CosmicMan: A Text-to-Image Foundation Model for Humans

• URL: http://arxiv.org/abs/2404.01294v1
• Date: Mon, 1 Apr 2024 17:59:05 GMT
• Title: CosmicMan: A Text-to-Image Foundation Model for Humans
• Authors: Shikai Li, Jianglin Fu, Kaiyuan Liu, Wentao Wang, Kwan-Yee Lin, Wayne Wu,
• Abstract summary: We present CosmicMan, a text-to-image foundation model specialized for generating high-fidelity human images. CosmicMan enables generating photo-realistic human images with meticulous appearance, reasonable structure, and precise text-image alignment with detailed dense descriptions.
• Score: 30.155677646188572
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present CosmicMan, a text-to-image foundation model specialized for generating high-fidelity human images. Unlike current general-purpose foundation models that are stuck in the dilemma of inferior quality and text-image misalignment for humans, CosmicMan enables generating photo-realistic human images with meticulous appearance, reasonable structure, and precise text-image alignment with detailed dense descriptions. At the heart of CosmicMan's success are the new reflections and perspectives on data and models: (1) We found that data quality and a scalable data production flow are essential for the final results from trained models. Hence, we propose a new data production paradigm, Annotate Anyone, which serves as a perpetual data flywheel to produce high-quality data with accurate yet cost-effective annotations over time. Based on this, we constructed a large-scale dataset, CosmicMan-HQ 1.0, with 6 Million high-quality real-world human images in a mean resolution of 1488x1255, and attached with precise text annotations deriving from 115 Million attributes in diverse granularities. (2) We argue that a text-to-image foundation model specialized for humans must be pragmatic -- easy to integrate into down-streaming tasks while effective in producing high-quality human images. Hence, we propose to model the relationship between dense text descriptions and image pixels in a decomposed manner, and present Decomposed-Attention-Refocusing (Daring) training framework. It seamlessly decomposes the cross-attention features in existing text-to-image diffusion model, and enforces attention refocusing without adding extra modules. Through Daring, we show that explicitly discretizing continuous text space into several basic groups that align with human body structure is the key to tackling the misalignment problem in a breeze.

Related papers

• MoLE: Enhancing Human-centric Text-to-image Diffusion via Mixture of Low-rank Experts [61.274246025372044]
  We study human-centric text-to-image generation in context of faces and hands. We propose a method called Mixture of Low-rank Experts (MoLE) by considering low-rank modules trained on close-up hand and face images respectively as experts. This concept draws inspiration from our observation of low-rank refinement, where a low-rank module trained by a customized close-up dataset has the potential to enhance the corresponding image part when applied at an appropriate scale.
  arXiv  Detail & Related papers  (2024-10-30T17:59:57Z)
• Improving face generation quality and prompt following with synthetic captions [57.47448046728439]
  We introduce a training-free pipeline designed to generate accurate appearance descriptions from images of people. We then use these synthetic captions to fine-tune a text-to-image diffusion model. Our results demonstrate that this approach significantly improves the model's ability to generate high-quality, realistic human faces.
  arXiv  Detail & Related papers  (2024-05-17T15:50:53Z)
• Towards Effective Usage of Human-Centric Priors in Diffusion Models for Text-based Human Image Generation [24.49857926071974]
  Vanilla text-to-image diffusion models struggle with generating accurate human images. Existing methods address this issue mostly by fine-tuning the model with extra images or adding additional controls. This paper explores the integration of human-centric priors directly into the model fine-tuning stage.
  arXiv  Detail & Related papers  (2024-03-08T11:59:32Z)
• Filter & Align: Leveraging Human Knowledge to Curate Image-Text Data [31.507451966555383]
  We present a novel algorithm that incorporates human knowledge on image-text alignment to guide filtering vast corpus of web-crawled image-text datasets. We collect a diverse image-text dataset where each image is associated with multiple captions from various sources. We train a reward model on these human-preference annotations to internalize the nuanced human understanding of image-text alignment.
  arXiv  Detail & Related papers  (2023-12-11T05:57:09Z)
• Stellar: Systematic Evaluation of Human-Centric Personalized Text-to-Image Methods [52.806258774051216]
  We focus on text-to-image systems that input a single image of an individual and ground the generation process along with text describing the desired visual context. We introduce a standardized dataset (Stellar) that contains personalized prompts coupled with images of individuals that is an order of magnitude larger than existing relevant datasets and where rich semantic ground-truth annotations are readily available. We derive a simple yet efficient, personalized text-to-image baseline that does not require test-time fine-tuning for each subject and which sets quantitatively and in human trials a new SoTA.
  arXiv  Detail & Related papers  (2023-12-11T04:47:39Z)
• Paragraph-to-Image Generation with Information-Enriched Diffusion Model [67.9265336953134]
  ParaDiffusion is an information-enriched diffusion model for paragraph-to-image generation task. It delves into the transference of the extensive semantic comprehension capabilities of large language models to the task of image generation. The code and dataset will be released to foster community research on long-text alignment.
  arXiv  Detail & Related papers  (2023-11-24T05:17:01Z)
• HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion [114.15397904945185]
  We propose a unified framework, HyperHuman, that generates in-the-wild human images of high realism and diverse layouts. Our model enforces the joint learning of image appearance, spatial relationship, and geometry in a unified network. Our framework yields the state-of-the-art performance, generating hyper-realistic human images under diverse scenarios.
  arXiv  Detail & Related papers  (2023-10-12T17:59:34Z)
• HumanDiffusion: a Coarse-to-Fine Alignment Diffusion Framework for Controllable Text-Driven Person Image Generation [73.3790833537313]
  Controllable person image generation promotes a wide range of applications such as digital human interaction and virtual try-on. We propose HumanDiffusion, a coarse-to-fine alignment diffusion framework, for text-driven person image generation.
  arXiv  Detail & Related papers  (2022-11-11T14:30:34Z)

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.