Pith. sign in

REVIEW 4 cited by

Magic-Me: Identity-Specific Video Customized Diffusion

Not yet reviewed by Pith; the record is open.

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 2402.09368 v2 pith:Z4R52XDH submitted 2024-02-14 cs.CV cs.AI

Magic-Me: Identity-Specific Video Customized Diffusion

classification cs.CV cs.AI
keywords identityvideogenerationstableavailablebetterdiffusionfield
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Creating content with specified identities (ID) has attracted significant interest in the field of generative models. In the field of text-to-image generation (T2I), subject-driven creation has achieved great progress with the identity controlled via reference images. However, its extension to video generation is not well explored. In this work, we propose a simple yet effective subject identity controllable video generation framework, termed Video Custom Diffusion (VCD). With a specified identity defined by a few images, VCD reinforces the identity characteristics and injects frame-wise correlation at the initialization stage for stable video outputs. To achieve this, we propose three novel components that are essential for high-quality identity preservation and stable video generation: 1) a noise initialization method with 3D Gaussian Noise Prior for better inter-frame stability; 2) an ID module based on extended Textual Inversion trained with the cropped identity to disentangle the ID information from the background 3) Face VCD and Tiled VCD modules to reinforce faces and upscale the video to higher resolution while preserving the identity's features. We conducted extensive experiments to verify that VCD is able to generate stable videos with better ID over the baselines. Besides, with the transferability of the encoded identity in the ID module, VCD is also working well with personalized text-to-image models available publicly. The codes are available at https://github.com/Zhen-Dong/Magic-Me.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

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

  1. ID-V2V: Identity-Preserving Video Restylization

    cs.CV 2026-07 conditional novelty 6.0

    ID-V2V restyles video by conditioning a diffusion model on edited keyframes, depth, relit faces, and face normals, so scene edits propagate while facial identity and performance are preserved.

  2. GroupVideo: Multi-Identity Customized Text-to-Video Generation

    cs.CV 2026-07 conditional novelty 6.0

    GroupVideo generates multi-person videos from reference photos plus text, using multimodal identity alignment and ID localization to keep each person's identity consistent.

  3. Segmentation, Detection and Explanation: A Unified Framework for CT Appearance Reasoning

    cs.CV 2026-05 unverdicted novelty 6.0

    A unified autoregressive vision-language framework integrates segmentation, detection, and appearance reasoning for CT images via task-routing tokens and progressive refinement, with gains on public benchmarks.

  4. Evolution of Video Generative Foundations

    cs.CV 2026-04 unverdicted novelty 2.0

    This survey traces video generation technology from GANs to diffusion models and then to autoregressive and multimodal approaches while analyzing principles, strengths, and future trends.