pith. sign in

arxiv: 2304.08818 · v2 · pith:V2JSTAMLnew · submitted 2023-04-18 · 💻 cs.CV · cs.LG

Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models

classification 💻 cs.CV cs.LG
keywords diffusionmodelvideoimagelatentldmsmodelsresolution
0
0 comments X
read the original abstract

Latent Diffusion Models (LDMs) enable high-quality image synthesis while avoiding excessive compute demands by training a diffusion model in a compressed lower-dimensional latent space. Here, we apply the LDM paradigm to high-resolution video generation, a particularly resource-intensive task. We first pre-train an LDM on images only; then, we turn the image generator into a video generator by introducing a temporal dimension to the latent space diffusion model and fine-tuning on encoded image sequences, i.e., videos. Similarly, we temporally align diffusion model upsamplers, turning them into temporally consistent video super resolution models. We focus on two relevant real-world applications: Simulation of in-the-wild driving data and creative content creation with text-to-video modeling. In particular, we validate our Video LDM on real driving videos of resolution 512 x 1024, achieving state-of-the-art performance. Furthermore, our approach can easily leverage off-the-shelf pre-trained image LDMs, as we only need to train a temporal alignment model in that case. Doing so, we turn the publicly available, state-of-the-art text-to-image LDM Stable Diffusion into an efficient and expressive text-to-video model with resolution up to 1280 x 2048. We show that the temporal layers trained in this way generalize to different fine-tuned text-to-image LDMs. Utilizing this property, we show the first results for personalized text-to-video generation, opening exciting directions for future content creation. Project page: https://research.nvidia.com/labs/toronto-ai/VideoLDM/

This paper has not been read by Pith yet.

discussion (0)

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

Forward citations

Cited by 10 Pith papers

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

  1. Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution

    cs.CL 2023-09 unverdicted novelty 8.0

    Promptbreeder evolves both task prompts and the mutation prompts that improve them using LLMs, outperforming Chain-of-Thought and Plan-and-Solve on arithmetic and commonsense reasoning benchmarks.

  2. 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.

  3. Learning Interactive Real-World Simulators

    cs.AI 2023-10 conditional novelty 7.0

    UniSim learns a universal real-world simulator from orchestrated diverse datasets, enabling zero-shot deployment of policies trained purely in simulation.

  4. A Systematic Study of Behavioral Cloning for Scientific Data Annotation

    cs.HC 2026-05 unverdicted novelty 6.0

    Introduces 9 synthetic annotation tasks and benchmarks for behavioral cloning, finding hierarchical skill learning, scaling benefits, effective multi-task pretraining, and shared internal representations of task phase...

  5. SwiftI2V: Efficient High-Resolution Image-to-Video Generation via Conditional Segment-wise Generation

    cs.CV 2026-05 unverdicted novelty 6.0

    SwiftI2V achieves comparable 2K I2V quality to end-to-end models on VBench-I2V while cutting GPU time by 202x through low-resolution motion planning followed by strongly image-conditioned segment-wise high-resolution ...

  6. SwiftI2V: Efficient High-Resolution Image-to-Video Generation via Conditional Segment-wise Generation

    cs.CV 2026-05 unverdicted novelty 6.0

    SwiftI2V matches end-to-end 2K I2V quality on VBench while cutting GPU time by 202x via conditional segment-wise generation that bounds token cost and preserves input fidelity.

  7. Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets

    cs.CV 2023-11 conditional novelty 6.0

    Stable Video Diffusion scales latent video diffusion models via text-to-image pretraining, video pretraining on curated data, and high-quality finetuning to produce competitive text-to-video and image-to-video results...

  8. SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

    cs.CV 2023-07 conditional novelty 6.0

    SDXL improves upon prior Stable Diffusion versions through a larger UNet backbone, dual text encoders, novel conditioning, and a refinement model, producing higher-fidelity images competitive with black-box state-of-t...

  9. BioVid: Autoregressive Video Generation with Biological Behavior Semantic Comprehension

    cs.CV 2026-06 unverdicted novelty 5.0

    BioVid is a data-driven autoregressive model using 2D-encode/3D-decode tokenization and causal Transformer with EOS termination that reproduces real action duration distributions (W1 distance 1.24 frames) on NTU RGB+D...

  10. DisagFusion: Asynchronous Pipeline Parallelism and Elastic Scheduling for Disaggregated Diffusion Serving

    cs.DC 2026-05 unverdicted novelty 5.0

    DisagFusion achieves 3.4x-20.5x higher throughput and 18.5x lower latency for diffusion serving via asynchronous pipeline parallelism and elastic hybrid scheduling on disaggregated hardware.