Upcycling Text-to-Image Diffusion Models for Multi-Task Capabilities

• URL: http://arxiv.org/abs/2503.11905v1
• Date: Fri, 14 Mar 2025 22:19:20 GMT
• Title: Upcycling Text-to-Image Diffusion Models for Multi-Task Capabilities
• Authors: Ruchika Chavhan, Abhinav Mehrotra, Malcolm Chadwick, Alberto Gil Ramos, Luca Morreale, Mehdi Noroozi, Sourav Bhattacharya,
• Abstract summary: Multi-Task Upcycling (MTU) is a recipe that extends the capabilities of a pre-trained text-to-image diffusion model to support a variety of image-to-image generation tasks.<n>MTU is the first multi-task diffusion modeling approach that seamlessly blends multi-tasking with on-device compatibility.<n>We show that the performance of MTU is on par with the single-task fine-tuned diffusion models across several tasks.
• Score: 8.81828807024982
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text-to-image synthesis has witnessed remarkable advancements in recent years. Many attempts have been made to adopt text-to-image models to support multiple tasks. However, existing approaches typically require resource-intensive re-training or additional parameters to accommodate for the new tasks, which makes the model inefficient for on-device deployment. We propose Multi-Task Upcycling (MTU), a simple yet effective recipe that extends the capabilities of a pre-trained text-to-image diffusion model to support a variety of image-to-image generation tasks. MTU replaces Feed-Forward Network (FFN) layers in the diffusion model with smaller FFNs, referred to as experts, and combines them with a dynamic routing mechanism. To the best of our knowledge, MTU is the first multi-task diffusion modeling approach that seamlessly blends multi-tasking with on-device compatibility, by mitigating the issue of parameter inflation. We show that the performance of MTU is on par with the single-task fine-tuned diffusion models across several tasks including image editing, super-resolution, and inpainting, while maintaining similar latency and computational load (GFLOPs) as the single-task fine-tuned models.

Related papers

• Unified Multimodal Discrete Diffusion [78.48930545306654]
  Multimodal generative models that can understand and generate across multiple modalities are dominated by autoregressive (AR) approaches. We explore discrete diffusion models as a unified generative formulation in the joint text and image domain. We present the first Unified Multimodal Discrete Diffusion (UniDisc) model which is capable of jointly understanding and generating text and images.
  arXiv  Detail & Related papers  (2025-03-26T17:59:51Z)
• UniVG: A Generalist Diffusion Model for Unified Image Generation and Editing [59.590505989071175]
  Text-to-Image (T2I) diffusion models have shown impressive results in generating visually compelling images following user prompts. We introduce UniVG, a generalist diffusion model capable of supporting a diverse range of image generation tasks with a single set of weights.
  arXiv  Detail & Related papers  (2025-03-16T21:11:25Z)
• Do We Need to Design Specific Diffusion Models for Different Tasks? Try ONE-PIC [77.8851460746251]
  We propose a simple, efficient, and general approach to fine-tune diffusion models.<n> ONE-PIC enhances the inherited generative ability in the pretrained diffusion models without introducing additional modules.<n>Our method is simple and efficient which streamlines the adaptation process and achieves excellent performance with lower costs.
  arXiv  Detail & Related papers  (2024-12-07T11:19:32Z)
• DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception [66.88792390480343]
  We propose DEEM, a simple but effective approach that utilizes the generative feedback of diffusion models to align the semantic distributions of the image encoder.<n>DEEM exhibits enhanced robustness and a superior capacity to alleviate model hallucinations while utilizing fewer trainable parameters, less pre-training data, and a smaller base model size.
  arXiv  Detail & Related papers  (2024-05-24T05:46:04Z)
• Many-to-many Image Generation with Auto-regressive Diffusion Models [59.5041405824704]
  This paper introduces a domain-general framework for many-to-many image generation, capable of producing interrelated image series from a given set of images. We present MIS, a novel large-scale multi-image dataset, containing 12M synthetic multi-image samples, each with 25 interconnected images. We learn M2M, an autoregressive model for many-to-many generation, where each image is modeled within a diffusion framework.
  arXiv  Detail & Related papers  (2024-04-03T23:20:40Z)
• MM-Diff: High-Fidelity Image Personalization via Multi-Modal Condition Integration [7.087475633143941]
  MM-Diff is a tuning-free image personalization framework capable of generating high-fidelity images of both single and multiple subjects in seconds. MM-Diff employs a vision encoder to transform the input image into CLS and patch embeddings. CLS embeddings are used on the one hand to augment the text embeddings, and on the other hand together with patch embeddings to derive a small number of detail-rich subject embeddings.
  arXiv  Detail & Related papers  (2024-03-22T09:32:31Z)
• Multi-task Image Restoration Guided By Robust DINO Features [88.74005987908443]
  We propose mboxtextbfDINO-IR, a multi-task image restoration approach leveraging robust features extracted from DINOv2. We first propose a pixel-semantic fusion (PSF) module to dynamically fuse DINOV2's shallow features. By formulating these modules into a unified deep model, we propose a DINO perception contrastive loss to constrain the model training.
  arXiv  Detail & Related papers  (2023-12-04T06:59:55Z)
• MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation [34.61940502872307]
  MultiDiffusion is a unified framework that enables versatile and controllable image generation. We show that MultiDiffusion can be readily applied to generate high quality and diverse images.
  arXiv  Detail & Related papers  (2023-02-16T06:28:29Z)
• Versatile Diffusion: Text, Images and Variations All in One Diffusion Model [76.89932822375208]
  Versatile Diffusion handles multiple flows of text-to-image, image-to-text, and variations in one unified model. Our code and models are open-sourced at https://github.com/SHI-Labs/Versatile-Diffusion.
  arXiv  Detail & Related papers  (2022-11-15T17:44:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.