FaceChain-FACT: Face Adapter with Decoupled Training for Identity-preserved Personalization

• URL: http://arxiv.org/abs/2410.12312v2
• Date: Fri, 25 Oct 2024 06:56:54 GMT
• Title: FaceChain-FACT: Face Adapter with Decoupled Training for Identity-preserved Personalization
• Authors: Cheng Yu, Haoyu Xie, Lei Shang, Yang Liu, Jun Dan, Liefeng Bo, Baigui Sun,
• Abstract summary: adapter-based method obtains the ability to customize and generate portraits by text-to-image training on facial data. There is often a significant performance decrease in test following ability, controllability, and diversity of generated faces compared to the base model. We propose the Face Adapter with deCoupled Training (FACT) framework, focusing on both model architecture and training strategy.
• Score: 24.600720169589334
• License:
• Abstract: In the field of human-centric personalized image generation, the adapter-based method obtains the ability to customize and generate portraits by text-to-image training on facial data. This allows for identity-preserved personalization without additional fine-tuning in inference. Although there are improvements in efficiency and fidelity, there is often a significant performance decrease in test following ability, controllability, and diversity of generated faces compared to the base model. In this paper, we analyze that the performance degradation is attributed to the failure to decouple identity features from other attributes during extraction, as well as the failure to decouple the portrait generation training from the overall generation task. To address these issues, we propose the Face Adapter with deCoupled Training (FACT) framework, focusing on both model architecture and training strategy. To decouple identity features from others, we leverage a transformer-based face-export encoder and harness fine-grained identity features. To decouple the portrait generation training, we propose Face Adapting Increment Regularization~(FAIR), which effectively constrains the effect of face adapters on the facial region, preserving the generative ability of the base model. Additionally, we incorporate a face condition drop and shuffle mechanism, combined with curriculum learning, to enhance facial controllability and diversity. As a result, FACT solely learns identity preservation from training data, thereby minimizing the impact on the original text-to-image capabilities of the base model. Extensive experiments show that FACT has both controllability and fidelity in both text-to-image generation and inpainting solutions for portrait generation.

Related papers

• Turn That Frown Upside Down: FaceID Customization via Cross-Training Data [49.51940625552275]
  CrossFaceID is the first large-scale, high-quality, and publicly available dataset designed to improve the facial modification capabilities of FaceID customization models. It consists of 40,000 text-image pairs from approximately 2,000 persons, with each person represented by around 20 images showcasing diverse facial attributes. During the training stage, a specific face of a person is used as input, and the FaceID customization model is forced to generate another image of the same person but with altered facial features. Experiments show that models fine-tuned on the CrossFaceID dataset its performance in preserving FaceID fidelity while significantly improving its
  arXiv  Detail & Related papers  (2025-01-26T05:27:38Z)
• FaceMe: Robust Blind Face Restoration with Personal Identification [27.295878867436688]
  We propose a personalized face restoration method, FaceMe, based on a diffusion model. Given a single or a few reference images, we use an identity encoder to extract identity-related features, which serve as prompts to guide the diffusion model in restoring high-quality facial images. Experimental results demonstrate that our FaceMe can restore high-quality facial images while maintaining identity consistency, achieving excellent performance and robustness.
  arXiv  Detail & Related papers  (2025-01-09T11:52:54Z)
• Face Adapter for Pre-Trained Diffusion Models with Fine-Grained ID and Attribute Control [59.954322727683746]
  Face-Adapter is designed for high-precision and high-fidelity face editing for pre-trained diffusion models. Face-Adapter achieves comparable or even superior performance in terms of motion control precision, ID retention capability, and generation quality.
  arXiv  Detail & Related papers  (2024-05-21T17:50:12Z)
• StableIdentity: Inserting Anybody into Anywhere at First Sight [57.99693188913382]
  We propose StableIdentity, which allows identity-consistent recontextualization with just one face image. We are the first to directly inject the identity learned from a single image into video/3D generation without finetuning.
  arXiv  Detail & Related papers  (2024-01-29T09:06:15Z)
• Effective Adapter for Face Recognition in the Wild [72.75516495170199]
  We tackle the challenge of face recognition in the wild, where images often suffer from low quality and real-world distortions. Traditional approaches-either training models directly on degraded images or their enhanced counterparts using face restoration techniques-have proven ineffective. We propose an effective adapter for augmenting existing face recognition models trained on high-quality facial datasets.
  arXiv  Detail & Related papers  (2023-12-04T08:55:46Z)
• DreamIdentity: Improved Editability for Efficient Face-identity Preserved Image Generation [69.16517915592063]
  We propose a novel face-identity encoder to learn an accurate representation of human faces. We also propose self-augmented editability learning to enhance the editability of models. Our methods can generate identity-preserved images under different scenes at a much faster speed.
  arXiv  Detail & Related papers  (2023-07-01T11:01:17Z)
• DiffFace: Diffusion-based Face Swapping with Facial Guidance [24.50570533781642]
  We propose a diffusion-based face swapping framework for the first time, called DiffFace. It is composed of training ID conditional DDPM, sampling with facial guidance, and a target-preserving blending. DiffFace achieves better benefits such as training stability, high fidelity, diversity of the samples, and controllability.
  arXiv  Detail & Related papers  (2022-12-27T02:51:46Z)
• DotFAN: A Domain-transferred Face Augmentation Network for Pose and Illumination Invariant Face Recognition [94.96686189033869]
  We propose a 3D model-assisted domain-transferred face augmentation network (DotFAN) DotFAN can generate a series of variants of an input face based on the knowledge distilled from existing rich face datasets collected from other domains. Experiments show that DotFAN is beneficial for augmenting small face datasets to improve their within-class diversity.
  arXiv  Detail & Related papers  (2020-02-23T08:16:34Z)

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.