Pith. sign in

REVIEW 24 cited by

Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model

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 2504.08685 v2 pith:LMUD5STE submitted 2025-04-11 cs.CV cs.AI

classification cs.CVcs.AI
keywords modelseaweed-7bvideogenerationperformancetrainedtrainingdesign
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This technical report presents a cost-efficient strategy for training a video generation foundation model. We present a mid-sized research model with approximately 7 billion parameters (7B) called Seaweed-7B trained from scratch using 665,000 H100 GPU hours. Despite being trained with moderate computational resources, Seaweed-7B demonstrates highly competitive performance compared to contemporary video generation models of much larger size. Design choices are especially crucial in a resource-constrained setting. This technical report highlights the key design decisions that enhance the performance of the medium-sized diffusion model. Empirically, we make two observations: (1) Seaweed-7B achieves performance comparable to, or even surpasses, larger models trained on substantially greater GPU resources, and (2) our model, which exhibits strong generalization ability, can be effectively adapted across a wide range of downstream applications either by lightweight fine-tuning or continue training. See the project page at https://seaweed.video/

Discussion (0). Sign in to comment.

Forward citations

Cited by 24 Pith papers

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

  1. FantasyPortrait: Enhancing Multi-Character Portrait Animation with Expression-Augmented Diffusion Transformers

    cs.CV 2025-07 conditional novelty 7.0 of 10

    A DiT-based portrait animation model transfers implicit facial expressions to one or more characters using a masked cross-attention mechanism, supported by a new multi-face dataset and benchmark.

  2. Kaleido: Algorithm-Hardware Co-Design for Video Diffusion Transformers by Exploiting Latent Space Correlations

    cs.AR 2026-07 conditional novelty 6.0 of 10

    A channel-wise reuse algorithm plus a reconfigurable systolic accelerator skips redundant vDiT attention and MLP computation, achieving up to 5.9x speedup and 16x energy savings.

  3. PISCES: Annotation-free Text-to-Video Post-Training via Optimal Transport-Aligned Rewards

    cs.CV 2026-02 conditional novelty 6.0 of 10

    PISCES post-trains text-to-video models using dual optimal-transport-aligned rewards (global quality plus token-level semantic) and outperforms annotation-based and annotation-free baselines on VBench and human evaluation.

  4. Transition Matching Distillation for Fast Video Generation

    cs.CV 2026-01 conditional novelty 6.0 of 10

    Splitting a video diffusion model into a fixed feature extractor and a small recurrent flow head lets TMD generate videos in one to two effective steps with better VBench scores than prior distilled models.

  5. Timeripple: Accelerating vDiTs by Understanding the Spatio-Temporal Correlations in Latent Space

    cs.AR 2025-11 conditional novelty 6.0 of 10

    Timeripple cuts vDiT self-attention compute by up to 85% by reusing partial attention scores of spatially and temporally correlated tokens across channels, with VBench quality essentially unchanged.

  6. HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning

    cs.CV 2025-09 conditional novelty 6.0 of 10

    HuMo uses a two-stage training scheme and a face-focus trick to generate human videos that follow text, keep a reference person's identity, and sync speech to audio, beating several single-task systems on benchmarks.

  7. Waver: Wave Your Way to Lifelike Video Generation

    cs.CV 2025-08 conditional novelty 6.0 of 10

    Waver unifies text-to-video, image-to-video, and text-to-image generation in a single 12B-parameter DiT with a hybrid dual/single-stream architecture and a cascade refiner, claiming top-three public leaderboard performance.

  8. X-UniMotion: Animating Human Images with Expressive, Unified and Identity-Agnostic Motion Latents

    cs.CV 2025-08 conditional novelty 6.0 of 10

    A self-supervised framework encodes whole-body motion into four identity-agnostic latent tokens and uses them to animate reference images, outperforming skeleton-based baselines.

  9. NeoBabel: A Multilingual Open Tower for Visual Generation

    cs.CL 2025-07 conditional novelty 6.0 of 10

    A 2B multilingual text-to-image model trained on 124M translated pairs matches or beats larger English-only baselines on English while scoring higher on the authors' multilingual benchmark extensions.

