Skip to content

Computer Vision & Learning Group

  • Home
  • People
  • Publications
  • Research
  • Teaching
  • Open Positions
  • Contact
  • Menu

Stable Diffusion in the Press

Stable Diffusion came from the Machine Vision & Learning research group (CompVis) @LMU_Muenchen, dig into more of their amazing research here: https://t.co/4V0eNqI3fd

More to come 🚀 https://t.co/MNC0JSvQk6

— Emad (@EMostaque) November 2, 2022
Pineappowl

“Wie ein deutscher KI-Forscher das Silicon Valley verblüfft”

“Wie ein Münchner KI-Professor gegen den Größenwahn der Branche kämpft”

“Die vielen Möglichkeiten der generativen KI”

“Generative KI & die Transformation medialer Kommunikation”

“Künstliche Zukunft – Gefährdet KI die Demokratie?”

“Der KI-Bildgenerator Stable Diffusion stammt aus München – und soll KI ‘demokratisieren'”

“Text-zu-Bild-Revolution: Stable Diffusion ermöglicht KI-Bildgenerieren für alle”

“Demokratisierung von Kunst”

“Die digitalen Apokalypsen wie auch die Weltrettungsfantasien sind letztlich Werbetrommelzüge dieser Industrie”

“Wie künstliche Intelligenz die Kreativwelt revolutioniert”

„Stable Diffusion“-Erfinder Björn Ommer: Kluger Umgang mit KI kann Gutes bewirken

“AI’s sudden big leap forward into usefulness”

Stable Diffusion most influential CVPR’22 paper and VQGAN top 12 in CVPR’21

News

Foundation Model Initiative

Stable Diffusion - Advanced image synthesis for all!
Stable Diffusion in the Press

Open PhD and PostDoc Positions

2025


  • 4 papers accepted at ICCV’25

  • Generative AI and the Future of Intelligence, Opening Keynote at re:publica'25

  • The European Way. A Blueprint for Reclaiming Our Digital Future

  • 4 papers accepted at CVPR’25:
    • CleanDIFT: Diffusion Features without Noise (ORAL)
    • Attribute Control in T2I by Semantic Directions
    • Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment
    • Latent Drifting in Diffusion for Counterfactual Synthesis (Highlight)

  • 2 papers (DepthFM & DisCLIP) at AAAI’25 + 1 paper at WACV’25

  • Awarded Technology-Prize of Eduard-Rhein-Foundation

  • Medical Physics article on analyzing CT enhancement

  • 2024


  • Awarded German AI-Prize’24

  • Nominated German Future Prize of the President of Germany

  • 4 papers accepted at ECCV'24 on:
    • Conditional LoRAs for 0-Shot Control & Altering of T2I-Models
    • ZigMa: Zigzag Mamba Diffusion Model
    • 3D Gaussian Splatting for 3D Stylization using Wasserstein-2 Distance
    • Flow Matching for Boosting Latent Diffusion

  • Eurographics overview article on Diffusion Models

  • Medical Physics article on benchmarking AI-based CT image denoising

  • 2022


  • GCPR'22 Honorable Mention for paper on ArtFID: Quantitative Evaluation of Neural Style Transfer

  • NeurIPS'22 article on retrieval-augmented diffusion models

  • Nature article using image registration to analyze neuropathic pain

  • CVPR'22 tutorial on Deep Visual Similarity and Metric Learning

  • T-PAMI publication accepted on
    • Shared feature learning for Deep Metric Learning (PDF Download)

  • CVPR'22 on latent diffusion models for high-res image synthesis, a.k.a. LDM & Stable Diffusion, source code & models
  • 2021


  • PLOS ONE article on Interactive Retrieval in Art Collections

  • 2 papers accepted at NeurIPS'21 on:
    • Multinomial Diffusion for Improving Autoregressive Image Synthesis
    • Analyzing OOD Generalization in Deep Metric Learning

  • T-PAMI publication accepted on
    • Improving Deep Metric Learning by divide and conquer (PDF Download)

  • Nature Machine Intelligence article on unsupervised behavior analysis & magnification (uBAM) for biomedical diagnostics

  • 3 papers accepted at ICCV'21 on:
    • Transformers for Geometry-Free 3D Novel-View Synthesis
    • iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis
    • Self-Supervised LiDAR Scene Flow and Motion Segmentation (ORAL)

  • ICML'21 paper accepted on self-distillation for deep metric learning

  • 6 papers accepted at CVPR'21 on:
    • Taming Transformers for Hi-Res Image Synthesis
    • Learning Object Dynamics for Interactive Video Synthesis
    • Stochastic Image-to-Video Synthesis
    • Stroke-based Style Transfer
    • Behavior-driven Synthesis of Human Dynamics
    • Learning Exposure Correction

  • Best Paper Award at CVPR'21—AI for Content Creation WS on
    • High-Res Complex Scene Synthesis with Transformers

  • ICRA'21 paper accepted on 3D object detection
  • 2020


  • NeurIPS'20 ORAL on cINNs for Network-to-Network Translation

  • T-PAMI publication accepted on
    • Shared feature learning for Deep Metric Learning

  • PLoS ONE publication on weakly supervised transliteration alignment for cuneiform sign detection

  • GCPR'20 ORAL on unsupervised part learning by disentangling

  • 2 papers accepted at ECCV'20 on:
    • Explainable AI and semantic image manipulation
    • Deep Metric Learning beyond discriminative features

  • ICML'20 paper accepted on
    • Generalization in Deep Metric Learning

  • Best Paper Award at CVPR'20—AI for Content Creation WS on
    • Interpretable Models for Visual Synthesis

  • 3 papers accepted at CVPR'20 on:
    • Explainable AI
    • Reinforcement Learning for Deep Metric Learning
    • Unsupervised Behavior Analytics
  • 2019


  • 3 papers accepted at ICCV'19

  • Best paper finalist at CVPR'19

  • 3 papers accepted at CVPR'19
  • Categories

    • No categories
    Imprint | Privacy Policy
    A SiteOrigin Theme