Pith. sign in

REVIEW 17 cited by

Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation

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 2410.07718 v2 pith:XJM3MUBB submitted 2024-10-10 cs.CV

Jiahao Cui , Hui Li , Yao Yao , Hao Zhu , Hanlin Shang , Kaihui Cheng , Hang Zhou , Siyu Zhu
show 1 more author
Jingdong Wang
This is my paper · ORCID
classification cs.CV
keywords portraitimageresolutiontemporalanimationhallo2long-durationmethod
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent advances in latent diffusion-based generative models for portrait image animation, such as Hallo, have achieved impressive results in short-duration video synthesis. In this paper, we present updates to Hallo, introducing several design enhancements to extend its capabilities. First, we extend the method to produce long-duration videos. To address substantial challenges such as appearance drift and temporal artifacts, we investigate augmentation strategies within the image space of conditional motion frames. Specifically, we introduce a patch-drop technique augmented with Gaussian noise to enhance visual consistency and temporal coherence over long duration. Second, we achieve 4K resolution portrait video generation. To accomplish this, we implement vector quantization of latent codes and apply temporal alignment techniques to maintain coherence across the temporal dimension. By integrating a high-quality decoder, we realize visual synthesis at 4K resolution. Third, we incorporate adjustable semantic textual labels for portrait expressions as conditional inputs. This extends beyond traditional audio cues to improve controllability and increase the diversity of the generated content. To the best of our knowledge, Hallo2, proposed in this paper, is the first method to achieve 4K resolution and generate hour-long, audio-driven portrait image animations enhanced with textual prompts. We have conducted extensive experiments to evaluate our method on publicly available datasets, including HDTF, CelebV, and our introduced "Wild" dataset. The experimental results demonstrate that our approach achieves state-of-the-art performance in long-duration portrait video animation, successfully generating rich and controllable content at 4K resolution for duration extending up to tens of minutes. Project page https://fudan-generative-vision.github.io/hallo2

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 17 Pith papers

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

  1. Proxy Avatar Meets Low-Rank Caching: Real-Time One-Shot Emotion-Controllable Portrait Animation

    cs.CV 2026-08 conditional novelty 6.0 of 10

    A cascade of a single-identity Gaussian emotion proxy, a one-shot diffusion retargeting model, and low-rank appearance caching enables real-time one-shot portrait animation with emotion control.

  2. Towards Flexible, Natural, Efficient Interaction for Conversational Talking Face Generation

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    InterTalk is a motion-based real-time framework for flexible multi-round multi-person conversational talking face generation using motion feedback, iterative strategies, and facial component disentanglement, supported...

  3. SyncBreaker:Stage-Aware Multimodal Adversarial Attacks on Audio-Driven Talking Head Generation

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    SyncBreaker jointly attacks image and audio streams with Multi-Interval Sampling and Cross-Attention Fooling to degrade speech-driven talking head generation more than single-modality baselines.

  4. STARCaster: Spatio-Temporal AutoRegressive Video Diffusion for Identity- and View-Aware Talking Portraits

    cs.CV 2025-12 conditional novelty 6.0 of 10

    STARCaster is a 2D spatio-temporal video diffusion model that unifies identity-conditioned audio-driven portrait animation and novel-view synthesis without explicit 3D reconstruction.

  5. AmbiGraph-Eval: Can LLMs Effectively Handle Ambiguous Graph Queries?

    cs.DB 2025-08 unverdicted novelty 6.0 of 10

    A benchmark organized by a six-type taxonomy of ambiguous graph queries reportedly shows that nine LLMs, including top models, frequently produce wrong query translations.

  6. LaVieID: Local Autoregressive Diffusion Transformers for Identity-Preserving Video Creation

    cs.CV 2025-08 conditional novelty 6.0 of 10

    LaVieID improves identity-preserving text-to-video by routing local facial parts into early DiT blocks and autoregressively refining denoised video tokens in temporal chunks.

  7. Multi-human Interactive Talking Dataset

    cs.CV 2025-08 conditional novelty 6.0 of 10

    The paper contributes a 12-hour multi-person conversational video dataset with pose and speaking annotations, plus a baseline model for generating full-body talking videos of two to four people.

  8. MagicAnime: A Hierarchically Annotated, Multimodal and Multitasking Dataset with Benchmarks for Cartoon Animation Generation

    cs.CV 2025-07 conditional novelty 6.0 of 10

    MagicAnime is a 400k-clip multimodal cartoon dataset with hierarchical annotations and benchmarks for image-to-video, pose-driven, face reenactment, and audio-driven animation generation.

  9. Silence is Golden: Leveraging Adversarial Examples to Nullify Audio Control in LDM-based Talking-Head Generation

    cs.GR 2025-06 conditional novelty 6.0 of 10

    Silencer adds a nearly invisible disturbance to portraits that makes LDM-based talking-head models keep the mouth silent, and it survives several image-purification countermeasures.

  10. FA-LAM: Focus-Aware Large Avatar Model for One-Shot 4D Animatable Gaussian Head

    cs.CV 2026-07 conditional novelty 5.0 of 10

    A one-shot model for animatable 3D/4D Gaussian head reconstruction that adds attention regularization, decoupled reconstruction-animation training, and autoregressive visibility-gated fusion, reporting consistent metr...

  11. EDTalk++: Full Disentanglement for Controllable Talking Head Synthesis

    cs.CV 2025-08 conditional novelty 5.0 of 10

    EDTalk++ disentangles talking-head video into four orthogonal motion banks (mouth, pose, eyes, expression) and drives them from either video or audio inputs.

  12. MoDA: Multi-modal Diffusion Architecture for Talking Head Generation

    cs.GR 2025-07 conditional novelty 5.0 of 10

    MoDA uses flow matching in a compact face-motion space with a progressively fused multi-modal transformer to generate expressive, lip-synced talking-head videos from a single image and audio.

  13. FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases

    cs.CV 2025-07 conditional novelty 5.0 of 10

    FixTalk adds two modules to a real-time GAN talking-head model, decoupling identity from motion to stop identity leakage while using a memory to recover details and reduce artifacts.

  14. FaceEditTalker: Controllable Talking Head Generation with Facial Attribute Editing

    cs.CV 2025-05 conditional novelty 5.0 of 10

    A single framework can edit predefined facial attributes in audio-synchronized talking head videos while preserving identity and lip-sync quality.

  15. Preview WB-DH: Towards Whole Body Digital Human Bench for the Generation of Whole-body Talking Avatar Videos

    cs.CV 2025-08 reject novelty 4.0 of 10

    The paper previews a claimed 2M-clip multimodal benchmark for whole-body talking avatar video generation, with standard metrics and an initial evaluation of eight open-source models.

  16. JWB-DH-V1: Benchmark for Joint Whole-Body Talking Avatar and Speech Generation Version 1

    cs.CV 2025-07 reject novelty 4.0 of 10

    A paper announcing a large-scale whole-body talking avatar benchmark and evaluation protocol, but with insufficient details to verify the dataset or the joint audio-video evaluation.

  17. LLIA -- Enabling Low-Latency Interactive Avatars: Real-Time Audio-Driven Portrait Video Generation with Diffusion Models

    cs.CV 2025-06 conditional novelty 4.0 of 10

    Using consistency distillation, INT8 quantization, and pipeline parallelism, the LLIA system generates portrait video from audio at 78 FPS, with 140 ms initial latency.

Pith tools