Pith. sign in

REVIEW 21 cited by

Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning

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 2311.10709 v2 pith:GUKR7RF3 submitted 2023-11-17 cs.CV cs.AIcs.GRcs.LGcs.MM

Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning

classification cs.CV cs.AIcs.GRcs.LGcs.MM
keywords videogenerationimagepriortextconditionedfactorizinggenerated
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We present Emu Video, a text-to-video generation model that factorizes the generation into two steps: first generating an image conditioned on the text, and then generating a video conditioned on the text and the generated image. We identify critical design decisions--adjusted noise schedules for diffusion, and multi-stage training that enable us to directly generate high quality and high resolution videos, without requiring a deep cascade of models as in prior work. In human evaluations, our generated videos are strongly preferred in quality compared to all prior work--81% vs. Google's Imagen Video, 90% vs. Nvidia's PYOCO, and 96% vs. Meta's Make-A-Video. Our model outperforms commercial solutions such as RunwayML's Gen2 and Pika Labs. Finally, our factorizing approach naturally lends itself to animating images based on a user's text prompt, where our generations are preferred 96% over prior work.

discussion (0)

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

Forward citations

Cited by 21 Pith papers

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

  1. Physics in 2-Steps: Locking Motion Priors Before Visual Refinement Erases Them

    cs.CV 2026-06 unverdicted novelty 7.0

    PhaseLock extracts motion priors from 2-step inference and enforces them via Latent Delta Guidance to raise physical consistency scores by 6.2 points on average in image-to-video diffusion models.

  2. StreamingEffect: Real-Time Human-Centric Video Effect Generation

    cs.CV 2026-05 unverdicted novelty 7.0

    StreamingEffect enables real-time 720p human-centric video effect generation on one GPU via teacher-student distillation, keyframe control, and a new 130K video dataset.

  3. DCR: Counterfactual Attractor Guidance for Rare Compositional Generation

    cs.CV 2026-05 unverdicted novelty 7.0

    DCR uses a counterfactual attractor and projection-based repulsion to suppress default completion bias in diffusion models, improving fidelity for rare compositional prompts while preserving quality.

  4. Diffusion Models Are Real-Time Game Engines

    cs.LG 2024-08 conditional novelty 7.0

    A diffusion model trained on DOOM play sessions generates stable real-time interactive game frames at 20 FPS with quality near lossy JPEG.

  5. RoboDreamer: Learning Compositional World Models for Robot Imagination

    cs.RO 2024-04 unverdicted novelty 7.0

    RoboDreamer factorizes video generation using language primitives to achieve compositional generalization in robot world models, outperforming monolithic baselines on unseen goals in RT-X.

  6. TPD: Temporal Prior Decoupling for Text-to-Video Diffusion Models

    cs.CV 2026-07 conditional novelty 6.5

    TPD restores suppressed late-segment events in text-to-video diffusion by projecting classifier-free guidance onto a frame- and timestep-selective lower bound along a temporal-counterfactual direction.

  7. Head Forcing: Long Autoregressive Video Generation via Head Heterogeneity

    cs.CV 2026-05 unverdicted novelty 6.0

    Head Forcing assigns tailored KV cache strategies to local, anchor, and memory attention heads plus head-wise RoPE re-encoding to extend autoregressive video generation from seconds to minutes without training.

  8. CityRAG: Stepping Into a City via Spatially-Grounded Video Generation

    cs.CV 2026-04 unverdicted novelty 6.0

    CityRAG generates minutes-long 3D-consistent videos of real-world cities by grounding outputs in geo-registered data and using temporally unaligned training to disentangle fixed scenes from transient elements like weather.

  9. CityRAG: Stepping Into a City via Spatially-Grounded Video Generation

    cs.CV 2026-04 conditional novelty 6.0

    PlayCoder combines a repository-aware coding agent with a vision-based GUI testing agent and an automated program repair loop to detect and fix silent logic errors in LLM-generated interactive application code.

  10. Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion

    cs.CV 2026-02 unverdicted novelty 6.0

    Rolling Sink is a training-free cache adjustment technique that maintains visual consistency in autoregressive video diffusion models for ultra-long open-ended generation beyond training horizons.

  11. Enhancing Physical Plausibility in Video Generation by Reasoning the Implausibility

    cs.CV 2025-09 unverdicted novelty 6.0

    A training-free framework uses physics-violating counterfactual prompts and Synchronized Decoupled Guidance to suppress implausible motions in diffusion-based video generation while preserving photorealism.

  12. Unified Video Action Model

    cs.RO 2025-02 unverdicted novelty 6.0

    UVA learns a joint video-action latent representation with decoupled diffusion decoding heads, enabling a single model to perform accurate fast policy learning, forward/inverse dynamics, and video generation without p...

  13. Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation

    cs.RO 2024-09 unverdicted novelty 6.0

    Gen2Act enables generalizable robot manipulation for unseen objects and novel motions by using zero-shot human video generation from web data to condition a policy trained on an order of magnitude less robot interaction data.

  14. CAT3D: Create Anything in 3D with Multi-View Diffusion Models

    cs.CV 2024-05 conditional novelty 6.0

    A multi-view diffusion model generates consistent novel views from sparse images to enable fast 3D scene reconstruction.

  15. HunyuanVideo: A Systematic Framework For Large Video Generative Models

    cs.CV 2024-12 unverdicted novelty 5.0

    HunyuanVideo presents a 13B-parameter open-source video generative model with integrated data, architecture, training, and inference systems whose professional evaluations show it outperforming prior SOTA models inclu...

  16. KFC-W: Generating 3D-Consistent Videos from Unposed Internet Photos

    cs.CV 2024-11 unverdicted novelty 5.0

    KFC-W is a self-supervised 3D-aware video model trained on videos and multiview internet photos that produces geometrically consistent interpolations between unposed input images without any 3D annotations.

  17. Character-Centered Dialogue Generation from Scene-Level Prompts

    cs.CV 2025-05 unverdicted novelty 4.0

    A training-free framework generates expressive, character-grounded dialogue and speech from scene prompts using vision-language encoders, LLMs, and a recursive narrative memory bank for cross-scene consistency.

  18. Image-to-Video Diffusion: From Foundations to Open Frontiers

    cs.CV 2026-05 unverdicted novelty 3.0

    A survey that organizes diffusion image-to-video methods into a taxonomy, distills core designs in condition encoding, temporal modeling, noise prior, and upsampling, and discusses applications plus challenges.

  19. Scene-Action Prompt Fusion for Coherent Text-to-Video Storytelling

    cs.CV 2025-03 unverdicted novelty 3.0

    A prompt fusion approach combines bidirectional time-weighted latent blending, dynamics-informed prompt weighting via CLIP, and semantic action representations to produce temporally consistent long videos from text wi...

  20. 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.

  21. Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models

    cs.CV 2024-02 unverdicted novelty 2.0

    The paper reviews the background, technology, applications, limitations, and future directions of OpenAI's Sora text-to-video generative model based on public information.