image generation module to utilize multilingual, interleaved multimodal inputs despite being trained solely on monomodal data in a single language.


page 5

page 6

page 8

page 9

page 14

page 16

page 17

page 18


LAFITE: Towards Language-Free Training for Text-to-Image Generation

One of the major challenges in training text-to-image generation models ...

Generating Images with Multimodal Language Models

We propose a method to fuse frozen text-only large language models (LLMs...

SUR-adapter: Enhancing Text-to-Image Pre-trained Diffusion Models with Large Language Models

Diffusion models, which have emerged to become popular text-to-image gen...

Weakly Supervised Annotations for Multi-modal Greeting Cards Dataset

In recent years, there is a growing number of pre-trained models trained...

Enhancing Subtask Performance of Multi-modal Large Language Model

Multi-modal Large Language Model (MLLM) refers to a model expanded from ...

Progressive Text-to-Image Diffusion with Soft Latent Direction

In spite of the rapidly evolving landscape of text-to-image generation, ...