Skip to content

@CompVis CompVis - Computer Vision and Learning LMU Munich

Change the repository type filter

All

    Repositories list

    52 repositories

    • tread

      Public
      Python
      •
      Other
      •8•124•3•0•Updated Aug 26, 2025Aug 26, 2025

    • cleandift

      Public
      Jupyter Notebook
      •3•105•7•0•Updated Aug 19, 2025Aug 19, 2025

    • SCFlow

      Public
      [ICCV 2025] SCFlow: Implicitly Learning Style and Content Disentanglement with Flow Models
      Jupyter Notebook
      •
      MIT License
      •0•23•1•0•Updated Aug 12, 2025Aug 12, 2025

    • DisCLIP

      Public
      [AAAI 2025] Does VLM Classification Benefit from LLM Description Semantics?
      Python
      •0•22•0•0•Updated Aug 5, 2025Aug 5, 2025

    • discrete-interpolants

      Public
      The official implementation of "[MASK] is All You Need"
      diffusionflow-matchingstochastic-interpolantdiscrete-state
      Jupyter Notebook
      •
      Apache License 2.0
      •6•124•0•0•Updated Jul 23, 2025Jul 23, 2025

    • distilldift

      Public
      [WACV 2025] DistillDIFT: Distillation of Diffusion Features for Semantic Correspondence
      Python
      •2•27•0•0•Updated Jul 10, 2025Jul 10, 2025

    • diff2flow

      Public
      [CVPR 2025] Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment
      Python
      •
      MIT License
      •1•58•2•0•Updated Jun 4, 2025Jun 4, 2025

    • EDGS

      Public
      A PyTorch implementation of the paper "EDGS: Eliminating Densification for Efficient Convergence of 3DGS"
      reconstruction3dgs
      Jupyter Notebook
      •
      Other
      •40•565•6•6•Updated May 12, 2025May 12, 2025

    • depth-fm

      Public
      [AAAI 2025, Oral] DepthFM: Fast Monocular Depth Estimation with Flow Matching
      depth-estimationdiffusion-modelflow-matchingstochastic-interpolants
      Jupyter Notebook
      •
      MIT License
      •46•649•22•0•Updated May 6, 2025May 6, 2025

    • zigma

      Public
      A PyTorch implementation of the paper "ZigMa: A DiT-Style Mamba-based Diffusion Model" (ECCV 2024)
      mambastate-space-modeldiffusion-modelsflow-matchingzigmastochastic-interpolant
      Python
      •
      Apache License 2.0
      •22•335•6•0•Updated Mar 17, 2025Mar 17, 2025

    • maskflow

      Public
      MaskFlow: Discrete Flows For Flexible and Efficient Long Video Generation
      Jupyter Notebook
      •
      Apache License 2.0
      •3•26•1•0•Updated Mar 4, 2025Mar 4, 2025

    • attribute-control

      Public
      Fine-Grained Subject-Specific Attribute Expression Control in T2I Models
      Jupyter Notebook
      •
      MIT License
      •12•128•5•0•Updated Feb 27, 2025Feb 27, 2025

    • mask

      Public
      The official implementation of "[MASK] is All You Need"
      Jupyter Notebook
      •
      Apache License 2.0
      •6•1•0•0•Updated Feb 24, 2025Feb 24, 2025

    • fm-boosting

      Public
      [ECCV 2024, Oral] FMBoost: Boosting Latent Diffusion with Flow Matching
      super-resolutiondiffusion-modelsstable-diffusionflow-matching
      Python
      •
      MIT License
      •5•244•5•0•Updated Dec 3, 2024Dec 3, 2024

    • zigma2

      Public
      0•2•0•0•Updated Nov 29, 2024Nov 29, 2024

    • wast3d

      Public
      Official project page for the paper "WaSt-3D: Wasserstein-2 Distance for Scene-to-Scene Stylization on 3D Gaussians"
      JavaScript
      •0•5•0•0•Updated Nov 2, 2024Nov 2, 2024

    • LoRAdapter

      Public
      Python
      •5•121•2•0•Updated Oct 14, 2024Oct 14, 2024

    • taming-transformers

      Public
      Taming Transformers for High-Resolution Image Synthesis
      Jupyter Notebook
      •
      MIT License
      •1.2k•6.3k•147•20•Updated Jul 30, 2024Jul 30, 2024

    • stable-diffusion

      Public
      A latent text-to-image diffusion model
      Jupyter Notebook
      •
      Other
      •11k•71k•532•75•Updated Jun 18, 2024Jun 18, 2024

    • latent-diffusion

      Public
      High-Resolution Image Synthesis with Latent Diffusion Models
      Jupyter Notebook
      •
      MIT License
      •1.7k•13k•272•19•Updated Feb 29, 2024Feb 29, 2024

    • instant-lora-composition

      Public
      MIT License
      •1•31•0•0•Updated Dec 8, 2023Dec 8, 2023

    • cuneiform-sign-detection-dataset

      Public
      Dataset provided with the article "Deep learning for cuneiform sign detection with weak supervision using transliteration alignment". It comprises image references, transliterations and sign annotations of clay tablets from the Neo-Assyrian epoch.
      Jupyter Notebook
      •7•17•1•0•Updated Aug 24, 2023Aug 24, 2023

    • cuneiform-sign-detection-code

      Public
      Code for the article "Deep learning of cuneiform sign detection with weak supervision using transliteration alignment"
      Jupyter Notebook
      •7•9•1•0•Updated Aug 24, 2023Aug 24, 2023

    • geometry-free-view-synthesis

      Public
      Is a geometric model required to synthesize novel views from a single image?
      novel-view-synthesistransformers
      Python
      •
      MIT License
      •35•381•9•2•Updated Apr 16, 2023Apr 16, 2023

    • retrieval-augmented-diffusion-models

      Public
      Official codebase for the Paper “Retrieval-Augmented Diffusion Models”
      Jupyter Notebook
      •
      Other
      •8•135•3•0•Updated Apr 5, 2023Apr 5, 2023

    • ipoke

      Public
      iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis
      Python
      •10•53•3•1•Updated Dec 21, 2022Dec 21, 2022

    • net2net

      Public
      Network-to-Network Translation with Conditional Invertible Neural Networks
      lightningpytorchgenerative-modelinngansnormalizing-flowsstreamlitautoencoderspytorch-lightning
      Python
      •21•227•6•1•Updated Dec 20, 2022Dec 20, 2022

    • interactive-image2video-synthesis

      Public
      Python
      •
      MIT License
      •15•58•0•1•Updated Dec 18, 2022Dec 18, 2022

    • behavior-driven-video-synthesis

      Public
      Python
      •
      Apache License 2.0
      •8•27•0•1•Updated Dec 15, 2022Dec 15, 2022

    • imagebart

      Public
      ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis
      Python
      •14•125•4•0•Updated Mar 14, 2022Mar 14, 2022