Pith. sign in

REVIEW 20 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

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

classification cs.CV cs.AI
keywords modelseaweed-7bvideogenerationperformancetrainedtrainingdesign
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
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 with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 20 Pith papers

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

  1. Explicit Critic Guidance for Aligning Diffusion Models

    cs.LG 2026-05 unverdicted novelty 7.0

    Introduces a state-aligned latent actor-critic framework that lets diffusion models act as their own timestep-conditioned value functions for trajectory-level RL post-training and inference steering.

  2. EM-Vid: Training-Free Entity-Centric Memory for Efficient and Consistent Multi-Shot Video Generation

    cs.CV 2026-05 unverdicted novelty 7.0

    EM-Vid introduces an entity-centric latent patch memory bank with sparse token conditioning and budgeted updates for training-free consistent multi-shot video generation.

  3. Grounded Forcing: Bridging Time-Independent Semantics and Proximal Dynamics in Autoregressive Video Synthesis

    cs.CV 2026-04 unverdicted novelty 7.0

    Grounded Forcing introduces dual memory caching, reference-based positional embeddings, and proximity-weighted recaching to bridge stable semantics with local dynamics, improving long-range consistency in autoregressi...

  4. Mind the Generative Details: Direct Localized Detail Preference Optimization for Video Diffusion Models

    cs.CV 2026-01 unverdicted novelty 7.0

    LocalDPO aligns text-to-video diffusion models with human preferences at the spatio-temporal region level by automatically generating localized preference pairs from corrupted real videos and applying a region-aware DPO loss.

  5. Mind the Generative Details: Direct Localized Detail Preference Optimization for Video Diffusion Models

    cs.CV 2026-01 unverdicted novelty 7.0

    LocalDPO creates localized preference pairs from real videos by applying random spatio-temporal masks and restoring masked regions with the frozen base model, then applies region-restricted DPO loss to improve fidelit...

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

    cs.AR 2026-07 conditional novelty 6.0

    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.

  7. HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers

    cs.CV 2026-06 unverdicted novelty 6.0

    HYDRA-X presents the first unified multimodal model using a single ViT for holistic image-video tokenization, with ablations on attention and compression plus a latent-level editing improvement.

  8. Leveraging Verifier-Based Reinforcement Learning in Image Editing

    cs.CV 2026-04 unverdicted novelty 6.0

    Edit-R1 trains a CoT-based reasoning reward model with GCPO and uses it to boost image editing performance over VLMs and models like FLUX.1-kontext via GRPO.

  9. Leveraging Verifier-Based Reinforcement Learning in Image Editing

    cs.CV 2026-04 unverdicted novelty 6.0

    Edit-R1 builds a CoT-based reasoning reward model (RRM) via SFT and GCPO, then applies it with GRPO to improve image editing models such as FLUX.1-kontext.

  10. Continuous Adversarial Flow Models

    cs.LG 2026-04 unverdicted novelty 6.0

    Continuous adversarial flow models replace MSE in flow matching with adversarial training via a discriminator, improving guidance-free FID on ImageNet from 8.26 to 3.63 for SiT and similar gains for JiT and text-to-im...

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

    cs.CV 2026-02 conditional novelty 6.0

    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.

  12. Transition Matching Distillation for Fast Video Generation

    cs.CV 2026-01 conditional novelty 6.0

    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.

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

    cs.AR 2025-11 conditional novelty 6.0

    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.

  14. Rolling Forcing: Autoregressive Long Video Diffusion in Real Time

    cs.CV 2025-09 unverdicted novelty 6.0

    Rolling Forcing generates multi-minute videos in real time by jointly denoising frames at increasing noise levels, anchoring attention to early frames, and using windowed distillation to limit error accumulation.

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

    cs.CV 2025-10 conditional novelty 5.0

    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. Emerging Properties in Unified Multimodal Pretraining

    cs.CV 2025-05 unverdicted novelty 5.0

    BAGEL is a unified decoder-only model that develops emerging complex multimodal reasoning abilities after pretraining on large-scale interleaved data and outperforms prior open-source unified models.

  17. Show-o2: Improved Native Unified Multimodal Models

    cs.CV 2025-06 unverdicted novelty 4.0

    Show-o2 unifies text, image, and video understanding and generation in a single autoregressive-plus-flow-matching model built on 3D causal VAE representations.

  18. Seedance 1.0: Exploring the Boundaries of Video Generation Models

    cs.CV 2025-06 unverdicted novelty 4.0

    Seedance 1.0 generates 5-second 1080p videos in about 41 seconds with claimed superior motion quality, prompt adherence, and multi-shot consistency compared to prior models.

  19. Seedance 2.0: Advancing Video Generation for World Complexity

    cs.CV 2026-04 unverdicted novelty 3.0

    Seedance 2.0 is an updated multi-modal model for generating 4-15 second audio-video content at 480p/720p with support for up to 3 video, 9 image, and 3 audio references.

  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.