Pith. sign in

REVIEW 13 cited by

SkyReels-A2: Compose Anything in Video Diffusion Transformers

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 2504.02436 v1 pith:WJCZNOSI submitted 2025-04-03 cs.CV

Zhengcong Fei , Debang Li , Di Qiu , Jiahua Wang , Yikun Dou , Rui Wang , Jingtao Xu , Mingyuan Fan
show 3 more authors
Guibin Chen Yang Li Yahui Zhou
This is my paper · ORCID
classification cs.CV
keywords skyreels-a2elementgenerationmodelvideocommercialconsistencycontrollable
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper presents SkyReels-A2, a controllable video generation framework capable of assembling arbitrary visual elements (e.g., characters, objects, backgrounds) into synthesized videos based on textual prompts while maintaining strict consistency with reference images for each element. We term this task elements-to-video (E2V), whose primary challenges lie in preserving the fidelity of each reference element, ensuring coherent composition of the scene, and achieving natural outputs. To address these, we first design a comprehensive data pipeline to construct prompt-reference-video triplets for model training. Next, we propose a novel image-text joint embedding model to inject multi-element representations into the generative process, balancing element-specific consistency with global coherence and text alignment. We also optimize the inference pipeline for both speed and output stability. Moreover, we introduce a carefully curated benchmark for systematic evaluation, i.e, A2 Bench. Experiments demonstrate that our framework can generate diverse, high-quality videos with precise element control. SkyReels-A2 is the first open-source commercial grade model for the generation of E2V, performing favorably against advanced closed-source commercial models. We anticipate SkyReels-A2 will advance creative applications such as drama and virtual e-commerce, pushing the boundaries of controllable video generation.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 13 Pith papers

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

  1. CineWeaver: Training-Free Reference-Controllable Multi-Shot Long Video Generation for Cinematic Storytelling

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Inference-time manipulation of RoPE, attention masks, per-shot conditioning, and VAE decoding lets frozen text-to-video models produce reference-controlled multi-shot long videos.

  2. HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent Enhancement

    cs.CV 2026-07 conditional novelty 6.0 of 10

    HOMIE unifies inter- and intra-subject video personalization by injecting MLLM-derived relational features into DiT self-attention (GMG) and tagging tokens with modality/reference embeddings (MRE), reporting SOTA on a...

  3. Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Aura combines VLM meta-queries, T5-teacher alignment, subject-aware RoPE shifts, memory tokens, and a large AIGC-curated dataset to claim SOTA multi-element subject-to-video generation under OpenS2V-Eval Total score.

  4. Rethinking Position Embedding as a Context Controller for Multi-Reference and Multi-Shot Video Generation

    cs.CV 2026-04 conditional novelty 6.0 of 10

    SideInfo-RoPE encodes reference-identity agreement as an extra rotary axis, disambiguating similar characters in multi-reference multi-shot video generation while keeping full semantic attention.

  5. RefAlign: Representation Alignment for Reference-to-Video Generation

    cs.CV 2026-03 conditional novelty 6.0 of 10

    Explicit training-time alignment of DiT reference features to a VFM (with pull/push loss) raises OpenS2V-Eval TotalScore over prior R2V methods with no inference cost.

  6. OmniCustom: Sync Audio-Video Customization Via Joint Audio-Video Generation Model

    cs.SD 2026-02 conditional novelty 6.0 of 10

    A zero-shot model that generates a video of a reference face speaking user-chosen text with a reference voice timbre.

  7. CustomX: Unified Character, Action, and Scene Customization in Video World Models

    cs.CV 2025-12 conditional novelty 6.0 of 10

    AniX generates controllable videos of a user-supplied character performing typed actions inside a user-supplied 3D scene by fine-tuning a pre-trained video generator on small locomotion datasets.

  8. Phantom-Data : Towards a General Subject-Consistent Video Generation Dataset

    cs.CV 2025-06 conditional novelty 6.0 of 10

    Phantom-Data provides around one million cross-context, identity-consistent reference-video pairs for subject-to-video generation, and training on it improves prompt following and visual quality.

  9. PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancement

    cs.CV 2025-06 conditional novelty 6.0 of 10

    PolyVivid combines VLLM-based grounding, 3D-RoPE positional encoding, and attention-inherited identity injection to generate customized videos with multiple consistent subjects and text-specified interactions.

  10. OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation

    cs.CV 2025-05 conditional novelty 6.0 of 10

    A benchmark and five-million-clip dataset for evaluating and training subject-to-video generation models, with three new metrics for subject consistency, naturalness, and text alignment.

  11. Vera: Identity-Faithful Human Subject-to-Video Generation

    cs.CV 2026-07 conditional novelty 5.0 of 10

    Vera improves identity consistency in human subject-to-video generation using cross-clip identity-aligned data, face-weighted masked loss, and layer-aware reference attention.

  12. Keyframe-Anchored Identity Preservation for Sequential-Action Video Generation

    cs.CV 2026-07 conditional novelty 5.0 of 10

    A keyframe-anchored, training-free pipeline—terminal-state prompts, chained keyframe generation, and identity-aware sampling—ranks third on the IPVG26 Track 2 leaderboard.

  13. SkyReels-Audio: Omni Audio-Conditioned Talking Portraits in Video Diffusion Transformers

    cs.CV 2025-06 conditional novelty 5.0 of 10

    An audio-conditioned video diffusion transformer that animates portraits from image, video, text, and audio inputs with a sliding-window fusion for long videos.

Pith tools