Pith. sign in

REVIEW 8 cited by

StableIdentity: Inserting Anybody into Anywhere at First Sight

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2401.15975 v1 pith:HRE7NNGG submitted 2024-01-29 cs.CV

Qinghe Wang , Xu Jia , Xiaomin Li , Taiqing Li , Liqian Ma , Yunzhi Zhuge , Huchuan Lu This is my paper · ORCID
classification cs.CV
keywords identityfacegenerationpriorimagelearnedstableidentityaddition
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Recent advances in large pretrained text-to-image models have shown unprecedented capabilities for high-quality human-centric generation, however, customizing face identity is still an intractable problem. Existing methods cannot ensure stable identity preservation and flexible editability, even with several images for each subject during training. In this work, we propose StableIdentity, which allows identity-consistent recontextualization with just one face image. More specifically, we employ a face encoder with an identity prior to encode the input face, and then land the face representation into a space with an editable prior, which is constructed from celeb names. By incorporating identity prior and editability prior, the learned identity can be injected anywhere with various contexts. In addition, we design a masked two-phase diffusion loss to boost the pixel-level perception of the input face and maintain the diversity of generation. Extensive experiments demonstrate our method outperforms previous customization methods. In addition, the learned identity can be flexibly combined with the off-the-shelf modules such as ControlNet. Notably, to the best knowledge, we are the first to directly inject the identity learned from a single image into video/3D generation without finetuning. We believe that the proposed StableIdentity is an important step to unify image, video, and 3D customized generation models.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. RefSTAR: Blind Facial Image Restoration with Reference Selection, Transfer, and Reconstruction

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A reference-based face restoration method that explicitly selects which reference regions to transfer, uses dual-stream attention to force feature transfer, and adds a mask-compatible cycle loss, achieving state-of-th...

  2. "I Know It When I See It": Mood Spaces for Connecting and Expressing Visual Concepts

    cs.CV 2025-04 conditional novelty 6.0 of 10

    A few-example Mood Space, learned by matching spectral affinity structure of DINO tokens and decoding to CLIP, lets users interpolate and analogize visual concepts with simple vector arithmetic.

  3. Arc2Avatar: Generating Expressive 3D Avatars from a Single Image via ID Guidance

    cs.CV 2025-01 conditional novelty 6.0 of 10

    Arc2Avatar generates expressive 3D head avatars from a single image by distilling a LoRA-fine-tuned Arc2Face model into 3D Gaussian splats anchored to a FLAME mesh, enabling blendshape expressions.

  4. RealisID: Scale-Robust and Fine-Controllable Identity Customization via Local and Global Complementation

    cs.CV 2024-12 conditional novelty 6.0 of 10

    RealisID uses two complementary control branches to deliver scale-robust identity fidelity, fine facial control, and zero-shot multi-person customization for text-to-image generation.

  5. SHMT: Self-supervised Hierarchical Makeup Transfer via Latent Diffusion Models

    cs.CV 2024-12 conditional novelty 6.0 of 10

    SHMT is a self-supervised latent-diffusion makeup transfer method that decouples face content and makeup and reconstructs the input, avoiding pseudo-paired training data.

  6. MoTrans: Customized Motion Transfer with Text-driven Video Diffusion Models

    cs.CV 2024-12 conditional novelty 6.0 of 10

    MoTrans transfers specific motions from reference videos to new subjects using a two-stage fine-tuning scheme with recaptioned prompts, appearance injection, and a motion-specific verb embedding.

  7. Dense-Face: Personalized Face Generation Model via Dense Annotation Prediction

    cs.CV 2024-12 conditional novelty 4.0 of 10

    Dense-Face is a personalized face generation model that adds a pose-controllable adapter and dense face annotation prediction to Stable Diffusion, improving identity preservation and text alignment.

  8. Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlook

    cs.CV 2024-11 conditional novelty 4.0 of 10

    The paper introduces BioDeepAV, a benchmark of real and fake talking-face videos, and reports that state-of-the-art deepfake detectors drop sharply when tested on deepfakes from unseen generators.

Pith tools