  10. DreamArt: Generating Interactable Articulated Objects from a Single Image

    cs.CV 2025-07 conditional novelty 6.0 of 10

    From one image, DreamArt generates a textured 3D articulated object with segmented moving parts and plausible motion, using a mask-prompted video diffusion model and dual quaternion joint optimization.

  11. 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.

  12. DreamActor-H1: High-Fidelity Human-Product Demonstration Video Generation via Motion-designed Diffusion Transformers

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A diffusion transformer model generates human-product demonstration videos from paired human and product images while preserving both identities through masked cross-attention and motion template guidance.

  13. PanoWan: Lifting Diffusion Video Generation Models to 360{\deg} with Latitude/Longitude-aware Mechanisms

    cs.CV 2025-05 conditional novelty 6.0 of 10

    PanoWan adapts the Wan 2.1 text-to-video model to generate seamless 360-degree videos by remapping initial noise, rotating the latent grid during denoising, and padding the latent before VAE decoding, trained on a new...

  14. 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.

  15. Physics-Driven Spatiotemporal Modeling for AI-Generated Video Detection

    cs.CV 2025-10 conditional novelty 5.0 of 10

    NSG-VD detects AI-generated videos by measuring the ratio of spatial probability gradients to temporal density changes and comparing these 'NSG' features with a maximum mean discrepancy test.

  16. RewardDance: Reward Scaling in Visual Generation

    cs.CV 2025-09 conditional novelty 5.0 of 10

    RewardDance reframes visual reward modeling as a yes/no judgment task in a VLM and reports consistent gains in text-to-image, text-to-video, and image-to-video generation as the reward model scales from 1B to 26B.

  17. From Black Box to Transparency: Enhancing Automated Interpreting Assessment with Explainable AI in College Classrooms

    cs.CL 2025-08 unverdicted novelty 5.0 of 10

    An explainable model using BLEURT, CometKiwi, pause features, and Chinese phraseological diversity predicts human-rated quality dimensions in English-Chinese consecutive interpreting, with SHAP identifying the stronge...

  18. Captain Cinema: Towards Short Movie Generation

    cs.CV 2025-07 conditional novelty 5.0 of 10

    A two-stage text-to-movie system that plans keyframes for the story and then synthesizes video between them, using a compressed memory bank to keep long narratives consistent.

  19. AlignHuman: Improving Motion and Fidelity via Timestep-Segment Preference Optimization for Audio-Driven Human Animation

    cs.CV 2025-06 conditional novelty 5.0 of 10

    Timestep-segment preference optimization with separate motion and fidelity LoRAs improves audio-driven human animation quality and allows a 3.3x inference speedup.

  20. ByteMorph: Benchmarking Instruction-Guided Image Editing with Non-Rigid Motions

    cs.CV 2025-06 conditional novelty 5.0 of 10

    A released 6.4 million pair dataset and 613 sample benchmark for instruction-guided image editing of non-rigid motions, plus a Flux.1-dev based baseline that outperforms open-source methods on the new benchmark.

  21. ATI: Any Trajectory Instruction for Controllable Video Generation

    cs.CV 2025-05 conditional novelty 5.0 of 10

    ATI injects user-drawn point trajectories as soft Gaussian feature masks into a pretrained image-to-video diffusion model, enabling unified camera, object, and local motion control.

  22. Frame-Level Captions for Long Video Generation with Complex Multi Scenes

    cs.CV 2025-05 conditional novelty 5.0 of 10

    Frame-level captions with per-frame cross-attention and parallel multi-window denoising reduce semantic confusion in long multi-scene video generation in the authors' internal evaluation.

  23. Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation

    cs.CV 2025-08 conditional novelty 4.0 of 10

    A hierarchical direct preference optimization with four alignment levels plus automated data selection improves physical plausibility of text-to-video models.

  24. Hunyuan-Game: Industrial-grade Intelligent Game Creation Model

    cs.CV 2025-05 reject novelty 4.0 of 10

    Tencent's Hunyuan-Game applies diffusion transformers to game asset creation across nine image and video generation tasks, with self-reported gains that are partly contradicted by its own evaluation table.

Pith tools